Scutellaria baicalensis george planting digital intelligent supervision method and system based on internet of things

Abstract

This invention relates to the field of digital intelligent monitoring technology for Scutellaria baicalensis cultivation, and particularly to a digital intelligent monitoring method and system for Scutellaria baicalensis cultivation based on the Internet of Things (IoT). The method includes the following steps: collecting multi-source Scutellaria baicalensis sensor data through an array of IoT sensors, and analyzing the plant density and canopy temperature to generate plant density and canopy temperature data; performing multi-dimensional growth state confidence analysis based on the plant density and canopy temperature data to generate multi-dimensional growth state confidence data; performing environmental parameter index matching processing for the growth stages of Scutellaria baicalensis based on the multi-dimensional growth state confidence data to generate environmental parameter index matching data for the growth stages; and performing Scutellaria baicalensis cultivation parameter suitability analysis and intelligent control processing of the Scutellaria baicalensis distribution and cultivation environment based on the environmental parameter index matching data and the multi-dimensional growth state confidence data. This invention achieves intelligent control of the Scutellaria baicalensis cultivation environment.

Description

Technical Field

[0001] This invention relates to the field of digital intelligent monitoring technology for Scutellaria baicalensis cultivation, and in particular to a digital intelligent monitoring method and system for Scutellaria baicalensis cultivation based on the Internet of Things. Background Technology

[0002] Scutellaria baicalensis is a perennial herbaceous medicinal plant belonging to the genus Scutellaria in the Lamiaceae family. Its dried root is a traditional and valuable Chinese medicinal material, widely used in pharmaceuticals, health preservation, and other fields. Scutellaria baicalensis prefers a warm, dry, and sunny growing environment and is sensitive to changes in environmental factors such as soil moisture, light intensity, and climate temperature. The adaptation requirements for soil moisture and light intensity vary significantly at different growth stages. Internet of Things-based digital intelligent monitoring methods for Scutellaria baicalensis cultivation are widely used in medicinal herb cultivation, smart agriculture, and digital agriculture. Currently, environmental monitoring of Scutellaria baicalensis cultivation often relies on manual observation and recording or fragmented data collection using single sensors. This ignores the multidimensional correlation characteristics of core growth indicators such as plant density and canopy temperature, and fails to dynamically and intelligently regulate the planting environment based on the real-time growth status of Scutellaria baicalensis, thus affecting the normal growth of the plant. Summary of the Invention

[0003] Based on this, the present invention provides a digital intelligent monitoring method and system for Scutellaria baicalensis cultivation based on the Internet of Things, in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things includes the following steps: Step S1: Collect multi-source Scutellaria baicalensis sensor data through the array sensor of the Internet of Things, analyze the plant density and canopy temperature of Scutellaria baicalensis based on the multi-source Scutellaria baicalensis sensor data, and generate Scutellaria baicalensis plant density-canopy temperature data; perform multi-dimensional crown cluster type association classification of Scutellaria baicalensis based on the plant density-canopy temperature data, and generate multi-dimensional crown cluster type association data of Scutellaria baicalensis. Step S2: Perform confidence analysis on the multidimensional growth state of Scutellaria baicalensis based on the multidimensional crown cluster type association data, and generate confidence data on the multidimensional growth state of Scutellaria baicalensis. Step S3: Perform environmental parameter index matching processing on the growth stage of Scutellaria baicalensis based on the multidimensional growth state confidence data, and generate environmental parameter index matching data for the growth stage of Scutellaria baicalensis. Step S4: Based on the index matching data of environmental parameters in the growth stage of Scutellaria baicalensis and the confidence data of multidimensional growth status of Scutellaria baicalensis, conduct a fitness analysis of Scutellaria baicalensis planting parameters and generate fitness data of Scutellaria baicalensis planting parameters; Step S5: Based on the Scutellaria baicalensis planting parameter adaptation data, perform intelligent regulation and control processing of the Scutellaria baicalensis distribution and planting environment to generate intelligent regulation and control data of the Scutellaria baicalensis distribution and planting environment.

