Intelligent agricultural greenhouse management method and system based on AI

Abstract

The invention discloses an AI-based intelligent agricultural greenhouse management method and system, and relates to the technical field of AI management, and the main scheme is that the method comprises the steps: collecting growth environment data, plant physiological data, pesticide residue data and soil nutrient data in an agricultural greenhouse based on an AI system; the AI system calculates corresponding environmental suitability indexes, plant physiological health indexes, pesticide residue degradation rate indexes and soil nutrient health indexes, finally, the system presets a plant healthy growth threshold set and compares the indexes with the set to judge the plant growth state, and the AI system generates corresponding control strategies according to the indexes. And plants in the greenhouse can grow healthily.

Description

Technical Field

[0001] The present invention relates to the field of AI management technology, and specifically to an AI-based smart agricultural greenhouse management method and system. Background Art

[0002] In the process of agricultural modernization, the cultivation of genetically modified plants is becoming more and more common, and their growth management is crucial. For genetically modified plants, their growth is more sensitive to conditions such as the environment, their own physiological state, pesticide residues, and soil nutrients. There are many kinds of genetically modified plants, such as insect-resistant genetically modified cotton, which has the ability to resist pests such as cotton bollworm by introducing exogenous genes; and herbicide-resistant genetically modified soybeans, which can grow normally when sprayed with specific herbicides.

[0003] There are many shortcomings in traditional agricultural greenhouse management methods. In terms of data collection, it is difficult to obtain comprehensive relevant data, resulting in missing or inaccurate data. There is no scientific calculation system, and it is impossible to monitor relevant data in real time and in detail. It is difficult to carry out effective monitoring and evaluation, and it is impossible to promptly discover plant growth and health problems and take targeted measures. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides an AI-based smart agricultural greenhouse management method and system. By collecting growth environment data, plant physiological data, pesticide residue data and soil nutrient data in the agricultural greenhouse based on the AI ​​system, the corresponding environmental suitability index, plant physiological health index, pesticide residue degradation rate index and soil nutrient health index are calculated respectively. Finally, the system presets a set of plant health growth thresholds, compares the above-mentioned indexes with them, and judges the growth status of the plants. The AI ​​system generates corresponding control strategies based on this, which solves the problems in data collection, such as difficulty in comprehensively acquiring relevant data, resulting in missing or inaccurate data, failure to establish a scientific computing system, inability to monitor relevant data in real time and in detail, difficulty in effective monitoring and evaluation, and inability to timely discover plant growth health problems and take targeted measures.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI-based smart agricultural greenhouse management method, comprising the following steps: Step 1: Collect growth environment data, plant physiological data, pesticide residue data, and soil nutrient data in agricultural greenhouses based on the AI ​​system; Step 2: Calculate the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI based on the growth environment data; Calculate the environmental suitability index TSB based on the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI; Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; calculate the plant physiological health index SCQ based on the photosynthetic efficiency index PEC and pest and disease resistance index API; Calculate the pesticide residue degradation rate index YZC based on the pesticide residue data; Calculate the soil nutrient balance index SNT based on soil nutrient data; Calculate the soil nutrient health index SCH based on the soil nutrient balance index SNT; Step 3: Preset a set of plant health growth thresholds, compare the environmental suitability index TSB, plant physiological health index SCQ, pesticide residue degradation rate index YZC and soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

[0006] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI is: Growth environment data including temperature values ​​MXA i , standard temperature value suitable for growth NWS, minimum temperature value that can be tolerated NFR and maximum temperature value BSK; Temperature values ​​according to MXA i , the standard temperature value NWS suitable for crop growth, the minimum temperature value NFR that crops can withstand, and the maximum temperature value BSK are used to calculate the temperature deviation growth suitability index TDG. The formula is as follows: ; Among them, MXA i is the temperature value measured at the i-th time, i is the serial number corresponding to different measurement times, and its value is [1, n]; n is the number of measurements, and its value is a positive integer; The growth environment data also includes humidity value CJQ j and humidity average value DWX; According to humidity value CJQ j The humidity dispersion index HDI is calculated by the humidity average value DWX according to the following formula: ; Among them, CJQ jis the humidity value at the jth time point, j is the serial number corresponding to different time points, and its value is [1, z]; z is the number of time points, and its value is a positive integer; The growth environment data also includes the light intensity value JCU k , average light intensity CNS, minimum light intensity MCA and maximum light intensity NCA; According to the light intensity value JCU k , the average light intensity CNS, the minimum light intensity MCA and the maximum light intensity NCA are used to calculate the light intensity suitability index LUI. The formula is as follows: ; Where is JCU k is the light intensity value measured in the kth area, k is the serial number corresponding to different areas, and its value is [1, m]; m is the number of areas in the greenhouse, and its value is a positive integer.

[0007] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the environmental suitability index TSB is: The environmental suitability index TSB is calculated based on the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI. The formula is as follows: ; Among them, α1 is the weight coefficient of the temperature deviation growth suitability index TDG, which ranges from 0.1 to 0.3; α2 is the weight coefficient of the humidity dispersion index HDI, which ranges from 0.3 to 0.4; α3 is the weight coefficient of the light intensity suitability index LUI, which ranges from 0.4 to 0.5; and α1+α2+α3=1.

[0008] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the photosynthetic efficiency index PEC and the pest and disease resistance index API is: Plant physiological data include actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI; The photosynthetic efficiency index PEC is calculated based on the actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI. The formula is as follows: ; Plant physiological data also include polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW; The pest and disease resistance index API is calculated based on the polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW. The formula is as follows: .

[0009] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the plant physiological health index SCQ is: The plant physiological health index SCQ is calculated based on the photosynthetic efficiency index PEC and the pest and disease resistance index API. The formula is as follows: .

[0010] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the pesticide residue degradation rate index YZC is: Pesticide residue data including current pesticide residue concentration GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y ; According to the current residual concentration of pesticides GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y The formula for calculating the pesticide residue degradation rate index YZC is as follows: ; Among them, GJH y is the current residual concentration of the yth pesticide, MRL y is the maximum residue limit of the yth pesticide, EWP y is the initial residual concentration of the yth pesticide, KWE y is the maximum residue limit corresponding to the y-th pesticide at the initial time, y is the serial number corresponding to different types of pesticides, and its value is [1, s]; s is the number of pesticide types, and its value is a positive integer.

[0011] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the soil nutrient balance index SNT is: Soil nutrient data includes the actual amount of nutrients in the soil. q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q ; According to the actual content of nutrients in the soil ANZ q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q The soil nutrient balance index SNT is calculated based on the following formula: ; Among them, ANZ q is the actual content of the qth nutrient, ORN q is the best recommended content of the qth nutrient, PJX q is the amount of the qth nutrient absorbed by plants from the soil, ILZ q is the optimal absorption amount of the qth nutrient by the plant, JCA q is the supplement amount of the qth nutrient in the soil, OKJ q is the optimal supplement amount of the qth nutrient, VZX q VBM is the microbial transformation amount of the qth nutrient in the soil. q is the optimal microbial conversion amount of the qth nutrient, q is the serial number corresponding to different nutrients, and its value is [1, w]; w is the number of nutrient types, and its value is a positive integer.

