A plant lighting light quality regulation method, device, equipment and storage medium

Abstract

This invention relates to the field of plant lighting technology, and discloses a method, device, equipment, and storage medium for regulating plant lighting quality. It analyzes plant morphological image data and physiological index data using a pre-trained deep learning prediction model to obtain plant light quality requirements; it performs deviation analysis on plant variety growth measurement parameters and preset target growth curves to obtain deviation analysis results; it generates lighting quality regulation parameters based on the deviation analysis results and plant light quality requirements; it regulates lighting in preset lighting areas according to the lighting quality regulation parameters; and it determines plant light quality requirements based on a deep learning prediction model, generating targeted lighting quality regulation parameters to improve photosynthetic efficiency, reduce energy consumption, promote healthy plant growth, provide a reliable solution for facility cultivation, and promote the development of smart agriculture.

Description

Technical Field

[0001] This invention relates to the field of plant lighting technology, and in particular to a method, apparatus, equipment and storage medium for regulating the light quality of plant lighting. Background Technology

[0002] In plant lighting control in facility cultivation, plant factories, and other scenarios, existing light quality control methods largely rely on manual experience or single data judgments. Data collection is one-sided, often focusing only on the plant's external morphology or a single physiological indicator, without taking into account both external growth characteristics and internal physiological state. This leads to significant deviations in the judgment of light quality requirements. At the same time, some existing solutions lack growth deviation analysis mechanisms, making it impossible to clearly define the control priorities. Furthermore, the generation of light quality control parameters lacks specificity, making it difficult to adapt to different growth deviations. Moreover, lighting control is mostly based on fixed modes, which cannot match the dynamic growth needs of plants in real time. This not only wastes energy but also easily leads to problems such as excessive vegetative growth and stunted growth, reducing cultivation efficiency and plant quality. It is difficult to support the refined development of smart agriculture. Therefore, there is an urgent need for a technical solution that can achieve intelligent light quality control to solve the above-mentioned defects. Summary of the Invention

[0003] In order to overcome the shortcomings of the prior art, the present invention aims to provide a method, device, equipment and storage medium for regulating the light quality of plant lighting.

[0004] A method for regulating the light quality of plant lighting includes: collecting plant morphological image data and physiological index data; analyzing the plant morphological image data and physiological index data according to a pre-trained deep learning prediction model to obtain the plant light quality requirements; collecting plant variety growth measurement parameters, and performing deviation analysis on the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results. Lighting quality control parameters are generated based on the deviation analysis results and the light quality requirements of plants; lighting control is then applied to the preset lighting areas based on these parameters.

[0005] Furthermore, the step of analyzing plant morphological image data and physiological index data based on a pre-trained deep learning prediction model to obtain plant light quality requirements includes: collecting plant type and chlorophyll fluorescence signals; matching plant photosynthetic rate from a preset photosynthetic rate table according to plant type; analyzing plant photosynthetic rate and chlorophyll fluorescence signals according to a preset fast Fourier transform algorithm to obtain photosynthetic oscillation period and current photosynthetic phase; and analyzing plant morphological image data and physiological index data based on the deep learning prediction model, photosynthetic oscillation period, and current photosynthetic phase to obtain plant light quality requirements.

[0006] Furthermore, the analysis of plant morphological image data and physiological index data based on a deep learning prediction model, photosynthetic oscillation period, and current photosynthetic phase to obtain plant light quality requirements includes: analyzing plant morphological image data and physiological index data based on a preset plant growth state recognition algorithm to obtain plant growth state; and analyzing plant growth state based on a deep learning prediction model, photosynthetic oscillation period, and current photosynthetic phase to obtain plant light quality requirements.

[0007] Furthermore, the analysis of plant growth status based on a deep learning prediction model, photosynthetic oscillation cycle, and current photosynthetic phase to obtain plant light quality requirements includes: collecting time-series data on ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution; extracting features from the time-series data on ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution using a preset time-series feature analysis method to obtain time-series features of environmental factors; predicting plant growth status based on the deep learning prediction model and the time-series features of environmental factors to obtain basic light quality requirements; and optimizing the basic light quality requirements based on the photosynthetic oscillation cycle and current photosynthetic phase to obtain the plant light quality requirements.

[0008] Furthermore, the step of generating lighting quality control parameters based on deviation analysis results and plant light quality requirements includes: analyzing plant variety growth measurement parameters based on preset prior constraints and preset basic parameters for each band to obtain a basic light quality ratio; correcting the basic light quality ratio based on deviation analysis results to obtain an optimized light quality ratio; and generating lighting quality control parameters based on the optimized light quality ratio and plant light quality requirements.

[0009] Furthermore, the step of generating lighting quality control parameters based on optimized light quality ratio and plant light quality requirements includes: determining photoelectric conversion calibration coefficients based on optimized light quality ratios; collecting lighting driving current data and performing fitting calculations on the lighting driving current data according to a preset quadratic polynomial fitting method to obtain the actual photon flux; and generating lighting quality control parameters based on the photoelectric conversion calibration coefficients, the actual photon flux, and plant light quality requirements.

[0010] Furthermore, the deviation analysis of the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results includes: extracting the daily growth amount and plant height growth rate from the plant variety growth measurement parameters; constructing the actual growth curve based on the preset fitting function, the preset initial plant height parameter at planting time, the daily growth amount parameter, and the plant height growth rate parameter; and performing deviation analysis on the target growth curve and the actual growth curve to obtain the deviation analysis results.

[0011] Furthermore, a plant lighting quality control device includes: a data acquisition module for acquiring plant morphological image data and physiological index data; a data analysis module for analyzing the plant morphological image data and physiological index data according to a pre-trained deep learning prediction model to obtain the plant's light quality requirements; a deviation analysis module for acquiring plant variety growth measurement parameters and performing deviation analysis on the plant variety growth measurement parameters and a preset target growth curve to obtain deviation analysis results; a parameter generation module for generating lighting quality control parameters based on the deviation analysis results and the plant's light quality requirements; and a lighting control module for controlling the lighting of a preset lighting area according to the lighting quality control parameters.