[0005] This specification provides an IoT-based digital intelligent monitoring system for Scutellaria baicalensis cultivation, used to execute the IoT-based digital intelligent monitoring method for Scutellaria baicalensis cultivation as described above. The IoT-based digital intelligent monitoring system for Scutellaria baicalensis cultivation includes: The Scutellaria baicalensis sensing and acquisition module is used to collect multi-source Scutellaria baicalensis sensing data through an array of IoT sensors. Based on the multi-source Scutellaria baicalensis sensing data, the module analyzes the plant density and canopy temperature of Scutellaria baicalensis to generate plant density-canopy temperature data. Based on the plant density-canopy temperature data, the module performs multi-dimensional canopy cluster type association classification of Scutellaria baicalensis to generate multi-dimensional canopy cluster type association data. The Scutellaria baicalensis multidimensional confidence analysis module is used to perform multidimensional confidence analysis of Scutellaria baicalensis growth status based on multidimensional crown cluster type association data, and generate multidimensional confidence data of Scutellaria baicalensis growth status. The Scutellaria baicalensis growth status prediction module is used to perform Scutellaria baicalensis growth stage environmental parameter index matching processing based on the multidimensional growth status confidence data of Scutellaria baicalensis, and generate Scutellaria baicalensis growth stage environmental parameter index matching data. The Scutellaria baicalensis environmental parameter matching module is used to perform Scutellaria baicalensis planting parameter fit analysis based on the Scutellaria baicalensis growth stage environmental parameter index matching data and Scutellaria baicalensis growth multidimensional state confidence data, and generate Scutellaria baicalensis planting parameter fit data. The Scutellaria baicalensis planting parameter control module is used to intelligently control the distribution and planting environment of Scutellaria baicalensis based on the adaptability data of Scutellaria baicalensis planting parameters, and generate intelligent control data of the distribution and planting environment of Scutellaria baicalensis.

[0006] The beneficial effects of this invention are: 1. The present invention proposes a digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things (IoT). Compared with existing technologies, the beneficial effects of this application lie in the fact that it collects multi-source Scutellaria baicalensis sensor data through an array of IoT sensors, enabling simultaneous capture of multi-dimensional raw data on plants and the environment within the Scutellaria baicalensis cultivation area. Based on the multi-source Scutellaria baicalensis sensor data, the plant density and canopy temperature are analyzed, achieving precise quantification of core growth indicators and overcoming the subjectivity issues associated with manual observation of plant density and canopy temperature. Based on the plant density-canopy temperature data, multi-dimensional canopy cluster type association classification of Scutellaria baicalensis is performed, enabling scientific classification based on multi-dimensional information such as the growth characteristics, density distribution, and temperature performance of the canopy clusters. This accurately identifies the canopy cluster types of Scutellaria baicalensis in different plots and with different growth states, achieving refined and differentiated identification of the growth status of Scutellaria baicalensis. Based on the multidimensional crown cluster type correlation data of Scutellaria baicalensis, a confidence analysis of the multidimensional growth status of Scutellaria baicalensis was conducted. Through cross-analysis and mutual verification of multidimensional data, the current growth status, growth potential, and degree of deviation from normal growth state of different crown cluster types of Scutellaria baicalensis were comprehensively analyzed, making the assessment results of Scutellaria baicalensis growth status more objective and comprehensive. It can accurately identify growth differences among different crown cluster types of Scutellaria baicalensis and growth fluctuations within the same crown cluster type, effectively capturing subtle changes in growth status that are easily overlooked during the cultivation of Scutellaria baicalensis, and achieving dynamic and refined monitoring of the growth status of Scutellaria baicalensis. Based on the confidence data of the multidimensional growth status of Scutellaria baicalensis, environmental parameter index matching processing of Scutellaria baicalensis growth stages was performed to achieve intelligent and precise matching of Scutellaria baicalensis growth stages with optimal growth environment parameters. Based on the index matching data of environmental parameters during the growth stages of Scutellaria baicalensis and the confidence data of multidimensional growth states, an analysis of the fit of Scutellaria baicalensis planting parameters was conducted. A comprehensive comparative analysis was performed between ideal environmental parameters and actual environmental parameters in the planting area. Combined with the weighted support of the multidimensional growth state confidence data, the deviation and fit between actual and ideal planting parameters were accurately calculated from multiple core dimensions such as soil moisture and light intensity. This achieves dynamic and real-time assessment of the planting environment. Based on the fit data of Scutellaria baicalensis planting parameters, intelligent regulation and control of the planting environment of Scutellaria baicalensis distribution were implemented, achieving intelligent, precise, and differentiated regulation of the planting environment.