[0012] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the method for calculating the soil nutrient comprehensive health index SCH is: The soil nutrient health index SCH is calculated based on the soil nutrient balance index SNT, and the formula is as follows: ; Among them, δ is the weight coefficient of soil nutrient balance index SNT, which ranges from 0 to 1. represents a small change in the soil nutrient balance index, and dt represents a small change in time.

[0013] In the preferred embodiment of the above-mentioned AI-based smart agricultural greenhouse management method, the criteria for judging the growth status of the genetically modified plants in the current agricultural greenhouse are as follows: The plant health growth threshold set includes the optimal environment threshold WD and the inferior environment threshold WQ; wherein the optimal environment threshold WD> the inferior environment threshold WQ; The environmental suitability index TSB is compared with the optimal environment threshold WD and the inferior environment threshold WQ to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When in a superior environmental state, generate environmental control strategy 1; when in a suitable environmental state, generate environmental control strategy 2; when in a poor environmental state, generate environmental control strategy 3; The plant health growth threshold set also includes a thriving growth threshold GS and a withering growth threshold GF; wherein the thriving growth threshold GS> the withering growth threshold GF; The plant physiological health index SCQ is compared with the vigorous growth threshold GS and the withered growth threshold GF to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When in an exuberant physiological state, physiological control strategy one is generated; when in a stable physiological state, physiological control strategy two is generated; when in a weak physiological state, physiological control strategy three is generated; The plant health growth threshold set also includes a pesticide high degradation rate threshold NF and a pesticide low degradation rate threshold NB; wherein the pesticide high degradation rate threshold NF> the pesticide low degradation rate threshold NB; The pesticide residue degradation rate index YZC is compared with the pesticide high degradation rate threshold NF and the pesticide low degradation rate threshold NB to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When the pesticide is in a highly efficient degradation state, the pesticide residue control strategy 1 is generated; when the pesticide is in a conventional degradation state, the pesticide residue control strategy 2 is generated; when the pesticide is in an inefficient degradation state, the pesticide residue control strategy 3 is generated; The plant health growth threshold set also includes a fertile soil threshold YT and a poor soil threshold YU; wherein, the fertile soil threshold YT>the poor soil threshold YU; The soil nutrient health index SCH is compared with the fertile soil threshold YT and the poor soil threshold YU to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When the soil is in a state of abundant nutrients, nutrient control strategy one is generated; when the soil is in a state of balanced nutrients, nutrient control strategy two is generated; when the soil is in a state of scarce nutrients, nutrient control strategy three is generated.

[0014] The present invention also discloses an AI-based smart agricultural greenhouse management system, including: Data collection module, used to collect growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system; A data calculation module is used to calculate the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI according to the growth environment data; and calculate the environmental suitability index TSB according to the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI; Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; calculate the plant physiological health index SCQ based on the photosynthetic efficiency index PEC and pest and disease resistance index API; Calculate the pesticide residue degradation rate index YZC based on the pesticide residue data; Calculate the soil nutrient balance index SNT based on soil nutrient data; Calculate the soil nutrient health index SCH based on the soil nutrient balance index SNT; The data judgment module is used to preset a set of plant health growth thresholds, compare the environmental suitability index TSB, the plant physiological health index SCQ, the pesticide residue degradation rate index YZC and the soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of the genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

[0015] (III) Beneficial effects The present invention provides an AI-based smart agricultural greenhouse management method and system, which has the following beneficial effects: (1) By collecting growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system, it is possible to comprehensively and real-time collect multi-dimensional data in agricultural greenhouses, establish a complete information database on the growth status of genetically modified plants, and provide a rich and accurate data foundation for subsequent in-depth analysis and precise decision-making, changing the previous situation of incomplete and untimely information acquisition, making management decisions more scientific.

[0016] (2) By calculating the corresponding environmental suitability index, plant physiological health index, pesticide residue degradation rate index and soil nutrient health index respectively, complex data are converted into intuitive and practical quantitative indicators, providing clear quantitative standards for accurately judging the growth status of plants, greatly improving the accuracy and efficiency of the analysis.

[0017] (3) By presetting a set of plant health growth thresholds, the environmental suitability index, plant physiological health index, pesticide residue degradation rate index and soil nutrient health index are compared with them respectively. Based on the judgment results, the AI ​​system generates corresponding control strategies, which can quickly and accurately judge the growth status of genetically modified plants. Once a certain index deviates from the threshold, it can promptly detect possible problems in plant growth, thus achieving dynamic and precise regulation of plant growth, effectively ensuring the healthy growth of genetically modified plants, and improving the quality and efficiency of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the working steps of an AI-based smart agricultural greenhouse management method of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] See also Figure 1 The present invention provides an AI-based smart agricultural greenhouse management method, comprising the following steps: Step 1: Collect growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system.

[0021] When using, combine the content of step 1: By collecting growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system, it is possible to comprehensively and real-time collect multi-dimensional data in agricultural greenhouses, establish a complete information database on the growth conditions of genetically modified plants, and provide a rich and accurate data foundation for subsequent in-depth analysis and precise decision-making, changing the previous situation of incomplete and untimely information acquisition, and making management decisions more scientific.

[0022] Step 2: Calculate the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI based on the growth environment data; calculate the environmental suitability index TSB based on the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI.

[0023] Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; calculate the plant physiological health index SCQ based on the photosynthetic efficiency index PEC and pest and disease resistance index API; The pesticide residue degradation rate index YZC was calculated based on the pesticide residue data.

[0024] The soil nutrient balance index SNT is calculated based on the soil nutrient data; the soil nutrient health index SCH is calculated based on the soil nutrient balance index SNT.

[0025] Step 201: The method for calculating the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI is: Growth environment data including temperature values ​​MXA i , standard temperature value suitable for growth NWS, minimum temperature value that can be tolerated NFR and maximum temperature value BSK.

[0026] It should be noted that the temperature values ​​of MXA i It represents the temperature value in the agricultural greenhouse obtained by the i-th measurement, which is obtained by the temperature sensor; the standard temperature value NWS suitable for growth represents the most suitable temperature value during the growth of genetically modified plants, which is a relatively fixed reference value and is obtained through the crop planting manual; the lowest tolerable temperature value NFR represents the lowest temperature value that genetically modified plants can tolerate during their growth, which is obtained from agricultural science literature and crop planting guidelines; the maximum temperature value BSK represents the highest temperature value that genetically modified plants can tolerate during their growth, which is obtained from agricultural science literature and crop planting guidelines.

[0027] Temperature values ​​according to MXA i , the standard temperature value NWS suitable for crop growth, the minimum temperature value NFR that crops can withstand, and the maximum temperature value BSK are used to calculate the temperature deviation growth suitability index TDG. The formula is as follows: ; Among them, MXA i is the temperature value measured for the i-th time, i is the serial number corresponding to different measurement times, and its value is [1, n]; n is the number of measurements, and its value is a positive integer.

