AI-based intelligent vegetable seedling grafting management system

Abstract

The present invention discloses an AI-based intelligent vegetable seedling grafting management system, which relates to the technical field of seedling grafting. The technical solution deploys sensors in vegetable seedling sub-areas through an environmental data acquisition module to collect seedling environment-related data, and obtains vegetable grafting-related data through a health monitoring unit; the data is transmitted to an AI model database after preprocessing, and an environmental adaptability index Epj is analyzed and calculated, and compared and evaluated with an environmental adaptability threshold Q. When the environmental adaptability index is higher than the environmental adaptability threshold Q, an early warning is issued; at the same time, a growth risk coefficient Sfxs is calculated and evaluated to identify potential threats; a grafting process control module automatically calculates the optimal grafting interval duration Tjw through an AI algorithm and adjusts the grafting time; the smart seedling management module adjusts management measures based on the comparison results of the growth risk coefficient and the environmental adaptability index, including adjusting the irrigation amount, optimizing the light, and improving the soil oxygen supply, to achieve intelligent seedling management.

Description

Technical Field

[0001] The present invention relates to the technical field of seedling cultivation and grafting, and in particular to an AI-based intelligent vegetable seedling cultivation and grafting management system. Background Art

[0002] The vegetable seedling grafting management system originated from the vegetable seedling grafting technology in traditional agriculture. With the development of modern agricultural informatization, it has gradually integrated sensor technology, automatic control and data analysis to form an intelligent management model. The system can effectively improve the grafting efficiency, seedling survival rate, and optimize the environmental control during the seedling raising process.

[0003] However, the existing agricultural research institutions, although the vegetable seedling grafting management system used to improve the disease resistance of vegetable varieties has a certain level of intelligence, still has some technical shortcomings:

[0004] 1. Incomplete data collection and analysis: The data collected by the current system may be limited to environmental parameters and some indicators in the grafting process. There is a lack of in-depth collection and analysis of comprehensive parameters such as soil, water, and light, which makes it impossible to fully optimize the seedling environment.

[0005] 2. Low system integration: Many existing management systems cannot achieve seamless integration with other agricultural production links, such as real-time linkage with planting, irrigation and fertilization systems, resulting in data islands and affecting overall planting efficiency.

[0006] 3. Insufficient intelligence: The level of automation and intelligence in the system is low, and there is a lack of precise automated operations and intelligent decision-making support, which makes it impossible to achieve comprehensive unmanned management and still requires a lot of manual intervention. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides an AI-based intelligent vegetable seedling and grafting management system, which solves the technical shortcomings of incomplete data collection and analysis, low system integration and insufficient intelligence mentioned in the background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI-based intelligent vegetable seedling and grafting management system, characterized in that it includes an environmental data acquisition module, a data processing module, an intelligent analysis module, a grafting process control module and a smart seedling management module;

[0009] The environmental data acquisition module is used to divide the vegetable seedling raising area into several vegetable seedling raising sub-areas, and mark the vegetable seedling raising sub-areas, including YM1, YM2...YMn; then deploy sensors in each vegetable seedling raising sub-area to monitor and collect seedling raising environment related data in real time; then monitor the health status of grafted seedlings in the vegetable seedling raising sub-area in real time and collect vegetable grafting related data, and obtain the grafting success rate Jcs by calculation;

[0010] The data processing module is used to pre-process and normalize the seedling raising environment-related data in the vegetable seedling raising sub-area, and then preliminarily screen and store the collected seedling raising environment-related data through data fusion technology, and finally transmit the processed seedling raising environment-related data to the AI ​​model database;

[0011] The intelligent analysis module is used to extract the seedling environment related data in the AI ​​model database and use the AI ​​algorithm for intelligent analysis to build an environmental adaptability assessment model; then calculate and evaluate the environmental adaptability index Epj in the vegetable seedling sub-area, and issue an early warning instruction for the environment of the current vegetable seedling sub-area; finally, calculate and evaluate the growth risk coefficient Sfxs of the grafted seedlings in the current vegetable seedling sub-area based on the evaluation content of the environmental adaptability index Epj;

[0012] The grafting process control module is used to adjust the relevant environmental parameters during vegetable grafting according to the evaluation content of the growth risk coefficient Sfxs; then the optimal grafting interval time Tjw suitable for the vegetable variety is obtained by calculation and evaluated, and the grafting interval time period is automatically adjusted through the AI ​​algorithm according to the evaluation content of the optimal grafting interval time Tjw;

[0013] The smart seedling management module is used to compare and analyze the growth risk coefficient Sfxs and the environmental adaptation index Epj, and adjust the seedling management measures of the current vegetable seedling sub-area according to the analysis results.