[0007] 2. The IoT-based intelligent digital monitoring system for Scutellaria baicalensis cultivation proposed in this invention comprises a Scutellaria baicalensis sensor acquisition module, a Scutellaria baicalensis multidimensional confidence analysis module, a Scutellaria baicalensis growth status prediction module, a Scutellaria baicalensis environmental parameter matching module, and a Scutellaria baicalensis cultivation parameter control module. It can realize any IoT-based intelligent digital monitoring method for Scutellaria baicalensis cultivation described in this invention. The system utilizes the coordinated operations of computer programs running on each module to achieve this IoT-based intelligent monitoring method. The internal structure of the system collaborates with each other, which greatly reduces repetitive work and manpower input. It can quickly and effectively provide a more accurate and efficient dynamic intelligent control process for the real-time growth status and cultivation environment of Scutellaria baicalensis, thereby simplifying the operation process of the IoT-based intelligent digital monitoring system for Scutellaria baicalensis cultivation. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the steps of a digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things according to the present invention; Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3. Figure 3 for Figure 1 A detailed flowchart illustrating the implementation steps of step S4. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0009] The technical method of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0010] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0011] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0012] To achieve the above objectives, please refer to Figures 1 to 3 This invention provides a digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things. In the embodiments of this invention, please refer to... Figure 1 The diagram shown is a flowchart illustrating the steps of a digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things (IoT) according to the present invention. In this embodiment, the digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the IoT includes the following steps: Step S1: Collect multi-source Scutellaria baicalensis sensor data through the array sensor of the Internet of Things, analyze the plant density and canopy temperature of Scutellaria baicalensis based on the multi-source Scutellaria baicalensis sensor data, and generate Scutellaria baicalensis plant density-canopy temperature data; perform multi-dimensional crown cluster type association classification of Scutellaria baicalensis based on the plant density-canopy temperature data, and generate multi-dimensional crown cluster type association data of Scutellaria baicalensis. In this embodiment of the invention, within a standardized Scutellaria baicalensis planting base, an array of sensors, consisting of multispectral sensors and infrared thermal imaging sensors, is deployed at a grid spacing of 5 meters × 5 meters. The array sensors are connected to the planting base's IoT data acquisition terminal via an IoT communication module. The multispectral sensors collect plant reflectance spectral data for each grid plot within the Scutellaria baicalensis planting area, while the infrared thermal imaging sensors collect infrared thermal imaging data of the Scutellaria baicalensis canopy for the corresponding grid plot. These two types of data together constitute multi-source Scutellaria baicalensis sensing data. A multispectral inversion algorithm is used to analyze the plant reflectance spectral data from the multi-source Scutellaria baicalensis sensing data. Through a quantitative correlation model between spectral features and plant quantity, the number of Scutellaria baicalensis plants within each grid plot is calculated. The plant density value of Scutellaria baicalensis was obtained, and the temperature value was extracted from the infrared thermal imaging data to obtain the average canopy temperature value of Scutellaria baicalensis in each grid plot. The plant density value and the average canopy temperature value of each grid plot were integrated according to the plot location to generate Scutellaria baicalensis plant density-canopy temperature data. According to the Scutellaria baicalensis plant density classification standard (low density: <30 plants / m², medium density: 30-50 plants / m², high density: >50 plants / m²) and canopy temperature classification standard (low temperature layer: <25℃, medium temperature layer: 25-30℃, high temperature layer: >30℃), the Scutellaria baicalensis plant density-canopy temperature data were divided into two dimensions. Each grid plot was divided into 9 canopy cluster types according to the combination characteristics of density and temperature.