[0028] It should be noted that in this formula: The absolute value of the difference between each measured temperature and the standard temperature value suitable for crop growth is summed up to reflect the overall situation of temperature deviation from the suitable temperature over a period of time. It is the relative degree to which the average temperature measured each time deviates from the standard temperature suitable for crop growth over a period of time. It is an exponential function. By associating it with the temperature tolerance range, it adjusts the overall index value and reflects the nonlinear characteristics of temperature influence, providing a scientific basis for accurately judging and regulating the temperature environment in agricultural greenhouses. It is added on the basis of the exponential function to avoid the situation where the denominator is 0. At the same time, it also makes the denominator value always greater than 1, ensuring that the temperature deviation from the growth suitability index is between 0 and 1, which is convenient for the interpretation and application of the results. When the value of TDG is close to 1, it means that the temperature conditions in the greenhouse are generally close to the standard temperature suitable for crop growth, and the temperature deviation is small, which is more beneficial to crop growth. When the value of TDG is small, it means that the temperature deviates greatly from the suitable temperature, which may have an adverse effect on crop growth.

[0029] The growth environment data also includes humidity value CJQ j And the humidity average value DWX.

[0030] It should be noted that the humidity value CJQ j It represents the humidity value in the agricultural greenhouse measured at the jth time point, which is obtained by the humidity sensor; the humidity average value DWX represents the arithmetic mean of all humidity values, which is obtained by adding the humidity values ​​measured at z time points and then dividing by the number of time points z.

[0031] According to humidity value CJQ j The humidity dispersion index HDI is calculated by the humidity average value DWX according to the following formula: ; Among them, CJQ j is the humidity value at the jth time point, j is the serial number corresponding to different time points, and its value is [1, z]; z is the number of time points, and its value is a positive integer.

[0032] It should be noted that in this formula: The numerator is formed by summing the absolute value of the difference between each humidity value and the average value, highlighting the impact of large deviations on the dispersion. The z in the denominator is used for averaging, and z is multiplied by This makes the dispersion index calculated from humidity data of different magnitudes comparable; overall, when the value of the humidity dispersion index HDI is large, it means that the humidity in the greenhouse fluctuates more violently during this period and the humidity changes greatly; conversely, if the HDI value is small, it means that the humidity environment is relatively stable, which is conducive to the growth and development of crops.

[0033] The growth environment data also includes the light intensity value JCU k , average light intensity CNS, minimum light intensity MCA and maximum light intensity NCA.

[0034] It should be noted that the light intensity value JCU k It represents the light intensity value measured in the kth area in the greenhouse, which is obtained by the light intensity sensor; the average light intensity CNS represents the arithmetic mean of the light intensity values ​​of all areas in the greenhouse, which is obtained by adding the light intensity values ​​of m areas in the greenhouse and then dividing it by the number of areas m; the minimum light intensity MCA represents the minimum light intensity of all areas in the greenhouse. After obtaining the light intensity values ​​of each area in the greenhouse, these values ​​are compared to find the minimum value, which is MCA; the maximum light intensity NCA represents the maximum light intensity of all areas in the greenhouse. After obtaining the light intensity values ​​of each area in the greenhouse, these values ​​are compared to find the maximum value, which is NCA.

[0035] According to the light intensity value JCU k , the average light intensity CNS, the minimum light intensity MCA and the maximum light intensity NCA are used to calculate the light intensity suitability index LUI. The formula is as follows: ; Where is JCU k is the light intensity value measured in the kth area, k is the serial number corresponding to different areas, and its value is [1, m]; m is the number of areas in the greenhouse, and its value is a positive integer.

[0036] It should be noted that in this formula: The sum of the maximum and minimum light intensity of each area minus the actual measured light intensity value of the area can reflect the relative position relationship between the light intensity of the area and the light intensity range of the entire area, multiplied by The influence of the actual light intensity of the area on the overall suitability is further considered. This allows the calculation results to have a relatively uniform measurement standard in greenhouses with different lighting conditions, and can more objectively reflect the suitability of the light intensity in each area, rather than simply relying on the absolute numerical range of the light intensity in the greenhouse. By summing up, the light intensity suitability information of each area is integrated to obtain a sum that reflects the overall characteristics of the light intensity of the entire greenhouse. Dividing it by m plays an averaging role, so that the value of the light intensity suitability index is an average value calculated based on the lighting conditions of all areas in the entire greenhouse, rather than the result of a single area, which can better reflect the overall suitability of the light in the greenhouse; on the whole, when the LUI value is large, it means that the light intensity distribution in the greenhouse is relatively suitable for crop growth, and the light intensity of each area matches the ideal light intensity range well; when the LUI value is small, it means that the light intensity may be too strong or too weak in some areas, and the deviation from the ideal lighting conditions is large, which may be not conducive to the uniform growth and development of crops.

[0037] Step 202: The method for calculating the environmental suitability index TSB is: The environmental suitability index TSB is calculated based on the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI. The formula is as follows: ; Among them, α1 is the weight coefficient of the temperature deviation growth suitability index TDG, which is determined according to the influence of the temperature deviation growth suitability index TDG on the environmental suitability index TSB, and its value is 0.1~0.3; α2 is the weight coefficient of the humidity dispersion index HDI, which is determined according to the influence of the humidity dispersion index HDI on the environmental suitability index TSB, and its value is 0.3~0.4; α3 is the weight coefficient of the light intensity suitability index LUI, which is determined according to the influence of the light intensity suitability index LUI on the environmental suitability index TSB, and its value is 0.4~0.5; and α1+α2+α3=1.

[0038] It should be noted that in this formula: the formula of the environmental suitability index TSB is obtained by weighted summing the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI by their respective weight coefficients, and comprehensively considering the suitability of the three important environmental factors of temperature, humidity and light to the growth environment of genetically modified plants. The larger the value of TSB, the more suitable the overall environmental conditions in the greenhouse are for crop growth; the smaller the value of TSB, it means that there may be some factors in the environmental conditions that are not conducive to the growth of genetically modified plants, and corresponding adjustments and improvements are needed.

[0039] Step 203: The method for calculating the photosynthetic efficiency index PEC and the pest resistance index API is: Plant physiological data include actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI.

[0040] It should be noted that the actual photosynthetic rate KSQ refers to the rate of photosynthesis of genetically modified plants under actual environmental conditions, which is measured by a photosynthetic meter; the leaf chlorophyll content CHI refers to the key pigment for plant photosynthesis, which is obtained by grinding the leaves to extract chlorophyll, then using a spectrophotometer to measure the absorbance of the extract at a specific wavelength, and then calculating the chlorophyll content based on the standard curve; the light quantum efficiency MWQ refers to the efficiency of the photochemical reaction in photosynthesis, which is obtained by measuring the light response curve. For example, the plant is placed in a closed photosynthetic measurement system and a series of light intensity gradients are set, such as 100, 200, and 300 μmol·m - ²・s - ¹ etc., draw the light response curve, determine the linear part below the light saturation point, select two points in this part, and its horizontal axis is the light intensity , the vertical axis is the photosynthetic rate , using the formula to calculate the light quantum efficiency; the net photosynthetic rate PUI represents the rate at which plants assimilate carbon dioxide in photosynthesis minus the rate at which they release carbon dioxide in respiration, which is measured by a photosynthetic meter; the dark respiration rate RDX represents the rate at which plants consume oxygen and release carbon dioxide in respiration under dark conditions. The rate at which plants release carbon dioxide is measured in a dark environment using the same photosynthetic meter as that used to measure the photosynthetic rate, which is the dark respiration rate; the intercellular carbon dioxide concentration HDQ represents the ease of transporting carbon dioxide from the external environment to the chloroplasts and the utilization of carbon dioxide in photosynthesis. It is measured by the gas analysis module of the photosynthetic meter, and the instrument can monitor the carbon dioxide concentration in the intercellular spaces of leaves in real time; the chloroplast carbon dioxide concentration BWQ represents the driving force for the diffusion of carbon dioxide into chloroplasts and the carbon source supply for photosynthesis. It is calculated by combining parameters such as the intercellular carbon dioxide concentration and stomatal conductance and using a gas diffusion model; the maximum carboxylation rate EYI represents the maximum reaction rate of carboxylase in plant photosynthesis, which is calculated by fitting the light response curve with a photosynthesis model.