[0014] Preferably, the environmental data acquisition module includes a sensor deployment acquisition unit and a health monitoring unit;

[0015] The sensor deployment and collection unit deploys different types of sensors in each vegetable seedling area according to the plant layout and environmental characteristics in different vegetable seedling areas, and calibrates each sensor, and uses the calibrated sensors to monitor and collect seedling environment related data in real time; the seedling environment related data includes soil moisture Tsh, light intensity Gzq, temperature Wd, air humidity Ksh, soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, soil pH value Ph and nutrient content Yf.

[0016] Preferably, the health monitoring unit is used to monitor the health status of grafted seedlings in the vegetable seedling raising area in real time and collect vegetable grafting related data, wherein the vegetable grafting related data includes the total number of grafted vegetables Mzs, water flow rate Msl, stomatal conductance Mqk and chlorophyll content Myl; after extracting the vegetable grafting related data and performing dimensionless processing, the grafting success rate Jcs is calculated by the following formula:

[0017] .

[0018] Preferably, the data processing module is used to filter out non-compliant data in the seedling environment related data, including outliers and missing values; then the pre-processed seedling environment related data is normalized, and finally the seedling environment related data is fused by a weighted average algorithm based on the relationship between parameters in different seedling environment related data.

[0019] Preferably, the intelligent analysis module includes an AI model building unit, an early warning issuing unit and a risk assessment unit;

[0020] The AI ​​model building unit is used to build an environmental adaptability assessment model;

[0021] The warning issuing unit extracts soil moisture Tsh, light intensity Gzq, temperature Wd and grafting success rate Jcs and performs dimensionless processing, and then calculates the environmental adaptation index Epj using the following formula:

[0022] ;

[0023] Then, the preset environmental adaptability threshold Q is compared with the environmental adaptability index Epj for evaluation, and an early warning is issued based on the evaluation content. The specific evaluation content is as follows:

[0024] If the environmental adaptability threshold Q ≥ environmental adaptability index Epj, it means that the current environmental status in the vegetable seedling raising sub-area is normal and suitable for the growth of grafted seedlings, and no adjustment measures are needed. Then further analysis is carried out, including calculating the growth risk coefficient Sfxs and identifying potential growth threats;

[0025] If the environmental adaptability threshold Q is less than the environmental adaptability index Epj, it means that the current environmental conditions in the vegetable seedling raising sub-area are abnormal and not suitable for the growth of grafted seedlings. At this time, an early warning is issued to remind the management personnel to make adjustments.

[0026] Preferably, the risk assessment unit calculates the growth risk coefficient Sfxs in the current vegetable seedling raising sub-area by extracting the soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Th1, air humidity Ksh and nutrient content Yf from the seedling raising environment related data. The specific calculation formula of the growth risk coefficient Sfxs is:

[0027] ;

[0028] Where a is the first correction constant;

[0029] The preset growth risk threshold W is compared with the growth risk coefficient Sfxs to evaluate and identify potential growth threats based on the evaluation content. The specific evaluation content is as follows:

[0030] If the growth risk threshold W> the growth risk coefficient Sfxs, it means that there is no potential growth threat to the grafted seedlings in the current vegetable seedling raising sub-area; at this time, the manager continues to maintain the existing environmental control strategy and no intervention is required;

[0031] If the growth risk threshold W ≤ the growth risk coefficient Sfxs, it means that there is a potential growth threat to the grafted seedlings in the current vegetable seedling raising area, including abnormal soil electrical conductivity Tdd leading to salt accumulation, abnormal root respiration rate Ghx and soil oxygen content Th1; intervention measures should be taken at this time.

[0032] Preferably, the grafting process control module includes an environmental parameter adjustment unit and a grafting time control unit;

[0033] The environmental parameter adjustment unit is used to take intervention measures according to the potential growth threats output by the intelligent analysis module, including dynamically adjusting the environmental parameters involved in the seedling raising process, wherein the environmental parameters include soil electrical conductivity Tdd, root respiration rate Ghx and soil oxygen content Th1. The intervention measures taken include adjusting the oxygen in the soil through oxygenation equipment, adjusting the salt in the soil and controlling the air humidity to achieve the environmental conditions required for the grafting process.

[0034] Preferably, the grafting time control unit calculates the optimal grafting interval Tjw of the vegetable variety by extracting the vegetable grafting related data and the seedling raising environment related data and performing dimensionless processing. The specific calculation formula is as follows:

[0035] ;

[0036] In the formula, n represents the number of time points collected, Zsl represents the transpiration rate of seedlings in the vegetable grafting related data, represents the transpiration rate of seedlings at the i-th time point, represents the root respiration rate at the i-th time point, Ghxy represents the standard value of the root respiration rate in the vegetable grafting related data, g represents the second correction constant, d is the base of the natural logarithm, and f represents the regularization parameter, which is used to control the influence of the root respiration rate deviation.