[0013] Step S2: Perform confidence analysis on the multidimensional growth state of Scutellaria baicalensis based on the multidimensional crown cluster type association data, and generate confidence data on the multidimensional growth state of Scutellaria baicalensis. In this embodiment of the invention, the crown cluster type classification results, corresponding plant density values, and canopy temperature values ​​of all grid plots in the data are extracted. First, the proportion of plots corresponding to each crown cluster type to the total number of plots is calculated. Then, the interval difference of plant density and the interval difference of canopy temperature in plots of the same type are calculated to determine the growth interval characteristics of each crown cluster type, generating Scutellaria baicalensis crown cluster growth interval difference data. The plant density interval and canopy temperature interval of each crown cluster type are compared with the density benchmark interval and canopy temperature benchmark interval of Scutellaria baicalensis standardized growth, and the deviation percentage between the actual interval and the benchmark interval is calculated. The deviation percentage is the growth stage deviation degree of the corresponding crown cluster type. The deviation degrees are matched and integrated according to the plot location to generate Scutellaria baicalensis crown cluster growth stage deviation degree data. Based on the growth stage deviation degree, the first confidence level is assigned to 95 when the deviation degree is ≤5%, 90 when the deviation degree is 5%-10%, and 80 when the deviation degree is 10%-20%. When the confidence level is greater than 20%, a first confidence level of 70 is assigned. Following this rule, a first confidence level value is calculated for each grid plot, generating first confidence level data for Scutellaria baicalensis growth. Based on this first confidence level data, the average first confidence level value for all plots is calculated. Then, the difference between the first confidence level value for each plot and the average value is calculated; this difference is the mean deviation data for Scutellaria baicalensis growth. Simultaneously, the Scutellaria baicalensis plant density-canopy temperature data is processed, and the canopy temperature value for each plot is calculated relative to the canopy temperatures of all plots. The ratio of the average values ​​is used to generate the multi-canopy temperature ratio data of Scutellaria baicalensis. After normalizing the multi-canopy temperature ratio data, it is weighted and calculated with the growth mean deviation data, with weights of 60% and 40% respectively. The calculation result is converted into a value of 0-100 according to the linear mapping rule. This value is the second confidence level data of Scutellaria baicalensis growth. Finally, the first confidence level data and the second confidence level data of Scutellaria baicalensis growth are averaged with a weight of 50% to obtain the growth multidimensional state confidence value of each grid plot.