[0041] The photosynthetic efficiency index PEC is calculated based on the actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI. The formula is as follows: ; It should be noted that in this formula: Multiply the actual photosynthetic rate, the square root of the leaf chlorophyll content and the light quantum efficiency, Taking into account the basic role of chlorophyll in light energy absorption and conversion, it can better reflect its influence on photosynthesis. It is an exponential function. A larger value of the exponential function indicates that the plant has a stronger ability to accumulate organic matter in photosynthesis and contributes more to the photosynthetic efficiency index. On the contrary, a smaller value of the exponential function indicates that the plant has a weaker ability to accumulate organic matter in photosynthesis and contributes less to the photosynthetic efficiency index. The difference between the intercellular carbon dioxide concentration and the chloroplast carbon dioxide concentration It reflects the driving force for the diffusion of carbon dioxide from the intercellular space to the chloroplasts. Combined with other parameters, it can more reasonably reflect its impact on the photosynthetic efficiency index; the larger the PEC value, the higher the photosynthetic efficiency of the plant, the stronger the photosynthetic ability, and the higher the plant growth and productivity may be; the smaller the PEC value, the lower the photosynthetic efficiency of the plant may be.

[0042] The plant physiological data also include polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW.

[0043] It should be noted that the polyphenol oxidase activity value PPL represents the current activity value of polyphenol oxidase in the plant. It is obtained by extracting enzyme solution from plant tissues, adding substrates such as catechol, etc. to the spectrophotometric reaction system, reacting under suitable temperature, pH and other conditions for a period of time, and calculating the activity value of polyphenol oxidase by detecting the consumption rate of the substrate or the generation rate of the product. The polyphenol oxidase reference activity value PQW represents the activity level of polyphenol oxidase in a normal and healthy state of the plant. It is a reference value. The polyphenol oxidase activity value is determined by measuring the polyphenol oxidase activity value of a large number of healthy plant samples, and then taking the average value to determine a relatively stable reference value. The phenylalanine ammonia lyase activity value CSA represents the current activity value of phenylalanine ammonia lyase in the plant. It is one of the key enzymes in the plant's defense response. Its activity reflects the ability of the plant to resist diseases and insect pests. It is obtained by extracting enzyme solution from plant tissues, adding substrates such as phenylalanine, etc. to a specific reaction system, and detecting it by spectrophotometry. , the activity of phenylalanine ammonia lyase is calculated by detecting the product, such as the production of trans-cinnamic acid; the reference activity value of phenylalanine ammonia lyase NWW represents the reference value of phenylalanine ammonia lyase activity of plants in a normal and healthy state. The activity value of phenylalanine ammonia lyase is measured on healthy plant samples, and then a relatively stable reference value is determined by taking the average value; the salicylic acid content FQF plays the role of a signal molecule in the disease resistance of plants, which can induce plants to produce systemic acquired resistance and enhance the resistance of plants to a variety of diseases and insect pests. It is determined by high performance liquid chromatography; the jasmonic acid content TIE represents a plant hormone that participates in the defense response and stress resistance regulation of plants. It is determined by gas chromatography-mass spectrometry; the lignin content TJW represents an important component of the plant cell wall and plays an important role in the physical barrier of plants against diseases and insect pests. The plant samples are treated with strong acid by the Klason lignin determination method to precipitate lignin, and then the lignin content is calculated.

[0044] The pest and disease resistance index API is calculated based on the polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW. The formula is as follows: .

[0045] It should be noted that in this formula: the numerator is 1, which is a constant. As the numerator of the formula, it plays a benchmark role. It reflects the degree of change of polyphenol oxidase activity relative to the reference activity. The square further amplifies the impact of this change, highlighting the importance of changes in polyphenol oxidase activity in the evaluation of pest and disease resistance. It reflects the relative change of phenylalanine ammonia lyase activity and its effect on plant resistance to diseases and insect pests. The square operation is also to enhance its influence on the results. It is an exponential function. By taking the form of negative exponents, when the content of these substances is high, the value of the exponential function is small, and the value of the denominator is relatively small, so that the value of the disease and pest resistance index API is larger. The denominator integrates information such as enzyme activity and the content of disease resistance-related substances, providing a comprehensive and adjustable standard for evaluating plant disease and pest resistance. The larger the API value, the stronger the plant's disease and pest resistance; the smaller the API value, the weaker the plant's disease and pest resistance, and it may be more susceptible to disease and pest attacks.

[0046] Step: 204: The method for calculating the plant physiological health index SCQ is: The plant physiological health index SCQ is calculated based on the photosynthetic efficiency index PEC and the pest and disease resistance index API. The formula is as follows: .

[0047] It should be noted that in this formula: Taking the square root of the photosynthetic efficiency index PEC can more reasonably reflect the impact of PEC on plant physiological health. It is an exponential function, which highlights the influence of the relative relationship between PEC and API on plant physiological health. It comprehensively reflects the comprehensive impact of the two key factors, photosynthetic efficiency and pest resistance, on plant physiological health, and provides a reasonable basis for accurately calculating the plant physiological health index SCQ. The square of the ratio of the photosynthetic efficiency index to the pest and disease resistance index further emphasizes the impact of the change in the ratio on the results. Adding 1 to the square of the ratio is to avoid the situation where the denominator is 0. At the same time, it also makes the denominator value always greater than 1, ensuring that the value of the plant physiological health index SCQ is within a reasonable range, which is convenient for the interpretation and comparison of the results.

[0048] Step 205: The method for calculating the pesticide residue degradation rate index YZC is: Pesticide residue data including current pesticide residue concentration GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y .

[0049] It should be noted that the current pesticide residue concentration GJH yIndicates the current residual concentration of the yth pesticide. The sample is collected and pre-treated by a liquid chromatography-mass spectrometry analyzer, such as extraction and purification, and then the residual concentration of the pesticide is detected by instrumental analysis; the maximum residue limit (MRL) of the pesticide y represents the maximum residue limit of the yth pesticide, obtained through the standard database of China's Ministry of Agriculture and Rural Affairs; the initial residue concentration of the pesticide EWP y It represents the initial residual concentration of the yth pesticide, which is obtained by collecting and testing samples by chemical analysis methods within a short period of time after the pesticide is used; the maximum residue limit KWE corresponding to the pesticide at the initial time y It represents the maximum residue limit corresponding to the yth pesticide at the initial time, which is obtained through the standard database of the Ministry of Agriculture and Rural Affairs of China.

[0050] According to the current residual concentration of pesticides GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y The formula for calculating the pesticide residue degradation rate index YZC is as follows: ; Among them, GJH y is the current residual concentration of the yth pesticide, MRL y is the maximum residue limit of the yth pesticide, EWP y is the initial residual concentration of the yth pesticide, KWE y is the maximum residue limit corresponding to the y-th pesticide at the initial time, y is the serial number corresponding to different types of pesticides, and its value is [1, s]; s is the number of pesticide types, and its value is a positive integer.