[0037] Preferably, the grafting time control unit compares and evaluates the preset optimal grafting time interval threshold R with the optimal grafting interval time Tjw, and the specific evaluation content is as follows:

[0038] When the optimal grafting interval threshold R ≥ the optimal grafting interval Tjw, it means that the current grafting interval meets the requirements and there is no need to adjust the grafting interval.

[0039] When the optimal grafting time interval threshold R is less than the optimal grafting time interval Tjw, it means that the current grafting time interval does not meet the requirements. The grafting time period is automatically adjusted according to the AI ​​algorithm. The specific implementation process is as follows: input the optimal grafting time interval Tjw and related parameters, then call the AI ​​algorithm model to analyze all input data, and finally generate a time adjustment strategy.

[0040] Preferably, the smart seedling management module compares and evaluates the growth risk coefficient Sfxs with the environmental adaptation index Epj to generate the following evaluation results:

[0041] When the growth risk coefficient Sfxs ≤ the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are normal, and the first assessment result is generated at this time;

[0042] When the growth risk coefficient Sfxs ≤ the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are abnormal, and the second evaluation result is generated at this time;

[0043] The smart seedling management module adjusts the seedling management measures of the current vegetable seedling sub-area according to the first evaluation result and the second evaluation result respectively; specifically:

[0044] When the first evaluation result is generated, the current vegetable seedling raising sub-area continues to be managed according to the established management plan, and continues to pay attention to the changes in the growth risk coefficient Sfxs and the environmental adaptation index Epj;

[0045] When the second assessment result is generated, identify the main sources of risk and adjust the corresponding parameters in a timely manner, including excessive soil moisture leading to root hypoxia, adjusting irrigation volume and soil drainage; if excessive light affects seedling growth, adjust the light intensity through shade nets.

[0046] The present invention provides an AI-based intelligent vegetable seedling and grafting management system, which has the following beneficial effects:

[0047] (1) This AI-based intelligent vegetable seedling grafting management system solves the problem of incomplete data collection and analysis through precise environmental data collection and analysis. The environmental data collection module of this system deploys a variety of sensors in the vegetable seedling sub-area to collect key parameters such as soil moisture Tsh, light intensity Gzq, temperature Wd, air humidity Ksh, soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, soil pH value Ph and nutrient content Yf in real time. At the same time, the health monitoring unit collects grafting-related data such as water flow rate Msl, stomatal conductance Mqk and chlorophyll content Myl of grafted seedlings. After preprocessing and normalization, these data are transmitted to the AI ​​model database for fusion analysis, ensuring the comprehensiveness and accuracy of data collection.

[0048] (2) This AI-based intelligent vegetable seedling and grafting management system integrates data processing modules and intelligent analysis modules to address the technical shortcomings of low system integration. It uses AI algorithms to conduct in-depth analysis of data in different vegetable seedling sub-areas. The environmental adaptability index Epj is calculated through the environmental adaptability assessment model and compared with the preset environmental adaptability threshold Q for evaluation. When the environmental adaptability index Epj is higher than the environmental adaptability threshold Q, the system issues an early warning. The system also further calculates the growth risk coefficient Sfxs, and combines soil electrical conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, air humidity Ksh, and nutrient content Yf to conduct a comprehensive risk assessment and identify potential growth threats. All modules are integrated smoothly, making the entire grafting management process a closed loop at the data processing, analysis, and decision-making levels.

[0049] (3) In order to solve the problem of insufficient intelligence, the grafting process control module in the AI-based vegetable seedling grafting management system automatically calculates the optimal grafting interval Tjw through the AI ​​algorithm and dynamically adjusts the grafting time period. At the same time, the smart seedling management module automatically adjusts the management measures of the current vegetable seedling sub-area based on the comparative evaluation results of Sfxs and the environmental adaptability index Epj. When the growth risk is higher than the environmental adaptability, the system takes timely intervention measures according to the risk source, including adjusting the irrigation amount, improving the soil oxygen supply, optimizing the light intensity, etc. This closed-loop control mechanism improves the intelligence level of the system, reduces human intervention, and realizes the intelligent management and optimization of the seedling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of the framework structure of the AI-based vegetable intelligent seedling and grafting management system of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Example 1

[0053] See also Figure 1 , the present invention provides an AI-based intelligent vegetable seedling and grafting management system, which is characterized by: including an environmental data acquisition module, a data processing module, an intelligent analysis module, a grafting process control module and a smart seedling management module;