[0012] Furthermore, a plant lighting light quality regulation device includes: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the plant lighting light quality regulation device to perform the various steps of the plant lighting light quality regulation method as described above.

[0013] Furthermore, a computer-readable storage medium stores instructions that, when executed by a processor, implement the steps of the plant lighting light quality regulation method as described above.

[0014] In the technical solution of this invention, by collecting plant morphological images and physiological index data, and taking into account both external growth characteristics and internal physiological states, reliable data support is provided for light quality demand analysis. Relying on a pre-trained deep learning prediction model, data patterns can be mined to output plant light quality requirements that align with plant photosynthetic needs. By combining deviation analysis of plant variety growth measurement parameters and target growth curves, key control points are identified, and targeted lighting quality control parameters are optimized and generated. These parameters can flexibly adapt to different growth deviations, effectively inhibiting excessive plant growth and promoting overall growth. Automated control of the lighting area is achieved through these lighting quality control parameters, ensuring real-time matching between the light environment and plant growth status and light quality requirements. This improves photosynthetic efficiency, reduces energy waste, helps plants grow healthily according to the target curve, enhances cultivation efficiency and plant quality, and provides reliable light quality control solutions for facility cultivation, plant factories, and other scenarios, promoting the refined development of smart agriculture. Attached Figure Description

[0015] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a first flowchart of a plant lighting light quality regulation method provided in an embodiment of the present invention; Figure 2This is a second flowchart of a method for regulating the light quality of plant lighting provided in an embodiment of the present invention; Figure 3 This is a third flowchart of a plant lighting light quality regulation method provided in an embodiment of the present invention; Figure 4 This is a fourth flowchart of a plant lighting light quality regulation method provided in an embodiment of the present invention; Figure 5 The fifth flowchart of a plant lighting light quality regulation method provided in an embodiment of the present invention; Figure 6 The sixth flowchart of a method for regulating the light quality of plant lighting provided in an embodiment of the present invention; Figure 7 The seventh flowchart of a method for regulating the light quality of plant lighting provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of a plant lighting light quality regulation device provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of a plant lighting light quality control device provided in an embodiment of the present invention. Detailed Implementation

[0016] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of a plant lighting light quality regulation method according to the present invention includes: 101. Collect plant morphological image data and physiological index data; In this embodiment, plant morphology image data is used to capture external growth characteristics of plants (such as leaf morphology, plant height, crown width, stem thickness, leaf color, etc.), which are external evidence that intuitively reflect the plant's growth status. It can be continuously acquired through image acquisition equipment, providing visual data support for subsequent growth status analysis. At the same time, it can capture external abnormalities such as yellowing leaves and excessive stem growth, helping to quickly identify growth problems. Physiological index data is used to characterize the plant's internal growth status (such as chlorophyll content, photosynthetic rate, nutrient content, transpiration rate, etc.), reflecting physiological processes such as photosynthesis and nutrient absorption. It is the internal data source for analyzing plant growth needs, providing comprehensive and reliable basic data for subsequent light quality requirement analysis, ensuring that the light quality requirement judgment is consistent with the actual growth of the plant. 102. Analyze plant morphological image data and physiological index data based on pre-trained deep learning prediction models to obtain plant light quality requirements; In this embodiment, the pre-trained deep learning prediction model was trained using a large number of plant growth samples, morphological image data, physiological index data, and light quality regulation data. It possesses powerful feature extraction, pattern matching, and demand prediction capabilities. This model can perform visual feature mining on the input plant morphological image data, analyze the inherent patterns of physiological index data, and output suitable basic light quality requirements (such as light quality band ratio, light intensity benchmark, and illumination duration). The light quality bands cover key bands such as red light, blue light, and far-red light, which aligns with the different spectral requirements of plant photosynthesis and provides a basis for the generation of subsequent lighting light quality regulation parameters. 103. Collect plant variety growth measurement parameters and perform deviation analysis on the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results; In this embodiment, the plant growth measurement parameters are parameters reflecting the actual growth progress of the plant (such as plant height growth rate, number of leaves, internode length, biomass, etc.), which are collected continuously at fixed intervals to ensure the continuity and timeliness of the data. The preset target growth curve is a standardized growth curve established based on the growth characteristics and cultivation scenario of the plant variety after extensive experimental verification. It covers the ideal growth indicators of each growth stage of the plant, conforms to the laws of common growth models such as linear and exponential growth, and clarifies the target growth status at different stages. Through the deviation analysis algorithm, the actual collected growth measurement parameters are compared with the target growth curve to identify the magnitude and type of deviation (such as growth lag, excessive growth, deviation caused by insufficient nutrients, etc.), generate detailed deviation analysis results, clarify the direction and focus of light quality regulation, and provide a basis for the subsequent optimization of light quality regulation parameters. 104. Generate lighting quality control parameters based on the deviation analysis results and plant light quality requirements; In this embodiment, the lighting quality control parameters are the basis for realizing plant lighting control, covering key parameters such as light quality band ratio, light intensity, lighting cycle, and light uniformity. Among them, the light quality ratio can be flexibly adjusted according to the needs of the plant to adjust the ratio of red light to blue light, and the light intensity can be adapted to low light intensity or saturated light intensity according to the growth stage. During the generation process, based on the output plant light quality requirements, targeted optimization is carried out in combination with the deviation analysis results. For example, for the deviation of delayed growth, the proportion of red light is appropriately increased and the light intensity is increased to promote growth; for the deviation of excessively rapid growth, the light quality ratio is adjusted and the lighting duration is shortened to inhibit excessive growth. This ensures that the generated lighting quality control parameters not only meet the plant light quality requirements, but also make up for the deviation between actual growth and target growth, thus achieving targeted light quality control. 105. Adjust the lighting in the preset lighting area according to the lighting quality control parameters; In this embodiment, the preset lighting area is the plant cultivation area (such as greenhouse, plant factory, seedling shed, etc.). The lighting equipment uses LED light sources with adjustable light quality and intensity, which can achieve multi-spectral control. During the control process, the generated lighting quality control parameters are transmitted to the lighting control system. The system automatically adjusts the operating status of the lighting equipment according to the parameters, matches the current growth needs and deviation correction needs of the plants in real time, and ensures that the light environment of the lighting area is always consistent with the plant growth status and light quality needs, ensuring the light quality control effect, helping the plants to grow healthily according to the target growth curve, and improving cultivation efficiency and plant quality. In this embodiment, by collecting plant morphological images and physiological index data, taking into account both external growth characteristics and internal physiological states, reliable data support is provided for light quality demand analysis. Relying on a pre-trained deep learning prediction model, data patterns can be mined to output plant light quality requirements that align with plant photosynthetic needs. By combining deviation analysis of plant variety growth measurement parameters and target growth curves, key control points are identified, and targeted lighting quality control parameters are optimized and generated. These parameters can flexibly adapt to different growth deviations, effectively suppressing excessive plant growth and promoting overall growth. Automated control of the lighting area through these parameters ensures real-time matching of the light environment with plant growth status and light quality requirements, improving photosynthetic efficiency, reducing energy waste, and helping plants grow healthily according to the target curve. This enhances cultivation efficiency and plant quality, providing reliable light quality control solutions for facility cultivation, plant factories, and other scenarios, and promoting the refined development of smart agriculture.