[0051] It should be noted that in this formula: This part is to sum the squares of the ratios of the current residue concentrations of all s pesticides to the maximum residue limit, highlighting the impact of the situation where the pesticide residue concentration is close to or exceeds the maximum residue limit on the overall index. The summation result is added by 1 and the reciprocal is taken, reflecting the impact of the overall relationship between the current pesticide residue concentration and the maximum residue limit on the pesticide residue degradation rate index, playing a role of regulation and balance. The index value is adjusted according to the cumulative relationship between the pesticide residue concentration and the maximum residue limit. The difference reflects the change in the pesticide residue concentration relative to the maximum residue limit from the initial moment to the current moment. Processing the above differences in the form of an exponential function can more sensitively reflect the impact of pesticide residue degradation on the index. By adding 1 to the exponential function and taking the inverse, we can finally get the contribution of this part to the pesticide residue degradation rate index. Together with the previous two parts, it constitutes the numerator, which comprehensively reflects the relationship between the pesticide residue concentration and the maximum residue limit and the impact of the changes from the initial to the current on the index. Overall, the larger the YZC value, the faster the pesticide residue degradation rate, the better the residue condition, and the smaller the impact on food safety and the environment; the smaller the YZC value, the slower the pesticide residue degradation and the higher the residue concentration may be.

[0052] Step 206: The method for calculating the soil nutrient balance index SNT is: Soil nutrient data includes the actual amount of nutrients in the soil. q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q .

[0053] It should be noted that the actual content of nutrients in the soil ANZ q It indicates the actual content of the qth nutrient in the soil, which is determined by chemical analysis methods. For example, for the nitrogen content in the soil, the Kjeldahl method can be used; for the phosphorus content, the molybdenum antimony colorimetric method can be used; for the potassium content, the flame photometer method can be used to obtain the actual content values ​​of various nutrients; the optimal recommended content of nutrients ORN q A reference value indicating the content range of the qth nutrient in the soil that is most suitable for plant growth, obtained from the crop planting manual; the amount of nutrients absorbed by plants PJX q It indicates the amount of the qth nutrient absorbed by plants from the soil. It is determined by plant tissue analysis. For example, for nitrogen, the amount of nitrogen absorbed by plants can be obtained by measuring the total nitrogen content in plant tissues and multiplying it by the dry weight of the plant. The optimal absorption amount of nutrients ILZ q Indicates the optimal absorption amount of the qth nutrient by the plant, obtained through crop cultivation technology data; the amount of nutrients added in the soil JCA qIt indicates the amount of the qth nutrient added to the soil by fertilization, organic fertilizer application, irrigation water, etc. It is calculated based on factors such as the amount of fertilizer applied, the content of nutrients in the fertilizer, and the utilization rate of the fertilizer. For example, if a certain amount of nitrogen fertilizer is applied, the amount of nitrogen added to the soil can be estimated based on the nitrogen content of the nitrogen fertilizer and the utilization rate of the nitrogen fertilizer in the soil; the optimal amount of nutrient supplement OKJ q It represents the most suitable supplement amount of the qth nutrient, obtained through soil test results; the microbial transformation amount of nutrients VZX q It indicates the amount of nutrient conversion by microorganisms in the soil. By using isotope tracing technology, specific nutrients are marked, such as nitrogen marked with 15N. The marked nutrients are applied to the soil, soil samples are collected regularly, and the conversion of marked nutrients between different forms is measured by mass spectrometer, such as the amount of ammonium nitrogen converted to nitrate nitrogen. The conversion of nitrogen by microorganisms is calculated in this way. The optimal microbial conversion of nutrients VBM q It represents the optimal conversion amount of the qth nutrient by microorganisms. By collecting data over many years and analyzing the microbial conversion amounts in different seasons and at different crop growth stages, the average value is statistically obtained as the optimal microbial conversion amount of nutrients in the soil.

[0054] According to the actual content of nutrients in the soil ANZ q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q The soil nutrient balance index SNT is calculated based on the following formula: ; Among them, ANZ q is the actual content of the qth nutrient, ORN q is the best recommended content of the qth nutrient, PJX q is the amount of the qth nutrient absorbed by plants from the soil, ILZ q is the optimal absorption amount of the qth nutrient by the plant, JCA q is the supplement amount of the qth nutrient in the soil, OKJ q is the optimal supplement amount of the qth nutrient, VZX q VBM is the microbial transformation amount of the qth nutrient in the soil. qis the optimal microbial conversion amount of the qth nutrient, q is the serial number corresponding to different nutrients, and its value is [1, w]; w is the number of nutrient types, and its value is a positive integer.

[0055] It should be noted that in this formula: The squares of the deviations of all w nutrients are summed to obtain a value that comprehensively reflects the overall deviation of the actual content of various nutrients in the soil from the optimal recommended content. The square root is taken to normalize the summation result so that the value of the soil nutrient balance index SNT will not increase excessively due to the increase in the number of nutrient types, and at the same time make the index value more comparable and practical. It reflects the relationship between the actual absorption of each nutrient by the plant and the optimal absorption amount. The squared sum highlights the impact of the plant's nutrient absorption on the soil nutrient balance. When the plant's nutrient absorption deviates greatly from the optimal absorption amount, the value of this part will be larger and its contribution to the denominator will also be greater. The sum of the squares of the ratios of the nutrient supplement amount to the optimal supplement amount in the soil reflects the impact of the deviation of the nutrient supplement situation from the optimal supplement situation on the soil nutrient balance; the square root of the sum of the two parts is taken and normalized, which corresponds to the processing method of the numerator part, so that the value of the denominator more reasonably reflects the comprehensive impact of plant absorption and nutrient supplementation on the soil nutrient balance; It is the sum of the ratio of the microbial transformation amount of nutrients in the soil to the optimal microbial transformation amount minus 1, reflecting the overall deviation of the microbial transformation of various nutrients from the optimal transformation. By treating the sum of the above deviations in the form of an exponential function, the effect of microbial transformation on soil nutrient balance can be more sensitively reflected. Add 1 to the exponential function and take the reciprocal to finally get the contribution of this part to the soil nutrient balance index. Together with the previous two parts, it constitutes the denominator, which comprehensively considers the effects of factors such as plant absorption, nutrient supplementation and microbial transformation on soil nutrient balance. Overall, when the SNT value is large, it means that the soil nutrient status is relatively balanced; when the SNT value is small, it means that there may be an imbalance in soil nutrients.

[0056] Step 207: The method for calculating the soil nutrient comprehensive health index SCH is: The soil nutrient health index SCH is calculated based on the soil nutrient balance index SNT, and the formula is as follows: ; Among them, δ is the weight coefficient of the soil nutrient balance index SNT, which is determined according to the influence of the soil nutrient balance index SNT on the soil nutrient health index SCH, and its value ranges from 0 to 1. represents a small change in the soil nutrient balance index, and dt represents a small change in time.