[0054] The environmental data acquisition module is used to divide the vegetable seedling raising area into several vegetable seedling raising sub-areas, and mark the vegetable seedling raising sub-areas, including YM1, YM2...YMn; then deploy sensors in each vegetable seedling raising sub-area to monitor and collect seedling raising environment related data in real time; then monitor the health status of grafted seedlings in the vegetable seedling raising sub-area in real time and collect vegetable grafting related data, and obtain the grafting success rate Jcs by calculation;

[0055] The data processing module is used to pre-process and normalize the seedling raising environment-related data in the vegetable seedling raising sub-area, and then preliminarily screen and store the collected seedling raising environment-related data through data fusion technology, and finally transmit the processed seedling raising environment-related data to the AI ​​model database;

[0056] The intelligent analysis module is used to extract the seedling environment related data in the AI ​​model database and use the AI ​​algorithm for intelligent analysis to build an environmental adaptability assessment model; then calculate and evaluate the environmental adaptability index Epj in the vegetable seedling sub-area, and issue an early warning instruction for the environment of the current vegetable seedling sub-area; finally, calculate and evaluate the growth risk coefficient Sfxs of the grafted seedlings in the current vegetable seedling sub-area based on the evaluation content of the environmental adaptability index Epj;

[0057] The grafting process control module is used to adjust the relevant environmental parameters during vegetable grafting according to the evaluation content of the growth risk coefficient Sfxs; then the optimal grafting interval time Tjw suitable for the vegetable variety is obtained by calculation and evaluated, and the grafting interval time period is automatically adjusted through the AI ​​algorithm according to the evaluation content of the optimal grafting interval time Tjw;

[0058] The smart seedling management module is used to compare and analyze the growth risk coefficient Sfxs and the environmental adaptation index Epj, and adjust the seedling management measures of the current vegetable seedling sub-area according to the analysis results.

[0059] In this embodiment, the environmental data acquisition module can accurately divide the vegetable seedling raising area and mark different vegetable seedling raising sub-areas, and monitor the soil moisture Tsh, light intensity Gzq, temperature Wd, air humidity Ksh, soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Th1, soil pH value Ph and nutrient content Yf in real time by deploying sensors to ensure comprehensive and accurate data collection; the data processing module can effectively pre-process and normalize the collected data, optimize data screening and storage through data fusion technology, and improve data processing efficiency; the intelligent analysis module constructs an environmental adaptability assessment model through AI algorithm, calculates the environmental adaptability index Epj and issues an early warning, further evaluates the growth risk coefficient Sfxs, and ensures accurate identification of potential growth threats; the grafting process control module can dynamically adjust the environmental parameters during grafting, calculate the optimal grafting interval Tjw for different vegetable varieties, and realize intelligent adjustment of the grafting time period; the intelligent seedling management module can optimize the seedling management measures according to the comparative analysis results of Sfxs and the environmental adaptability index Epj, to ensure that the system efficiently manages the seedling process throughout the process.

[0060] Example 2

[0061] The environmental data acquisition module includes a sensor deployment acquisition unit and a health monitoring unit;

[0062] The sensor deployment and collection unit deploys different types of sensors in each vegetable seedling area according to the plant layout and environmental characteristics in different vegetable seedling areas, and calibrates each sensor, and uses the calibrated sensors to monitor and collect seedling environment related data in real time; the seedling environment related data includes soil moisture Tsh, light intensity Gzq, temperature Wd, air humidity Ksh, soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, soil pH value Ph and nutrient content Yf.

[0063] The health monitoring unit is used to monitor the health status of grafted seedlings in the vegetable seedling raising area in real time and collect vegetable grafting related data, which includes the total number of grafted vegetables Mzs, water flow rate Msl, stomatal conductance Mqk and chlorophyll content Myl; after extracting the vegetable grafting related data and performing dimensionless processing, the grafting success rate Jcs is calculated by the following formula:

[0064] .

[0065] In this embodiment, the environmental data acquisition module can comprehensively monitor the environmental conditions of the vegetable seedling area and the growth of grafted seedlings through the combination of the sensor deployment acquisition unit and the health monitoring unit; the data acquisition unit deploys and calibrates different types of sensors according to the plant layout and environmental characteristics of different vegetable seedling areas, and collects soil moisture Tsh to reflect soil moisture supply; light intensity Gzq affects photosynthesis; temperature Wd affects growth metabolic rate; air humidity Ksh affects transpiration; soil conductivity Tdd represents soil salinity; root respiration rate Ghx represents root activity; soil oxygen content Thl directly affects normal root respiration; soil pH value Ph affects nutrient absorption; nutrient content Yf ensures normal growth and nutrient supply of seedlings; the total number of grafted vegetables Mzs, water flow rate Msl, stomatal conductance Mqk and chlorophyll content Myl collected by the health monitoring unit can reflect the overall health status and grafting success rate of grafted seedlings, and these dimensionless processed data are calculated through formulas to obtain the grafting success rate Jcs, providing a reliable basis for optimizing grafting management.