[0018] Please see Figure 2 A second embodiment of a plant lighting light quality regulation method according to the present invention includes: 201. Collect plant type and chlorophyll fluorescence signals; In this embodiment, plant type is used to clarify the characteristics of plant varieties (such as the photosynthetic characteristics and light quality requirements of different crops), providing a basis for subsequent photosynthetic rate matching; chlorophyll fluorescence signal reflects the operating state of the photosystem and is a data source for analyzing the physiological laws of photosynthesis. It can capture the energy conversion efficiency in the photosynthetic process and provide reliable support for the subsequent extraction of photosynthetic oscillation period and photosynthetic phase. 202. Obtain the plant photosynthetic rate from the preset photosynthetic rate table based on the plant type; In this embodiment, the photosynthetic rate table is a standardized data table established based on the growth characteristics and cultivation scenarios of different plant varieties and after extensive experimental verification. It covers the basic photosynthetic rate range of various plants under normal conditions, providing basic data for subsequent analysis of photosynthetic oscillation period and photosynthetic phase, ensuring the accuracy of photosynthetic related parameter analysis, while taking into account the differences in photosynthetic characteristics of different plant varieties. 203. Analyze the photosynthetic rate and chlorophyll fluorescence signal of the plant according to the preset fast Fourier transform algorithm to obtain the photosynthetic oscillation period and the current photosynthetic phase; In this embodiment, the Fast Fourier Transform algorithm has powerful signal analysis capabilities, which can effectively filter out interference information in the original data and uncover the fluctuation patterns of photosynthetic rate and chlorophyll fluorescence signal. Among them, the photosynthetic oscillation period reflects the inherent physiological fluctuation pattern of plant photosynthesis (such as the diurnal photosynthetic rate fluctuation period), which is the intrinsic rhythmic feature of plant photosynthesis. The current photosynthetic phase represents the current photosynthetic efficiency stage of the plant (such as the peak photosynthetic period and the decline period), determines the plant's real-time requirements for light quality and light intensity, provides a physiological basis for subsequent optimization of light quality requirements, and realizes the adaptation of light quality supply and photosynthetic rhythm. 204. Based on deep learning prediction models, photosynthetic oscillation cycles, and current photosynthetic phase, plant morphological image data and physiological index data are analyzed to obtain plant light quality requirements; In this embodiment, feature extraction and pattern matching are performed on the input plant morphology image data (such as leaf morphology, plant height, crown width, etc.) and physiological index data (such as chlorophyll content, photosynthetic rate, etc.), and the plant growth status (such as vigorous growth, slow growth, presence of stress, growth stage, etc.) is finally output. The plant growth status is analyzed by this deep learning prediction model to obtain the basic light quality requirements. The basic light quality requirements predicted by the model are corrected by combining the inherent law of photosynthetic oscillation cycle and the current photosynthetic phase, so as to achieve the matching of light quality requirements with plant growth status, improve photosynthetic utilization efficiency, reduce energy waste, provide suitable light environment for plants, help plants grow healthily, and improve the rationality of light quality regulation. In this embodiment, by collecting plant type and chlorophyll fluorescence signals, and relying on a preset standardized photosynthetic rate table, the photosynthetic rate is quickly matched to ensure data reliability. A pre-trained Fast Fourier Transform algorithm efficiently filters interference, extracts the photosynthetic oscillation period and current photosynthetic phase, and captures the inherent photosynthetic rhythm and real-time photosynthetic efficiency status of the plant, providing a physiological basis for light quality optimization. Combined with a deep learning prediction model, morphological images and physiological index data are fused to identify the plant's growth status, output basic light quality requirements, and combine these with photosynthetic parameter corrections to achieve matching of light quality requirements with plant growth status and photosynthetic rhythm. This effectively improves photosynthetic utilization efficiency, reduces energy waste, provides a suitable light environment for plants, promotes their healthy growth, enhances the rationality of light quality regulation, provides strong support for plant cultivation, and meets the needs of smart agriculture development.