[0014] Step S3: Perform environmental parameter index matching processing on the growth stage of Scutellaria baicalensis based on the multidimensional growth state confidence data, and generate environmental parameter index matching data for the growth stage of Scutellaria baicalensis. In this embodiment of the invention, based on the confidence level data of the multidimensional growth state of Scutellaria baicalensis, a confidence level value ≥90 is determined to be the rapid growth period of Scutellaria baicalensis, 80-90 is determined to be the stable growth period, 70-80 is determined to be the slow growth period, and <70 is determined to be the abnormal growth period. The growth stage is determined for each grid plot according to this standard. The growth stages of all plots are integrated with the plot location and confidence level value to generate multi-layer growth state stage data of Scutellaria baicalensis. According to the environmental parameter requirements for different growth stages of Scutellaria baicalensis, the rapid growth period corresponds to soil moisture of 60%-70% and light intensity of 8000-10000 lx, and the stable growth period corresponds to... The optimal soil moisture content is 50%-60% and light intensity is 6000-8000 lx. During the slow-growth period, the corresponding soil moisture content is 40%-50% and light intensity is 4000-6000 lx. During periods of abnormal growth, the corresponding soil moisture content is 50%-60% and light intensity is 5000-7000 lx. Environmental parameter index intervals are matched for each grid plot according to its growth stage, generating Scutellaria baicalensis canopy environmental parameter index data. The soil moisture and light intensity intervals in the Scutellaria baicalensis canopy environmental parameter index data are then precisely matched with the plot location. Furthermore, considering the soil type and topographic features of the Scutellaria baicalensis planting base, the environmental parameter index intervals for each plot are further refined. The data is refined by assigning unique ideal soil moisture and ideal light intensity values ​​to each plot, generating dynamic matching data for *Scutellaria baicalensis* soil moisture and light intensity. Feature extraction is performed on this data to extract the ideal soil moisture, ideal light intensity, and corresponding growth stage for each plot, generating environmental-matched growth parameter variation data for *Scutellaria baicalensis*. Simultaneously, the multi-dimensional growth confidence data of *Scutellaria baicalensis* is matrix-processed, constructing a matrix with plot location as rows and confidence values ​​as columns. This matrix is ​​then normalized and weighted to generate a confidence weight matrix for *Scutellaria baicalensis* growth. This confidence weight matrix data is then compared with the environmental data of *Scutellaria baicalensis*. Data fusion was performed on the growth parameter variation data, and the fused data was used as training samples. The data was divided into training and test sets in an 8:2 ratio. Based on the convolutional neural network framework, the training set was input into the network for iterative training. During the training process, the network accuracy was verified using the test set. Training was stopped when the network prediction error was ≤3%, thus completing the construction of the Scutellaria baicalensis multidimensional growth prediction network. The multi-level growth stage data of Scutellaria baicalensis were input into the constructed Scutellaria baicalensis multidimensional growth prediction network. The network outputs accurate ideal soil moisture value, ideal light intensity value and parameter adjustment gradient for each grid plot according to the plot growth stage, confidence value and environmental parameter requirements.

[0015] Step S4: Based on the index matching data of environmental parameters in the growth stage of Scutellaria baicalensis and the confidence data of multidimensional growth status of Scutellaria baicalensis, conduct a fitness analysis of Scutellaria baicalensis planting parameters and generate fitness data of Scutellaria baicalensis planting parameters; In this embodiment of the invention, the ideal soil moisture value and ideal light intensity value of each grid plot are extracted from the environmental parameter index matching data of Scutellaria baicalensis growth stage. These two types of values ​​are integrated according to the plot location to generate ideal planting environment parameters for Scutellaria baicalensis. Using soil moisture sensors and light intensity sensors deployed at the planting base, the actual soil moisture value and actual light intensity value of each grid plot are collected in real time. The sensor collection frequency is 5 minutes / time, continuously collecting 12 sets of actual data for 1 hour. Each set of collected soil moisture and light intensity data is filtered for valid values, eliminating abnormal data exceeding the reasonable value range. The arithmetic mean method is then used to calculate the average of the 12 sets of valid data as the final actual value. The actual value is then mapped one-to-one with the ideal planting environment parameters according to the plot location to generate the ideal planting environment parameters for Scutellaria baicalensis. Comparison data of actual planting environment parameters for Scutellaria baicalensis; Difference calculations were performed on the comparison data of actual planting environment parameters for Scutellaria baicalensis, specifically calculating the difference between the actual soil moisture value and the ideal soil moisture value, and the difference between the actual light intensity value and the ideal light intensity value for each plot. These differences were then converted into percentage deviations. The percentage deviations of soil moisture and light intensity were integrated according to plot location to generate deviation data for Scutellaria baicalensis planting environment parameters. Based on this deviation data, the percentage deviations of soil moisture and light intensity for each plot were directly extracted. These two types of values ​​were integrated according to plot location to generate soil moisture-light intensity deviation amplitude data. Weighted coefficients were calculated for the confidence data of the multidimensional growth state of Scutellaria baicalensis. A linear positive correlation was found between the confidence value and the weighted coefficient; the higher the confidence value, the larger the weighted coefficient. The calculation formula is as follows: ,in These are weighting coefficients. To generate the confidence score, a weighted coefficient is calculated for each plot, producing confidence-weighted data for the ideal planting parameters of Scutellaria baicalensis. The soil moisture-light intensity deviation data is then compared with the confidence-weighted data for the ideal planting parameters of Scutellaria baicalensis. First, the percentage deviations of soil moisture and light intensity are multiplied by their respective weighted coefficients. Then, the average of the two products is used to obtain the baseline fit value for each plot. The formula is as follows: ,in, This is the base value for fit. The percentage deviation of soil moisture. These are weighting coefficients. To calculate the percentage deviation in light intensity, all baseline fitness values ​​were integrated based on plot location to generate baseline fitness data for Scutellaria baicalensis planting parameters. This baseline fitness data was then converted to reflect the optimal fitness level. ,in The fit score is a numerical value ranging from 0 to 100. A higher value indicates a better fit for the planting parameters. All fit scores are integrated according to the location of the plot, and the corresponding deviations in soil moisture and light intensity are also marked.