[0066] Example 3

[0067] The data processing module is used to filter out non-compliant data in the seedling environment related data, including outliers and missing values; then the pre-processed seedling environment related data is normalized, and finally the seedling environment related data is fused through a weighted average algorithm based on the relationship between parameters in different seedling environment related data.

[0068] In this embodiment, the accuracy and completeness of the data are ensured by filtering out non-compliant data in the seedling environment-related data, including outliers and missing values; the preprocessed data are normalized so that parameters of different dimensions can be analyzed on the same scale to avoid distortion of the results due to large differences in numerical ranges; finally, the module fuses the data of each parameter through a weighted average algorithm, taking into account the relative importance of different parameters to the seedling environment, and improving the scientificity and rationality of the overall data analysis; the operation of this module ensures the efficient processing of system data, making subsequent intelligent analysis and decision-making more accurate.

[0069] Example 4

[0070] The intelligent analysis module includes an AI model building unit, an early warning issuing unit and a risk assessment unit;

[0071] The AI ​​model building unit is used to build an environmental adaptability assessment model;

[0072] The warning issuing unit extracts soil moisture Tsh, light intensity Gzq, temperature Wd and grafting success rate Jcs and performs dimensionless processing, and then calculates the environmental adaptation index Epj using the following formula:

[0073] ;

[0074] Then, the preset environmental adaptability threshold Q is compared with the environmental adaptability index Epj for evaluation, and an early warning is issued based on the evaluation content. The specific evaluation content is as follows:

[0075] If the environmental adaptability threshold Q ≥ environmental adaptability index Epj, it means that the current environmental status in the vegetable seedling raising sub-area is normal and suitable for the growth of grafted seedlings, and no adjustment measures are needed. Then further analysis is carried out, including calculating the growth risk coefficient Sfxs and identifying potential growth threats;

[0076] If the environmental adaptability threshold Q is less than the environmental adaptability index Epj, it means that the current environmental conditions in the vegetable seedling raising sub-area are abnormal and not suitable for the growth of grafted seedlings. At this time, an early warning is issued to remind the management personnel to make adjustments.

[0077] The risk assessment unit calculates the growth risk coefficient Sfxs in the current vegetable seedling raising sub-area by extracting soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Th1, air humidity Ksh and nutrient content Yf from the seedling raising environment related data. The specific calculation formula of the growth risk coefficient Sfxs is:

[0078] ;

[0079] Where a is the first correction constant;

[0080] The preset growth risk threshold W is compared with the growth risk coefficient Sfxs to evaluate and identify potential growth threats based on the evaluation content. The specific evaluation content is as follows:

[0081] If the growth risk threshold W> the growth risk coefficient Sfxs, it means that there is no potential growth threat to the grafted seedlings in the current vegetable seedling raising sub-area; at this time, the manager continues to maintain the existing environmental control strategy and no intervention is required;

[0082] If the growth risk threshold W ≤ the growth risk coefficient Sfxs, it means that there is a potential growth threat to the grafted seedlings in the current vegetable seedling raising area, including abnormal soil electrical conductivity Tdd leading to salt accumulation, abnormal root respiration rate Ghx and soil oxygen content Th1; intervention measures should be taken at this time.

[0083] In this embodiment, the intelligent level of seedling management is greatly improved by combining the AI ​​model construction unit, the early warning issuing unit and the risk assessment unit; the AI ​​model construction unit is used to construct an environmental adaptability assessment model, and the early warning issuing unit extracts soil moisture Tsh, light intensity Gzq, temperature Wd and grafting success rate Jcs for dimensionless processing, calculates the environmental adaptability index Epj, and compares and evaluates it with the preset environmental adaptability threshold Q, so as to timely identify whether the environmental state is suitable for the growth of grafted seedlings; if the environmental state is abnormal, an early warning is issued to remind the management personnel to make adjustments; the risk assessment unit further calculates the growth risk coefficient Sfxs by extracting data such as soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, air humidity Ksh and nutrient content Yf, and identifies potential growth threats by comparing and evaluating with the growth risk threshold W; this ensures that the system can intervene in time when the environment is abnormal, optimize the seedling environment, and improve the accuracy of seedling management; the significance of collecting each parameter is to provide comprehensive growth environment monitoring to ensure that the data basis is accurate and comprehensive.