[0019] Please see Figure 3 A third embodiment of a plant lighting light quality regulation method according to the present invention includes: 301. Based on a preset plant growth status recognition algorithm, analyze plant morphological image data and physiological index data to obtain the plant growth status; In this embodiment, a pre-trained plant growth status recognition algorithm extracts features and performs pattern matching on input plant morphological image data (such as leaf morphology, plant height, crown width, etc.) and physiological index data (such as chlorophyll content, photosynthetic rate, etc.), ultimately outputting the plant growth status (such as vigorous growth, slow growth, presence of stress, growth stage, etc.). This pre-trained algorithm adopts an architecture combining deep convolutional neural networks (CNN) and transfer learning models. Based on mature models such as ResNet and EfficientNet, it is specifically optimized in combination with plant growth characteristics. Through transfer learning, it reuses massive amounts of plant growth data and image features, eliminating the need to train the model from scratch. Only fine-tuning parameters for specific plant varieties and cultivation scenarios is required to ensure recognition accuracy. The algorithm takes into account both morphological visual features and internal physiological states. It captures external morphological anomalies of leaves, stems, and roots through image recognition, and judges the internal growth status of plants through physiological indicators. It can process data in real time and quickly output growth status results, providing data support for subsequent light quality demand analysis and growth status regulation. 302. Analyze the plant growth status based on deep learning prediction models, photosynthetic oscillation cycles, and current photosynthetic phases to obtain the plant's light quality requirements; In this embodiment, the photosynthetic oscillation period reflects the inherent fluctuation pattern of photosynthesis (such as the diurnal photosynthetic rate fluctuation period), and the current photosynthetic phase represents the current photosynthetic efficiency stage (such as the peak photosynthetic period and the decline period). The deep learning prediction model is a prediction model that has been pre-trained with a large number of plant growth samples and environmental time-series data, and has the ability to learn the mapping between environmental factors and plant growth status. By analyzing the plant growth status through this deep learning prediction model, the basic light quality requirements are obtained. The basic light quality requirements predicted by the model are corrected by combining the inherent pattern of the photosynthetic oscillation period and the current photosynthetic phase, so as to match the light quality requirements with the plant growth status, improve photosynthetic utilization efficiency, reduce energy waste, provide suitable light environment for plants, help plants grow healthily, and improve the rationality of light quality regulation. In this embodiment, the pre-trained plant growth status recognition algorithm adopts an architecture combining deep convolutional neural networks and transfer learning. Based on mature models such as ResNet and EfficientNet, it is trained using massive amounts of plant growth-related data. It eliminates the need to train a model from scratch; only parameter fine-tuning based on specific plant varieties and cultivation scenarios is required to quickly adapt to various application scenarios. This algorithm can fully utilize the features of massive amounts of plant growth-related data, efficiently analyze plant morphological images and physiological indicators, capture plant growth status, and consider both external morphological features and internal physiological states to achieve rapid growth status recognition. This provides solid data support for subsequent light quality demand analysis, while reducing model training costs and manual intervention costs, and improving recognition efficiency. Furthermore, by combining deep learning prediction models, photosynthetic oscillation cycles, and the current photosynthetic phase, the algorithm deeply analyzes plant growth status. By correcting the light quality supply scheme, it effectively avoids the problem of light quality supply being out of sync with the actual needs of plants, improves photosynthetic utilization efficiency, provides plants with a suitable light environment, promotes healthy plant growth, and enhances the rationality of light quality regulation, providing strong support for plant cultivation and promoting the efficient development of smart agriculture.