[0057] It should be noted that in this formula: Taking into account the soil nutrient balance status and its importance in assessing soil nutrient health, the contribution of SNT to the soil nutrient health index SCH was adjusted in a nonlinear manner, reflecting the complex relationship between soil nutrient balance and soil nutrient health more comprehensively and accurately. Squaring the rate of change further amplifies the impact of the rate of change, making the denominator value increase more significantly when the soil nutrient balance index changes significantly. Adding 1 to the square of the rate of change and taking the square root is to avoid the situation where the denominator is 0. At the same time, it also makes the denominator always greater than 1, ensuring that the value of the soil nutrient health index is within a reasonable range and can more reasonably reflect the impact of dynamic changes in soil nutrient balance on soil nutrient health. Overall, the larger the SCH value, the better the soil nutrient health; the smaller the SCH value, the possible problem with the soil nutrient health.

[0058] When used, combine the contents of step 201 to step 207: By calculating the corresponding environmental suitability index, plant physiological health index, pesticide residue degradation rate index and soil nutrient health index respectively, complex data are converted into intuitive and practical quantitative indicators, providing clear quantitative standards for accurately judging the growth status of plants, greatly improving the accuracy and efficiency of the analysis.

[0059] Step 3: Preset a set of plant health growth thresholds, compare the environmental suitability index TSB, plant physiological health index SCQ, pesticide residue degradation rate index YZC and soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

[0060] Step 301: The standards of the preset plant health growth threshold set are as follows: The plant health growth threshold set includes the favorable environment threshold WD, the unfavorable environment threshold WQ, the vigorous growth threshold GS, the sluggish growth threshold GF, the pesticide high degradation rate threshold NF, the pesticide low degradation rate threshold NB, the fertile soil threshold YT and the poor soil threshold YU.

[0061] It should be noted that the optimal environment threshold WD is obtained by collecting growth data of a large number of plants under suitable temperature, humidity and light intensity, calculating their average values ​​and then adding them up, and the optimal environment threshold WD is obtained; the unfavorable environment threshold WQ is obtained by collecting growth data of a large number of plants under abnormal temperature, humidity and light intensity, calculating their average values ​​and then adding them up, and the unfavorable environment threshold WQ is obtained.

[0062] The thriving growth threshold GS is obtained by collecting a large number of normal photosynthetic efficiency data of plants during the growth stage and calculating their average value; the sluggish growth threshold GF is obtained by collecting a large number of abnormal photosynthetic efficiency data of plants during the growth stage and calculating their average value.

[0063] The pesticide high degradation rate threshold NF is obtained by collecting data on a large number of plants in pesticide residue experiments and calculating their average and standard deviation. The average plus 2 times the standard deviation is used as the pesticide high degradation rate threshold NF; the average minus 2 times the standard deviation is used as the pesticide low degradation rate threshold NB.

[0064] The fertile soil threshold value YT is obtained by collecting a large amount of nutrient data indicating vigorous plant growth and calculating its average value, and the poor soil threshold value YU is obtained by collecting a large amount of nutrient data indicating slow plant growth and calculating its average value, and the poor soil threshold value YU is obtained by collecting a large amount of nutrient data indicating slow plant growth and calculating its average value.

[0065] Step 302: The criteria for determining the growth status of the genetically modified plants in the current agricultural greenhouse are as follows: The plant health growth threshold set includes a favorable environment threshold WD and a poor environment threshold WQ; wherein, the favorable environment threshold WD>the poor environment threshold WQ.

[0066] The environmental suitability index TSB is compared with the optimal environment threshold WD and the inferior environment threshold WQ to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When the environment is in a superior state, the environmental control strategy one is generated; when the environment is in a suitable state, the environmental control strategy two is generated; when the environment is in a suboptimal state, the environmental control strategy three is generated.

[0067] It should be noted that when in a superior environmental state, the first environmental control strategy is to maintain the current light intensity and duration to ensure that the photosynthesis of plants is fully carried out. The light angle can be fine-tuned appropriately to make the light evenly cover the plants, promote the balanced growth of the plants, stabilize the temperature in the greenhouse within a suitable range, avoid large temperature fluctuations, and control the humidity slightly below the current level to prevent excessive humidity from causing pests and diseases; when in a suitable environmental state, the second environmental control strategy is to increase the duration and intensity of artificial lighting to make up for the lack of natural light and improve the efficiency of photosynthesis. According to the plant growth stage and current temperature conditions, the temperature is slightly increased or decreased to make it closer to the optimal temperature for plant growth, ventilation is strengthened, humidity is reduced, and according to the soil humidity conditions, reasonable irrigation is carried out to keep the soil humidity suitable; when in a poor environmental state, the third environmental control strategy is to comprehensively check and clean the greenhouse covering to ensure good light transmittance, start the heating equipment, quickly increase the temperature in the greenhouse to a suitable range, and continuously monitor to prevent the temperature from dropping suddenly, turn on the dehumidification equipment, and quickly reduce the air humidity.

[0068] The plant healthy growth threshold set also includes a thriving growth threshold GS and a languid growth threshold GF; wherein the thriving growth threshold GS>the languid growth threshold GF.

[0069] The plant physiological health index SCQ is compared with the vigorous growth threshold GS and the withered growth threshold GF to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When in an exuberant physiological state, physiological control strategy one is generated; when in a stable physiological state, physiological control strategy two is generated; when in a weak physiological state, physiological control strategy three is generated.

[0070] It should be noted that when the plant is in a vigorous physiological state, the first physiological control strategy is to appropriately reduce the amount of nitrogen fertilizer applied, increase the proportion of phosphorus and potassium fertilizers, avoid excessive growth of plants, supplement trace elements, ensure comprehensive and balanced nutrients, maintain healthy growth of plants, lightly prune the plants, remove some dense branches and leaves, improve ventilation and light conditions, promote further improvement of photosynthesis efficiency, and prevent the breeding of diseases and pests; when the plant is in a stable physiological state, the second physiological control strategy is to supplement the nutrients required for plant growth according to the results of soil nutrient tests, maintain stable soil fertility, and fine-tune environmental factors such as temperature, humidity and light in the greenhouse to keep it in the optimal range for plant growth; when the plant is in a weak physiological state, the third physiological control strategy is to comprehensively inspect the plant, promptly discover and deal with diseases and pests, use biological control or low-toxic and high-efficiency chemical agents for prevention and control, and at the same time strengthen the plant's resistance, such as spraying plant growth regulators and foliar fertilizers, checking the root growth condition, improving soil aeration and drainage, and performing root pruning and disinfection when necessary.

[0071] The plant health growth threshold set also includes a pesticide high degradation rate threshold NF and a pesticide low degradation rate threshold NB; wherein, the pesticide high degradation rate threshold NF> the pesticide low degradation rate threshold NB.

[0072] The pesticide residue degradation rate index YZC is compared with the pesticide high degradation rate threshold NF and the pesticide low degradation rate threshold NB to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When the pesticide is in a state of efficient degradation, the pesticide residue control strategy 1 is generated; when the pesticide is in a state of conventional degradation, the pesticide residue control strategy 2 is generated; when the pesticide is in a state of inefficient degradation, the pesticide residue control strategy 3 is generated.