[0084] Example 5

[0085] The grafting process control module includes an environmental parameter adjustment unit and a grafting time control unit;

[0086] The environmental parameter adjustment unit is used to take intervention measures according to the potential growth threats output by the intelligent analysis module, including dynamically adjusting the environmental parameters involved in the seedling raising process, wherein the environmental parameters include soil electrical conductivity Tdd, root respiration rate Ghx and soil oxygen content Th1. The intervention measures taken include adjusting the oxygen in the soil through oxygenation equipment, adjusting the salt in the soil and controlling the air humidity to achieve the environmental conditions required for the grafting process.

[0087] The grafting time control unit calculates the optimal grafting interval Tjw of the vegetable variety by extracting the vegetable grafting related data and the seedling raising environment related data and performing dimensionless processing. The specific calculation formula is as follows:

[0088] ;

[0089] In the formula, n represents the number of time points collected, Zsl represents the transpiration rate of seedlings in the vegetable grafting related data, represents the transpiration rate of seedlings at the i-th time point, represents the root respiration rate at the i-th time point, Ghxy represents the standard value of the root respiration rate in the vegetable grafting related data, g represents the second correction constant, d is the base of the natural logarithm, and f represents the regularization parameter, which is used to control the influence of the root respiration rate deviation.

[0090] The grafting time control unit compares and evaluates the preset optimal grafting time interval threshold R with the optimal grafting interval time Tjw, and the specific evaluation content is as follows:

[0091] When the optimal grafting interval threshold R ≥ the optimal grafting interval Tjw, it means that the current grafting interval meets the requirements and there is no need to adjust the grafting interval.

[0092] When the optimal grafting time interval threshold R is less than the optimal grafting time interval Tjw, it means that the current grafting time interval does not meet the requirements. The grafting time period is automatically adjusted according to the AI ​​algorithm. The specific implementation process is as follows: input the optimal grafting time interval Tjw and related parameters, then call the AI ​​algorithm model to analyze all input data, and finally generate a time adjustment strategy.

[0093] In this embodiment, precise control of the grafting process is achieved through the cooperation of the environmental parameter adjustment unit and the grafting time control unit; the environmental parameter adjustment unit dynamically adjusts environmental parameters such as soil conductivity Tdd, root respiration rate Ghx and soil oxygen content Th1 according to the potential growth threats output by the intelligent analysis module, and the intervention measures taken include increasing the oxygen content in the soil through aeration equipment, adjusting the salt in the soil and controlling the air humidity Ksh, so that the environmental conditions during the grafting process meet the requirements; the grafting time control unit calculates the optimal grafting interval Tjw of the vegetable variety by extracting data such as the seedling transpiration rate Zsl and the root respiration rate Ghx and performing dimensionless processing, and then compares and evaluates it with the preset optimal grafting interval threshold R. If Tjw exceeds the threshold R, the grafting time period is adjusted through the AI ​​algorithm to ensure that the grafting operation is performed within the optimal time window; the collection and processing of these parameters ensure the controllability of the environment and the timeliness of the grafting operation, and effectively improves the grafting success rate and the intelligent management level of the system.

[0094] Example 6

[0095] The smart seedling management module compares and evaluates the growth risk coefficient Sfxs and the environmental adaptation index Epj to generate the following evaluation results:

[0096] When the growth risk coefficient Sfxs ≤ the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are normal, and the first assessment result is generated at this time;

[0097] When the growth risk coefficient Sfxs ≤ the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are abnormal, and the second evaluation result is generated at this time;

[0098] The smart seedling management module adjusts the seedling management measures of the current vegetable seedling sub-area according to the first evaluation result and the second evaluation result respectively; specifically:

[0099] When the first evaluation result is generated, the current vegetable seedling raising sub-area continues to be managed according to the established management plan, and continues to pay attention to the changes in the growth risk coefficient Sfxs and the environmental adaptation index Epj;

[0100] When the second assessment result is generated, identify the main sources of risk and adjust the corresponding parameters in a timely manner, including excessive soil moisture leading to root hypoxia, adjusting irrigation volume and soil drainage; if excessive light affects seedling growth, adjust the light intensity through shade nets.