[0020] Please see Figure 4 The fourth embodiment of a plant lighting light quality regulation method in this invention includes: 401. Collect time-series data of ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution; In this embodiment, collecting time-series data on ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution is a process of continuously and regularly collecting key parameters of the plant growth environment. Ambient temperature time-series data records the continuous changes in temperature over time within the cultivation area, reflecting diurnal fluctuations and phased increases / decreases. Ambient humidity time-series data tracks dynamic changes in humidity, reflecting the impact of humidity on plant transpiration and water metabolism. Carbon dioxide concentration time-series data records real-time changes in CO2 concentration; as a raw material for photosynthesis, CO2 concentration fluctuations are correlated with plant photosynthetic efficiency. Nutrient solution time-series data includes continuous changes in parameters such as nutrient solution concentration, EC value, and pH value, characterizing the dynamic level of nutrient supply to plant roots. These data are collected continuously at fixed intervals to form a complete time-series dataset, comprehensively and accurately reflecting the dynamic changes in the plant growth environment, providing a raw and reliable data foundation for subsequent time-series feature extraction and plant growth status prediction. 402. Based on the preset time series feature analysis method, feature extraction is performed on the environmental temperature time series data, environmental humidity time series data, carbon dioxide concentration time series data, and nutrient solution time series data to obtain the time series features of environmental factors; In this embodiment, the time-series feature analysis method is a comprehensive analysis method based on time series mining, including trend extraction algorithms, fluctuation feature calculation methods, period analysis algorithms, and extreme value identification methods. It is adapted to the characteristics of four types of environmental time-series data. The specific implementation process is as follows: For environmental temperature time-series data: the trend extraction algorithm captures the long-term trend of temperature change over time (such as daytime warming, nighttime cooling, and continuous multi-day warming and cooling trends); fluctuation feature calculation obtains parameters such as daily temperature fluctuation amplitude and frequency; extreme value identification extracts the daily highest and lowest temperatures and their occurrence times, ultimately forming temperature time-series features that reflect the impact of dynamic temperature changes on plant photosynthesis and transpiration. For environmental humidity time-series data: the focus is on extracting humidity fluctuation amplitude, duration of stable humidity, and the relationship between humidity and temperature (such as the decrease in humidity when temperature rises), while simultaneously identifying abnormal humidity fluctuation nodes (such as sudden increases and decreases), forming a humidity time series. Features are tailored to the dynamic needs of plant water metabolism and stomatal opening and closing. For carbon dioxide concentration time-series data: through periodic analysis algorithms, the diurnal fluctuation cycle of carbon dioxide concentration is extracted (e.g., the periodic pattern of concentration decrease due to photosynthetic consumption during the day and concentration increase due to respiration at night); the average concentration level, peak / trough values ​​and duration are calculated to form carbon dioxide time-series features, which directly reflect the dynamic supply of raw materials for plant photosynthesis; for nutrient solution time-series data (including nutrient solution concentration, EC value, and pH value time-series data): the long-term change trend of nutrient solution parameters (e.g., the slow decreasing trend of concentration), fluctuation amplitude and abnormal fluctuation nodes are extracted, and the correlation between nutrient solution and temperature and humidity (e.g., the change pattern of nutrient solution concentration when temperature rises) is analyzed to form nutrient solution time-series features, which characterize the dynamic level of nutrient supply to plant roots. Finally, these extracted temperature time-series features, humidity time-series features and nutrient solution time-series features are integrated to form environmental factor time-series features. 403. Predict plant growth status based on deep learning prediction models and temporal characteristics of environmental factors to obtain basic light quality requirements; In this embodiment, the source model of the deep learning prediction model is an LSTM or Transformer model trained on a large amount of plant growth data and environmental data. Relying on massive data training, it has powerful time series processing and trend prediction capabilities. The time series features of environmental factors are input into the deep learning prediction model. The model combines the dynamic change law of the environment to predict the current and short-term growth status of plants, such as photosynthetic potential, and outputs the basic light quality requirements adapted to the current environmental conditions. The basic light quality requirements include parameters such as the light quality band ratio and light intensity benchmark adapted to the environmental state. It is an initial light quality requirement scheme derived from the dynamic trend of the environment, providing a benchmark for subsequent optimization and adjustment at the physiological rhythm level. 404. Optimize the basic light quality requirements based on the photosynthetic oscillation period and the current photosynthetic phase to obtain the plant's light quality requirements; In this embodiment, the photosynthetic oscillation period reflects the inherent physiological fluctuation pattern of plant photosynthesis, and the current photosynthetic phase represents the current photosynthetic efficiency stage of the plant, directly determining the plant's real-time requirements for light quality and intensity. The basic light quality requirement is derived only from the environment and growth trend, without considering the plant's own photosynthetic physiological rhythm. Therefore, it is necessary to correct and optimize it by matching the photosynthetic oscillation period with the current photosynthetic phase. By matching the corresponding light quality ratio and light intensity for different photosynthetic phases, the light quality supply is synchronized with the plant's photosynthetic physiological rhythm, ultimately obtaining the plant's light quality requirement that matches the plant's real-time physiological state, providing a target basis for subsequent light quality regulation. In this embodiment, by continuously collecting multi-dimensional environmental time-series data and extracting time-series features, the dynamic changes in the environment can be comprehensively captured, providing a reliable basis for growth prediction. By relying on a deep learning prediction model to integrate the time-series features of environmental factors, the plant growth status can be predicted, making basic light quality requirements both environmentally adaptable and forward-looking. Combining photosynthetic oscillation period and photosynthetic phase to optimize basic light quality requirements ensures a high degree of match between light quality requirements and plant photosynthetic physiological rhythms, further enhancing the rationality of light quality requirements. This achieves an organic combination of environmental data, growth prediction, and physiological rhythms, providing a target-oriented approach for plant lighting quality regulation that aligns with actual growth needs, effectively improving photosynthetic utilization efficiency, and promoting healthy and efficient plant growth.

[0021] Please see Figure 5 The fifth embodiment of a plant lighting light quality regulation method in this invention includes: 501. Analyze the plant variety growth measurement parameters based on the preset prior constraints and preset basic parameters for each band to obtain the basic light quality ratio. In this embodiment, the prior constraints are constraint standards set based on plant cultivation experience, plant physiological characteristics, and the performance of lighting equipment. These include the light quality tolerance range of different plant varieties (e.g., leafy vegetables have a higher demand for blue light, while fruiting vegetables have a more prominent demand for red light), the band output limit of the lighting equipment, and energy consumption control thresholds. Basic parameters for each band are defined: the basic functions and benchmark parameters of different light quality bands (red light 660nm, blue light 450nm, etc.) are clarified, such as red light promoting plant photosynthesis and flowering / fruiting, blue light regulating plant morphogenesis and chlorophyll synthesis, and the basic photon flux of each band accounting for... Light quality ratios, light intensity baselines, and other parameters provide a basic reference standard for generating basic light quality ratios. Plant growth measurement parameters, including plant height, daily growth, plant height growth rate, and chlorophyll content, are used to match suitable light quality ratios. For example, for slow-growing plants, the proportion of red light can be appropriately increased to promote photosynthesis, while for plants with yellowish leaves, the proportion of blue light can be optimized to promote chlorophyll synthesis. The basic light quality ratio is the "initial benchmark" for light quality regulation. By using prior constraints, unreasonable ratios are avoided, ensuring that the basic light quality ratio conforms to the characteristics and basic growth needs of plant varieties, laying a solid foundation for subsequent optimization and adjustment. 502. Based on the deviation analysis results, the basic light quality ratio is corrected to obtain an optimized light quality ratio; In this embodiment, if the deviation analysis result indicates a lagging growth rate (e.g., actual plant height is lower than the target plant height), and the cause of the deviation is determined to be insufficient light or an unreasonable light quality ratio, the proportion of red light can be appropriately increased, and the photon flux can be increased to promote photosynthesis and improve the growth rate. If the deviation analysis result indicates excessive plant growth (e.g., excessively rapid plant height growth and thin stems), the proportion of blue light can be increased to inhibit excessive growth, promote thicker stems, and correct the growth trend. If the deviation analysis result indicates poor leaf development (e.g., low chlorophyll content and yellowing leaves), the ratio of blue light to red light can be optimized to promote chlorophyll synthesis and leaf morphology. By correcting the basic light quality ratio, light quality regulation becomes more targeted. 503. Generate lighting quality control parameters based on optimized light quality ratios and plant light quality requirements; In this embodiment, lighting quality control parameters are generated by combining optimized light quality ratio with plant light quality requirements. This not only fits the hardware characteristics of the equipment but also matches the light requirements of plants at different growth stages, making the light quality output more targeted, realizing dynamic control of light quality, creating a suitable light environment for plants, effectively promoting plant growth, and improving the intelligent level of plant lighting control. In this embodiment, the basic light quality ratio is determined by prior constraints, basic parameters of each band, and plant variety growth measurement parameters. This allows for the avoidance of setting unreasonable basic light quality ratios based on cultivation experience and equipment performance, aligning with the physiological characteristics and basic growth needs of different plant varieties, thus laying a reliable foundation for subsequent regulation. Dynamic correction of the basic light quality ratio, combined with deviation analysis results, can specifically address issues such as delayed plant growth, excessive vegetative growth, and poor leaf development, ensuring the light quality ratio matches the actual growth state and effectively correcting growth deviations. Finally, the optimized light quality ratio and the plant's real-time light quality requirements are integrated to generate light quality regulation parameters. This not only matches the hardware characteristics of the lighting equipment but also meets the light requirements of different plant growth stages, achieving dynamic light quality regulation, improving light utilization efficiency, creating an optimal growth light environment for plants, promoting photosynthesis and robust plant development, enhancing the intelligence level of plant lighting regulation, and contributing to high-quality and efficient plant growth.