[0073] It should be noted that when the pesticide is in a state of efficient degradation, the pesticide residue control strategy 1 is generated: continue to maintain the current planting management measures, including reasonable irrigation, fertilization and pest control methods, ensure the stability of environmental factors to maintain the efficient degradation of pesticides, regularly monitor the pesticide residue degradation rate index, as well as the pesticide residues in the soil and plants, to ensure that the degradation effect continues to be good, and adjust the strategy in time if there are changes; when the pesticide is in a state of conventional degradation, the pesticide residue control strategy 2 is generated: increase the application of organic fertilizers or beneficial microbial agents, such as Bacillus, to improve the soil microbial community structure and enhance the microbial resistance to pesticides. The degradation ability of pesticides is enhanced, the degradation rate of pesticides is promoted, precise irrigation methods such as drip irrigation or sprinkler irrigation are used, large-scale flooding is avoided, the soil moisture is kept appropriate, and good soil environmental conditions are created for the degradation of pesticides; when the pesticides are inefficiently degraded, the third pesticide residue control strategy is generated: use adsorbents such as activated carbon and zeolite to treat the soil, adsorb some pesticide residues, reduce their concentration and activity in the soil, and reduce harm to plants. Under professional guidance, use some chemical reagents or adjuvants that can promote the degradation of pesticides with caution, but pay attention to avoid secondary pollution to the soil and plants, and strengthen environmental monitoring after use.

[0074] The plant health growth threshold set also includes a fertile soil threshold YT and a poor soil threshold YU; wherein, the fertile soil threshold YT>the poor soil threshold YU.

[0075] The soil nutrient health index SCH is compared with the fertile soil threshold YT and the poor soil threshold YU to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ; When the soil is in a state of abundant nutrients, nutrient control strategy one is generated; when the soil is in a state of balanced nutrients, nutrient control strategy two is generated; when the soil is in a state of scarce nutrients, nutrient control strategy three is generated.

[0076] It should be noted that when the soil is in a fertile nutrient state, the first nutrient control strategy is to continue the current fertilization frequency and dosage, but be careful to avoid excessive nutrient accumulation. A small amount of fertilization can be used multiple times to improve fertilizer utilization, reduce nutrient loss and waste, and avoid fertilizer damage to plants due to excessive one-time fertilization. When the soil is in a balanced nutrient state, the second nutrient control strategy is to reasonably arrange crop rotation and intercropping. Different crops have different nutrient requirements and absorption capacities. Crop rotation and intercropping can improve soil nutrient structure and improve the sustainability of soil fertility. When the soil is in a nutrient-deficient state, The third strategy for controlling nutrient generation is: apply sufficient base fertilizer, choose a combination of organic fertilizer and compound fertilizer to increase the organic matter content in the soil, improve the physical and chemical properties of the soil, provide long-term nutrients for plant growth, and apply topdressing in time during the critical period of plant growth. According to the nutrient needs of different growth stages, choose the appropriate type and amount of fertilizer, such as applying nitrogen fertilizer in the seedling stage to promote growth, and adding phosphorus and potassium fertilizers in the flowering stage to promote flowering and fruiting. For severely poor soils, measures such as soil improvement and deep soil plowing can be taken to improve soil structure and aeration, enhance soil fertilizer and water retention capacity, and create a good soil environment for plant growth.

[0077] When used, combine the contents of step 301 to step 302: By presetting a set of plant health growth thresholds, the environmental suitability index, plant physiological health index, pesticide residue degradation rate index and soil nutrient health index are compared with them respectively. Based on the judgment results, the AI ​​system generates corresponding control strategies, which can quickly and accurately judge the growth status of genetically modified plants. Once a certain index deviates from the threshold, it can promptly detect possible problems with plant growth, thereby achieving dynamic and precise regulation of plant growth, effectively ensuring the healthy growth of genetically modified plants, and improving the quality and efficiency of agricultural production.

[0078] On the other hand, the present invention also discloses an AI-based smart agricultural greenhouse management system, comprising: Data collection module, used to collect growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system; A data calculation module is used to calculate the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI according to the growth environment data; and calculate the environmental suitability index TSB according to the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI; Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; calculate the plant physiological health index SCQ based on the photosynthetic efficiency index PEC and pest and disease resistance index API; Calculate the pesticide residue degradation rate index YZC based on the pesticide residue data; Calculate the soil nutrient balance index SNT based on soil nutrient data; Calculate the soil nutrient health index SCH based on the soil nutrient balance index SNT; The data judgment module is used to preset a set of plant health growth thresholds, compare the environmental suitability index TSB, the plant physiological health index SCQ, the pesticide residue degradation rate index YZC and the soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of the genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

[0079] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An AI-based smart agricultural greenhouse management method, characterized by: The following steps are involved: Step 1: Collect growth environment data, plant physiological data, pesticide residue data, and soil nutrient data in agricultural greenhouses based on the AI ​​system; Step 2: Calculate the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI based on the growth environment data; Calculate the environmental suitability index TSB based on the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI; Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; The plant physiological health index SCQ is calculated based on the photosynthetic efficiency index PEC and the pest and disease resistance index API; Calculate the pesticide residue degradation rate index YZC based on the pesticide residue data; Calculate the soil nutrient balance index SNT based on soil nutrient data; Calculate the soil nutrient health index SCH based on the soil nutrient balance index SNT; Step 3: Preset a set of plant health growth thresholds, compare the environmental suitability index TSB, plant physiological health index SCQ, pesticide residue degradation rate index YZC and soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

2. According to claim 1, a smart agricultural greenhouse management method based on AI is characterized in that: The method for calculating the temperature deviation growth suitability index TDG, humidity dispersion index HDI and light intensity suitability index LUI is: Growth environment data including temperature values ​​MXA i , standard temperature value suitable for growth NWS, minimum temperature value that can be tolerated NFR and maximum temperature value BSK; Temperature values ​​according to MXA i , the standard temperature value NWS suitable for crop growth, the minimum temperature value NFR that crops can withstand, and the maximum temperature value BSK are used to calculate the temperature deviation growth suitability index TDG. The formula is as follows: ； Among them, MXA i is the temperature value measured at the i-th time, i is the serial number corresponding to different measurement times, and its value is [1, n]; n is the number of measurements, and its value is a positive integer; The growth environment data also includes humidity value CJQ j and humidity average value DWX; According to humidity value CJQ j The humidity dispersion index HDI is calculated by the humidity average value DWX according to the following formula: ； Among them, CJQ j is the humidity value at the jth time point, j is the serial number corresponding to different time points, and its value is [1, z]; z is the number of time points, and its value is a positive integer; The growth environment data also includes the light intensity value JCU k , average light intensity CNS, minimum light intensity MCA and maximum light intensity NCA; According to the light intensity value JCU k , the average light intensity CNS, the minimum light intensity MCA and the maximum light intensity NCA are used to calculate the light intensity suitability index LUI. The formula is as follows: ； Where is JCU k is the light intensity value measured in the kth area, k is the serial number corresponding to different areas, and its value is [1, m]; m is the number of areas in the greenhouse, and its value is a positive integer.

3. According to claim 2, a smart agricultural greenhouse management method based on AI is characterized in that: The method for calculating the environmental suitability index TSB is: The environmental suitability index TSB is calculated based on the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI. The formula is as follows: ； Among them, α1 is the weight coefficient of the temperature deviation growth suitability index TDG, which ranges from 0.1 to 0.3; α2 is the weight coefficient of the humidity dispersion index HDI, which ranges from 0.3 to 0.4; α3 is the weight coefficient of the light intensity suitability index LUI, which ranges from 0.4 to 0.5; and α1+α2+α3=1.