[0101] In this embodiment, by comparing the growth risk coefficient Sfxs with the environmental adaptability index Epj, the environmental adaptability and seedling growth risk of the current vegetable seedling sub-area can be accurately evaluated, and a first or second evaluation result is generated; when the growth risk coefficient Sfxs is less than or equal to the environmental adaptability index Epj, a first evaluation result is generated, indicating that the seedling environment is normal, and the system manages and continuously monitors the changes of Sfxs and the environmental adaptability index Epj according to the established plan; when the growth risk coefficient Sfxs is greater than the environmental adaptability index Epj, a second evaluation result is generated, indicating that there is an abnormality in the environment, and the system will promptly identify the source of risk and adjust the corresponding parameters, such as adjusting the irrigation amount or drainage measures when the soil moisture Tsh is too high, and using a shade net to adjust the light when the light intensity Gzq is too strong; this dynamic management mechanism ensures the environmental adaptability and healthy growth of seedlings during the seedling cultivation process, and improves the efficiency and success rate of seedling cultivation.

[0102] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. AI-based intelligent vegetable seedling grafting management system, characterized by: It includes environmental data collection module, data processing module, intelligent analysis module, grafting process control module and smart seedling management module; The environmental data acquisition module is used to divide the vegetable seedling raising area into several vegetable seedling raising sub-areas and mark the vegetable seedling raising sub-areas; then deploy sensors in each vegetable seedling raising sub-area to monitor and collect data related to the seedling raising environment in real time; then monitor the health status of the grafted seedlings in the vegetable seedling raising sub-area in real time and collect data related to vegetable grafting, and obtain the grafting success rate Jcs by calculation; The data processing module is used to pre-process and normalize the seedling raising environment-related data in the vegetable seedling raising sub-area, and then preliminarily screen and store the collected seedling raising environment-related data through data fusion technology, and finally transmit the processed seedling raising environment-related data to the AI ​​model database; The intelligent analysis module is used to extract the seedling environment related data in the AI ​​model database and use the AI ​​algorithm for intelligent analysis to build an environmental adaptability assessment model; then calculate and evaluate the environmental adaptability index Epj in the vegetable seedling sub-area, and issue an early warning instruction for the environment of the current vegetable seedling sub-area; finally, calculate and evaluate the growth risk coefficient Sfxs of the grafted seedlings in the current vegetable seedling sub-area based on the evaluation content of the environmental adaptability index Epj; The grafting process control module is used to adjust the relevant environmental parameters during vegetable grafting according to the evaluation content of the growth risk coefficient Sfxs; then the optimal grafting interval time Tjw suitable for the vegetable variety is obtained by calculation and evaluated, and the grafting interval time period is automatically adjusted through the AI ​​algorithm according to the evaluation content of the optimal grafting interval time Tjw; The smart seedling management module is used to compare and analyze the growth risk coefficient Sfxs and the environmental adaptation index Epj, and adjust the seedling management measures of the current vegetable seedling sub-area according to the analysis results; The environmental data acquisition module includes a health monitoring unit; The health monitoring unit is used to monitor the health status of grafted seedlings in the vegetable seedling raising area in real time and collect vegetable grafting related data, which includes the total number of grafted vegetables Mzs, water flow rate Msl, stomatal conductance Mqk and chlorophyll content Myl; after extracting the vegetable grafting related data and performing dimensionless processing, the grafting success rate Jcs is calculated by the following formula: ； The intelligent analysis module includes an AI model building unit, an early warning issuing unit and a risk assessment unit; The AI ​​model building unit is used to build an environmental adaptability assessment model; The warning issuing unit extracts soil moisture Tsh, light intensity Gzq, temperature Wd and grafting success rate Jcs and performs dimensionless processing, and then calculates the environmental adaptation index Epj using the following formula: ； Then, the preset environmental adaptability threshold Q is compared with the environmental adaptability index Epj for evaluation, and an early warning is issued based on the evaluation content. The specific evaluation content is as follows: If the environmental adaptability threshold Q ≥ environmental adaptability index Epj, it means that the current environmental status in the vegetable seedling raising sub-area is normal and suitable for the growth of grafted seedlings, and no adjustment measures are needed. Then further analysis is carried out, including calculating the growth risk coefficient Sfxs and identifying potential growth threats; If the environmental adaptability threshold Q is less than the environmental adaptability index Epj, it means that the environmental status in the current vegetable seedling raising sub-area is abnormal and not suitable for the growth of grafted seedlings. At this time, an early warning is issued to remind the management personnel to make adjustments; The risk assessment unit calculates the growth risk coefficient Sfxs in the current vegetable seedling raising sub-area by extracting soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Th1, air humidity Ksh and nutrient content Yf from the seedling raising environment related data. The specific calculation formula of the growth risk coefficient Sfxs is: ； Where a is the first correction constant; The preset growth risk threshold W is compared with the growth risk coefficient Sfxs to evaluate and identify potential growth threats based on the evaluation content. The specific evaluation content is as follows: If the growth risk threshold W> the growth risk coefficient Sfxs, it means that there is no potential growth threat to the grafted seedlings in the current vegetable seedling raising sub-area; at this time, the manager continues to maintain the existing environmental control strategy and no intervention is required; If the growth risk threshold W ≤ the growth risk coefficient Sfxs, it means that there is a potential growth threat to the grafted seedlings in the current vegetable seedling raising sub-area, including abnormal soil conductivity Tdd leading to salt accumulation, abnormal root respiration rate Ghx and soil oxygen content Th1; intervention measures should be taken at this time; The grafting process control module includes a grafting time control unit; The grafting time control unit calculates the optimal grafting interval Tjw of the vegetable variety by extracting the vegetable grafting related data and the seedling raising environment related data and performing dimensionless processing. The specific calculation formula is as follows: ； In the formula, n represents the number of time points collected, Zsl represents the transpiration rate of seedlings in the vegetable grafting related data, represents the transpiration rate of seedlings at the i-th time point, represents the root respiration rate at the i-th time point, Ghxy represents the standard value of the root respiration rate in the vegetable grafting related data, g represents the second correction constant, d is the base of the natural logarithm, and f represents the regularization parameter, which is used to control the influence of the deviation of the root respiration rate; The grafting time control unit compares and evaluates the preset optimal grafting time interval threshold R with the optimal grafting interval time Tjw, and the specific evaluation content is as follows: When the optimal grafting interval threshold R ≥ the optimal grafting interval Tjw, it means that the current grafting interval meets the requirements and there is no need to adjust the grafting interval. When the optimal grafting time interval threshold R is less than the optimal grafting time interval Tjw, it means that the current grafting time interval does not meet the requirements. The grafting time period is automatically adjusted according to the AI ​​algorithm. The specific implementation process is as follows: input the optimal grafting time interval Tjw and related parameters, then call the AI ​​algorithm model to analyze all input data, and finally generate a time adjustment strategy.