[0022] Please see Figure 6 The sixth embodiment of a plant lighting light quality regulation method in this invention includes: 601. Determine the photoelectric conversion calibration coefficient based on the optimized light quality ratio; In this embodiment, the light quality ratio is optimized: the theoretical ratio and target light intensity of each light band (e.g., red light, blue light) are defined. Different light quality ratios (e.g., 60% red light and 40% blue light) correspond to different workloads of the light-emitting modules in different bands of the lighting equipment, resulting in differences in photoelectric conversion efficiency. Therefore, photoelectric conversion calibration coefficients need to be set specifically. The purpose of the photoelectric conversion calibration coefficients is to correct for issues such as hardware losses and band cross-interference in lighting equipment. With the same driving current input, the actual output light intensity of different bands may deviate from the theoretical value (e.g., the theoretical blue light intensity is set to 50 μmol / m²·s, but the actual output is only 45 μmol / m²·s). The photoelectric conversion calibration coefficients can be used to correct this deviation, ensuring that the output light quality of the equipment matches the optimized light quality ratio. Combining the factory parameters of the lighting equipment and previous debugging data, photoelectric conversion calibration coefficients are set for each band in the optimized light quality ratio. For example, the calibration coefficient for the red light band is 1.02, and the calibration coefficient for the blue light band is 0.98, providing a calibration basis for subsequent calculations of actual photonic quantum flux. 602. Collect lighting drive current data, and perform fitting calculation on the lighting drive current data according to the preset quadratic polynomial fitting method to obtain the actual photonic quantum flux; In this embodiment, lighting drive current data (such as red light independent channel current and blue light independent channel current) of LED lighting modules in each band are collected in real time. The lighting drive current data is the most direct control variable of LED output light intensity. The lighting drive current data is fitted and calculated using a quadratic polynomial fitting method. The specific expression is as follows: , In the formula, The independent variable represents the magnitude of the lighting drive current for a specific wavelength band (such as red light / blue light). The dependent variable is the actual photon flux (PPF / PPFD) obtained from the fitting. The first fitting coefficient, The second fitting coefficient, The third fitting coefficient is used. Each fitting coefficient is determined by the least squares method based on the factory calibration data or measured calibration data of the LED lamp model. The luminous efficiency of the LED is not a simple linear relationship with the driving current. When the current is low, the light intensity increases linearly with the current. When the current increases to the current threshold, the light intensity growth rate will gradually slow down due to factors such as chip heating and quantum well efficiency reduction, showing nonlinear saturation characteristics. The quadratic polynomial can fit this nonlinear curve of "fast at first and slow later". 603. Generate lighting quality control parameters based on photoelectric conversion calibration coefficient, actual photon flux, and plant light quality requirements; In this embodiment, considering physical factors such as individual differences in LED devices and optical path attenuation, the actual photonic flux needs to be multiplied by the photoelectric conversion calibration coefficient of the corresponding band to obtain the corrected actual photonic flux. The actual photonic flux reflects the current actual light output intensity of the device and is used to determine whether the current light quality output meets the needs of the plant. If the actual photonic flux is lower than the required value, the driving current needs to be adjusted to increase the light intensity, and vice versa. The plant's light quality requirements clearly define the most suitable light quality intensity and band ratio for the current growth stage of the plant, which is the goal of generating the control parameters. This ensures that the final generated lighting light quality control parameters match the real-time growth needs of the plant (e.g., high blue light and low light intensity are required in the seedling stage, and high red light and high light intensity are required in the growth stage). This achieves real-time control of light quality and leverages the promoting effect of light quality control on plant growth. In this embodiment, by setting photoelectric conversion calibration coefficients for each band according to the optimized light quality ratio, the light output deviation caused by LED hardware loss, individual device differences, and band interference can be effectively corrected, ensuring that the actual light output ratio of the device is consistent with the theoretical optimized ratio. The actual photon flux is calculated by fitting the lighting drive current data with a quadratic polynomial, which can match the nonlinear light emission characteristics of LEDs and improve the accuracy of light intensity measurement. After calibrating the fitting results with photoelectric conversion calibration coefficients, the true photon flux is obtained. Then, combined with the light quality requirements of different plant growth stages, control parameters are generated, which can dynamically adjust the drive current so that the light quality output matches the plant growth needs in real time, providing a stable and reliable light environment support for the efficient and high-quality growth of plants.