4. According to claim 3, a smart agricultural greenhouse management method based on AI is characterized in that: The method for calculating the photosynthetic efficiency index PEC and the pest resistance index API is: Plant physiological data include actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI; The photosynthetic efficiency index PEC is calculated based on the actual photosynthetic rate KSQ, leaf chlorophyll content CHI, light quantum efficiency MWQ, net photosynthetic rate PUI, dark respiration rate RDX, intercellular carbon dioxide concentration HDQ, chloroplast carbon dioxide concentration BWQ and maximum carboxylation rate EYI. The formula is as follows: ； Plant physiological data also include polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW; The pest and disease resistance index API is calculated based on the polyphenol oxidase activity value PPL, polyphenol oxidase reference activity value PQW, phenylalanine ammonia lyase activity value CSA, phenylalanine ammonia lyase reference activity value NWW, salicylic acid content FQF, jasmonic acid content TIE and lignin content TJW. The formula is as follows: 。 5. According to claim 4, a smart agricultural greenhouse management method based on AI is characterized in that: The method for calculating the plant physiological health index SCQ is: The plant physiological health index SCQ is calculated based on the photosynthetic efficiency index PEC and the pest and disease resistance index API. The formula is as follows: 。 6. The AI-based smart agricultural greenhouse management method according to claim 5 is characterized in that: The method for calculating the pesticide residue degradation rate index YZC is: Pesticide residue data including current pesticide residue concentration GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y ; According to the current residual concentration of pesticides GJH y , Maximum Residue Limits (MRL) of Pesticides y , initial residual concentration of pesticides EWP y and the maximum residue limit KWE corresponding to the pesticide at the initial stage y The formula for calculating the pesticide residue degradation rate index YZC is as follows: ； Among them, GJH y is the current residual concentration of the yth pesticide, MRL y is the maximum residue limit of the yth pesticide, EWP y is the initial residual concentration of the yth pesticide, KWE y is the maximum residue limit corresponding to the y-th pesticide at the initial time, y is the serial number corresponding to different types of pesticides, and its value is [1, s]; s is the number of pesticide types, and its value is a positive integer.

7. The AI-based smart agricultural greenhouse management method according to claim 6 is characterized in that: The method for calculating soil nutrient balance index SNT is: Soil nutrient data includes the actual amount of nutrients in the soil. q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q ; According to the actual content of nutrients in the soil ANZ q , the best recommended content of nutrients ORN q 、The amount of nutrients absorbed by plants PJX q , the optimal absorption amount of nutrients ILZ q , the amount of nutrients added to the soil q , the best amount of nutrients to supplement OKJ q , Microbial transformation of nutrients VZX q and the optimal microbial transformation of nutrients VBM q The soil nutrient balance index SNT is calculated based on the following formula: ； Among them, ANZ q is the actual content of the qth nutrient, ORN q is the best recommended content of the qth nutrient, PJX q is the amount of the qth nutrient absorbed by plants from the soil, ILZ q is the optimal absorption amount of the qth nutrient by the plant, JCA q is the supplement amount of the qth nutrient in the soil, OKJ q is the optimal supplement amount of the qth nutrient, VZX q VBM is the microbial transformation amount of the qth nutrient in the soil. q is the optimal microbial conversion amount of the qth nutrient, q is the serial number corresponding to different nutrients, and its value is [1, w]; w is the number of nutrient types, and its value is a positive integer.

8. The AI-based smart agricultural greenhouse management method according to claim 7 is characterized in that: The method for calculating the soil nutrient comprehensive health index SCH is: The soil nutrient health index SCH is calculated based on the soil nutrient balance index SNT, and the formula is as follows: ； Among them, δ is the weight coefficient of soil nutrient balance index SNT, which ranges from 0 to 1. represents a small change in the soil nutrient balance index, and dt represents a small change in time.

9. The AI-based smart agricultural greenhouse management method according to claim 8, characterized in that: The criteria for judging the growth status of genetically modified plants in current agricultural greenhouses are as follows: The plant health growth threshold set includes the optimal environment threshold WD and the inferior environment threshold WQ; wherein the optimal environment threshold WD> the inferior environment threshold WQ; The environmental suitability index TSB is compared with the optimal environment threshold WD and the inferior environment threshold WQ to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ； When in a superior environmental state, generate environmental control strategy 1; when in a suitable environmental state, generate environmental control strategy 2; when in a poor environmental state, generate environmental control strategy 3; The plant health growth threshold set also includes a thriving growth threshold GS and a withering growth threshold GF; wherein the thriving growth threshold GS> the withering growth threshold GF; The plant physiological health index SCQ is compared with the vigorous growth threshold GS and the withered growth threshold GF to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ； When in an exuberant physiological state, physiological control strategy one is generated; when in a stable physiological state, physiological control strategy two is generated; when in a weak physiological state, physiological control strategy three is generated; The plant health growth threshold set also includes a pesticide high degradation rate threshold NF and a pesticide low degradation rate threshold NB; wherein the pesticide high degradation rate threshold NF> the pesticide low degradation rate threshold NB; The pesticide residue degradation rate index YZC is compared with the pesticide high degradation rate threshold NF and the pesticide low degradation rate threshold NB to judge the growth status of the genetically modified plants in the current agricultural greenhouse. The standards are as follows: ； When the pesticide is in a highly efficient degradation state, the pesticide residue control strategy 1 is generated; when the pesticide is in a conventional degradation state, the pesticide residue control strategy 2 is generated; when the pesticide is in an inefficient degradation state, the pesticide residue control strategy 3 is generated; The plant health growth threshold set also includes a fertile soil threshold YT and a poor soil threshold YU; wherein, the fertile soil threshold YT>the poor soil threshold YU; The soil nutrient health index SCH is compared with the fertile soil threshold YT and the poor soil threshold YU to judge the growth status of genetically modified plants in the current agricultural greenhouse. The standards are as follows: ； When the soil is in a state of abundant nutrients, nutrient control strategy one is generated; when the soil is in a state of balanced nutrients, nutrient control strategy two is generated; when the soil is in a state of scarce nutrients, nutrient control strategy three is generated.

10. An AI-based smart agricultural greenhouse management system, characterized by: include: Data collection module, used to collect growth environment data, plant physiological data, pesticide residue data and soil nutrient data in agricultural greenhouses based on the AI ​​system; A data calculation module is used to calculate the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI according to the growth environment data; and calculate the environmental suitability index TSB according to the temperature deviation growth suitability index TDG, the humidity dispersion index HDI and the light intensity suitability index LUI; Calculate the photosynthetic efficiency index PEC and pest and disease resistance index API based on plant physiological data; The plant physiological health index SCQ is calculated based on the photosynthetic efficiency index PEC and the pest and disease resistance index API; Calculate the pesticide residue degradation rate index YZC based on the pesticide residue data; Calculate the soil nutrient balance index SNT based on soil nutrient data; Calculate the soil nutrient health index SCH based on the soil nutrient balance index SNT; The data judgment module is used to preset a set of plant health growth thresholds, compare the environmental suitability index TSB, the plant physiological health index SCQ, the pesticide residue degradation rate index YZC and the soil nutrient health index SCH with the plant health growth threshold set, and judge the growth status of the genetically modified plants in the current agricultural greenhouse; based on the judgment results, the AI ​​system generates corresponding control strategies.

Images