2. The AI-based vegetable seedling and grafting intelligent management system according to claim 1 is characterized in that: The environmental data acquisition module also includes a sensor deployment acquisition unit; The sensor deployment and collection unit deploys different types of sensors in each vegetable seedling area according to the plant layout and environmental characteristics in different vegetable seedling areas, and calibrates each sensor, and uses the calibrated sensors to monitor and collect seedling environment related data in real time; the seedling environment related data includes soil moisture Tsh, light intensity Gzq, temperature Wd, air humidity Ksh, soil conductivity Tdd, root respiration rate Ghx, soil oxygen content Thl, soil pH value Ph and nutrient content Yf.

3. The AI-based vegetable seedling and grafting intelligent management system according to claim 1 is characterized in that: The data processing module is used to filter out non-compliant data in the seedling environment related data, including outliers and missing values; then the pre-processed seedling environment related data is normalized, and finally the seedling environment related data is fused through a weighted average algorithm based on the relationship between parameters in different seedling environment related data.

4. The AI-based vegetable seedling and grafting intelligent management system according to claim 1 is characterized in that: The grafting process control module also includes an environmental parameter adjustment unit; The environmental parameter adjustment unit is used to take intervention measures according to the potential growth threats output by the intelligent analysis module, including dynamically adjusting the environmental parameters involved in the seedling cultivation process, wherein the environmental parameters include soil electrical conductivity Tdd, root respiration rate Ghx and soil oxygen content Th1. The intervention measures taken include adjusting the oxygen in the soil through oxygenation equipment, adjusting the salt in the soil and controlling the air humidity.

5. The AI-based vegetable seedling and grafting intelligent management system according to claim 1 is characterized in that: The smart seedling management module compares and evaluates the growth risk coefficient Sfxs and the environmental adaptation index Epj to generate the following evaluation results: When the growth risk coefficient Sfxs ≤ the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are normal, and the first assessment result is generated at this time; When the growth risk coefficient Sfxs> the environmental adaptability index Epj, it means that the environmental adaptability and seedling growth risk of the current vegetable seedling raising sub-area are abnormal, and the second evaluation result is generated; The smart seedling management module adjusts the seedling management measures of the current vegetable seedling sub-area according to the first evaluation result and the second evaluation result respectively; specifically: When the first evaluation result is generated, the current vegetable seedling raising sub-area continues to be managed according to the established management plan, and continues to pay attention to the changes in the growth risk coefficient Sfxs and the environmental adaptation index Epj; When the second assessment results are generated, identify the main risk sources and adjust the corresponding parameters in time, including soil moisture leading to root hypoxia, adjusting irrigation volume and soil drainage; If the light intensity affects the growth of seedlings, adjust the light intensity through the shade net.

Images