[0023] Please see Figure 7 The seventh embodiment of a plant lighting light quality regulation method in this invention includes: 701. Extract daily growth and plant height growth rate from plant variety growth measurement parameters; In this embodiment, two key indicators, "daily growth" and "plant height growth rate," are screened and extracted from plant variety growth measurement parameters. These parameters typically include multi-dimensional data such as plant height, leaf length, leaf width, fresh weight, and dry weight. Daily growth and plant height growth rate are the most intuitive and easily quantifiable indicators reflecting plant growth status, directly demonstrating the plant's current growth vitality and pace. For example, a low plant height growth rate may indicate insufficient light, nutrient deficiencies, or an unsuitable environment. Excessive fluctuations in daily growth may reflect instability in light quality and environmental parameters, providing foundational data for subsequent curve construction and deviation analysis. The extraction process must ensure the temporal continuity of the data (e.g., collecting plant height data at fixed times daily) to avoid distortion in the calculation of daily growth and growth rate due to time discrepancies. Simultaneously, it is necessary to consider the characteristics of different plant varieties and distinguish their growth rate baselines (e.g., the plant height growth rate differs significantly between herbaceous and woody plants) to ensure the extracted parameters are comparable and have reference value. 702. The actual growth curve is constructed based on the preset fitting function, preset initial plant height parameters at planting time, daily growth parameters, and plant height growth rate parameters. In this embodiment, the fitting function (such as a linear function, a logistic function, a quadratic polynomial function, etc.) is used, with the logistic function best matching the "slow-fast-slow" growth cycle of most plants (slow during germination, rapid during growth, and slow during maturity), ensuring that the fitted curve can truly reflect the natural laws of plant growth. The initial plant height parameter at planting time serves as the starting point benchmark for the growth curve, clarifying the initial state of the plant in the early stages of regulation. The daily growth rate parameter and the plant height growth rate parameter serve as data support for curve fitting. The daily growth rate determines the daily increment of the actual growth curve, and the plant height growth rate determines the slope change of the actual growth curve. The combination of the two can fit the growth rhythm of the plant at different growth stages, so that the actual growth curve can clearly show the plant's growth trend (such as accelerated growth, deceleration, and stagnation). The discrete growth parameters (daily growth rate and plant height growth rate) are transformed into continuous actual growth curves, realizing the "visualization and trending" presentation of the plant's growth status. The actual growth curve can more intuitively reflect the dynamic changes in plant growth, making it easier to quickly identify growth anomalies (such as a sudden flattening of the curve or a sharp drop in the slope), providing a comparable and quantifiable carrier for subsequent deviation analysis. 703. Perform a deviation analysis on the target growth curve and the actual growth curve to obtain the deviation analysis results; In this embodiment, commonly used deviation analysis methods include mean squared error analysis (MSE) and mean absolute error analysis (MAE). Combined with time points, the specific growth stage at which the deviation occurs (e.g., seedling stage deviation, growth stage deviation) is located. The preset target growth curve is an optimal growth curve pre-set based on plant variety characteristics, cultivation goals (e.g., early maturity, high yield, high quality), and ideal growth environment. It clarifies the expected plant height and growth rate at different time points and serves as a "benchmark" for judging whether the actual growth status meets the target. For example, for lettuce, the target growth curve might be set as a "fixed" curve. The goal was set at 10cm in height 7 days and 20cm in height 14 days after planting. The deviation was quantified to determine the extent of the gap between actual growth and the expected target, the growth stage at which the gap occurred, and whether the deviation was widening or narrowing. For example, if the slope of the actual growth curve was lower than the target growth curve during the growth period and the deviation value continued to increase, it indicated that the plant growth rate was lagging behind expectations, possibly due to deficiencies in light quality, light duration, or environmental factors. If the deviation value was small and gradually decreased, it indicated that the current growth status was basically in line with expectations, and there was no need to significantly adjust the lighting quality control parameters. In this embodiment, two indicators, daily growth and plant height growth rate, are extracted. The reliability of the parameters is ensured by combining the continuity of data time series and varietal characteristics, providing a solid foundation for subsequent analysis. A fitting function adapted to plant growth patterns is used to construct a continuous growth curve based on initial plant height and growth parameters, enabling visualization and trend presentation of plant growth status, facilitating rapid identification of abnormal plant growth. Various quantitative deviation analysis methods are employed to locate deviation nodes and their extent, clarifying growth gaps and their causes, providing a basis for light quality regulation. Simultaneously, it supports the optimization of light quality regulation, ensuring plant growth aligns with expected goals, adapting to different plant varieties to enhance versatility, reducing cost losses from over-regulation, and improving plant growth quality and efficiency, thus contributing to the intelligent and automated cultivation of facility agriculture.

[0024] The above describes a method for regulating plant lighting quality in an embodiment of the present invention. The following describes a device for regulating plant lighting quality in an embodiment of the present invention. Please refer to [link / reference]. Figure 8 One embodiment of the plant lighting light quality control device of the present invention includes: Data acquisition module 1 is used to collect plant morphology image data and physiological index data; Data analysis module 2 is used to analyze plant morphological image data and physiological index data based on a pre-trained deep learning prediction model in order to obtain the plant's light quality requirements. Deviation analysis module 3 is used to collect plant variety growth measurement parameters and perform deviation analysis on the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results; Parameter generation module 4 is used to generate lighting quality control parameters based on deviation analysis results and plant light quality requirements; The lighting control module 5 is used to control the lighting of a preset lighting area according to the lighting quality control parameters; In this embodiment, by collecting plant morphological images and physiological index data, taking into account both external growth characteristics and internal physiological states, reliable data support is provided for light quality demand analysis. Relying on a pre-trained deep learning prediction model, data patterns can be mined to output plant light quality requirements that align with plant photosynthetic needs. By combining deviation analysis of plant variety growth measurement parameters and target growth curves, key control points are identified, and targeted lighting quality control parameters are optimized and generated. These parameters can flexibly adapt to different growth deviations, effectively suppressing excessive plant growth and promoting overall growth. Automated control of the lighting area through these parameters ensures real-time matching of the light environment with plant growth status and light quality requirements, improving photosynthetic efficiency, reducing energy waste, and helping plants grow healthily according to the target curve. This enhances cultivation efficiency and plant quality, providing reliable light quality control solutions for facility cultivation, plant factories, and other scenarios, and promoting the refined development of smart agriculture.

[0025] Figure 9 This is a schematic diagram of the structure of a plant lighting light quality regulation device 900 provided in an embodiment of the present invention. The plant lighting light quality regulation device 900 can vary considerably due to different configurations or performance. It may include one or more central processing units (CPUs) 910 (e.g., one or more processors) and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the plant lighting light quality regulation device 900. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute a series of instruction operations in the storage media 930 on the plant lighting light quality regulation device 900 to implement the steps of the plant lighting light quality regulation method provided in the above-described method embodiments.

[0026] A plant lighting light quality control device 900 may further include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, MacOSX, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 9The illustrated structure of a plant lighting light quality control device does not constitute a limitation on a plant lighting light quality control device. It may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0027] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of a method for regulating the light quality of plant lighting.

[0028] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0029] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0030] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for regulating the light quality of plant lighting, characterized in that, include: Collect plant morphological image data and physiological index data; The plant morphology image data and physiological index data are analyzed based on the pre-trained deep learning prediction model to obtain the plant light quality requirements. Plant growth measurement parameters were collected, and deviation analysis was performed between the plant growth measurement parameters and the preset target growth curve to obtain the deviation analysis results. Lighting quality control parameters are generated based on the deviation analysis results and plant light quality requirements. Lighting is controlled in a preset lighting area based on lighting quality control parameters.

2. The method for regulating plant lighting light quality as described in claim 1, characterized in that, The process of analyzing plant morphological image data and physiological index data based on a pre-trained deep learning prediction model to obtain plant light quality requirements includes: Collect plant type and chlorophyll fluorescence signals; The plant photosynthetic rate is obtained by matching the plant type from a preset photosynthetic rate table; The photosynthetic rate and chlorophyll fluorescence signal of the plant are analyzed according to the preset fast Fourier transform algorithm to obtain the photosynthetic oscillation period and the current photosynthetic phase. Plant morphological image data and physiological index data are analyzed based on deep learning prediction models, photosynthetic oscillation cycles, and current photosynthetic phases to obtain plant light quality requirements.

3. The method for regulating plant lighting light quality as described in claim 2, characterized in that, The analysis of plant morphological image data and physiological index data based on a deep learning prediction model, photosynthetic oscillation period, and current photosynthetic phase to obtain plant light quality requirements includes: The plant growth status is obtained by analyzing plant morphology image data and physiological index data based on a preset plant growth status recognition algorithm. Plant growth status is analyzed based on deep learning prediction models, photosynthetic oscillation cycles, and current photosynthetic phases to determine plant light quality requirements.

4. The method for regulating plant lighting light quality as described in claim 3, characterized in that, The analysis of plant growth status based on a deep learning prediction model, photosynthetic oscillation period, and current photosynthetic phase to obtain plant light quality requirements includes: Collect time-series data on ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution; Based on the preset time series feature analysis method, feature extraction is performed on the time series data of ambient temperature, ambient humidity, carbon dioxide concentration, and nutrient solution to obtain the time series features of environmental factors. Plant growth status is predicted based on deep learning prediction models and temporal characteristics of environmental factors to obtain basic light quality requirements; The basic light quality requirements are optimized based on the photosynthetic oscillation cycle and the current photosynthetic phase to obtain the plant's light quality requirements.

5. The method for regulating plant lighting light quality as described in claim 1, characterized in that, The generation of lighting quality regulation parameters based on deviation analysis results and plant light quality requirements includes: The plant variety growth measurement parameters are analyzed based on the preset prior constraints and preset basic parameters for each band to obtain the basic light quality ratio. The basic light quality ratio is corrected based on the deviation analysis results to obtain an optimized light quality ratio; Lighting quality control parameters are generated based on optimized light quality ratios and plant light quality requirements.

6. The method for regulating plant lighting light quality as described in claim 5, characterized in that, The generation of lighting quality control parameters based on optimized light quality ratios and plant light quality requirements includes: The photoelectric conversion calibration coefficient is determined based on the optimized light quality ratio; Lighting drive current data is collected, and the lighting drive current data is fitted and calculated according to a preset quadratic polynomial fitting method to obtain the actual photonic quantum flux. Lighting quality control parameters are generated based on photoelectric conversion calibration coefficients, actual photonic quantum flux, and plant light quality requirements.

7. The method for regulating plant lighting light quality as described in claim 1, characterized in that, The deviation analysis of the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results includes: Daily growth and plant height growth rate were extracted from plant variety growth measurement parameters. The actual growth curve is constructed based on the preset fitting function, preset initial plant height parameters at planting time, daily growth parameters, and plant height growth rate parameters. Deviation analysis was performed between the target growth curve and the actual growth curve to obtain the deviation analysis results.

8. A plant lighting light quality control device, characterized in that, include: The data acquisition module is used to collect plant morphological image data and physiological index data; The data analysis module is used to analyze plant morphological image data and physiological index data based on a pre-trained deep learning prediction model in order to obtain the plant's light quality requirements. The deviation analysis module is used to collect plant variety growth measurement parameters and perform deviation analysis on the plant variety growth measurement parameters and the preset target growth curve to obtain the deviation analysis results. The parameter generation module is used to generate lighting quality control parameters based on the deviation analysis results and the light quality requirements of plants. The lighting control module is used to control the lighting of preset lighting areas according to the lighting quality control parameters.

9. A plant lighting light quality control device, characterized in that, The plant lighting light quality control device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the plant lighting light quality control device to perform the steps of the plant lighting light quality control method as claimed in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the plant lighting light quality regulation method as described in any one of claims 1-7.

Images