[0016] Step S5: Based on the Scutellaria baicalensis planting parameter adaptation data, perform intelligent regulation and control processing of the Scutellaria baicalensis distribution and planting environment to generate intelligent regulation and control data of the Scutellaria baicalensis distribution and planting environment.

[0017] In this embodiment of the invention, the fitness value of each grid plot within a continuous 24-hour period is extracted, and the difference between two adjacent fitness values ​​is calculated. This difference represents the environmental change amplitude for a single time period. The average of all environmental change amplitudes within the 24-hour period is then calculated as the environmental change amplitude value for that plot. All amplitude values ​​are integrated according to the plot location, and the trend of the amplitude values ​​(increasing, decreasing, or stable) is marked to generate Scutellaria baicalensis growth environment change amplitude data. This data is then compared with the Scutellaria baicalensis growth environment change amplitude data. The long-term multidimensional state confidence data were matched, and the ratio of the growth environment change amplitude value to the growth multidimensional state confidence value for each plot was calculated. A ratio ≤0.1 was considered highly adapted, 0.1-0.2 was considered moderately adapted, 0.2-0.3 was considered poorly adapted, and >0.3 was considered maladapted. Based on this standard, a fitness level was determined for each plot. The fitness level was then integrated with the plot location, environmental change amplitude value, and confidence value to generate Scutellaria baicalensis growth-environment change fitness matching data. Based on the fitness levels in the Scutellaria baicalensis growth-environmental change adaptability matching data, targeted adjustment rules for control parameters were formulated. Highly adapted plots maintained their existing environmental parameters without adjustment; moderately adapted plots saw a 5% fine-tuning of soil moisture and light intensity towards ideal values; low-adapted plots saw a 10% adjustment; and unadapted plots had their soil moisture and light intensity directly adjusted to ideal values. Simultaneously, combined with the plot's growth stage and fitness level, the adjusted values ​​were recalibrated to determine precise soil moisture control values, light intensity control values, and control durations for each plot, generating precise control parameter data for each Scutellaria baicalensis plot area. This precise control parameter data was transmitted via the Internet of Things to the intelligent control equipment terminal at the planting base. The terminal sent the control parameters to the corresponding irrigation and shading equipment according to the plot location. The irrigation equipment automatically adjusted the water output and irrigation duration based on the soil moisture control value, and the shading equipment automatically adjusted the opening and closing of the shading net based on the light intensity control value. All equipment operated synchronously according to the control parameters.

[0018] Furthermore, step S1 includes the following steps: Step S11: Collect multi-source Scutellaria baicalensis sensor data through the array sensor of the Internet of Things, perform multi-source Scutellaria baicalensis sensor filtering on the multi-source Scutellaria baicalensis sensor data, and generate multi-source Scutellaria baicalensis sensor filtered data. In this embodiment of the invention, within a large-scale Scutellaria baicalensis planting area, an array of sensors consisting of multispectral sensors and infrared thermal imaging sensors is deployed at a fixed grid spacing of 5 meters × 5 meters. All sensors are equipped with an Internet of Things (IoT) wireless transmission module. The sensor acquisition frequency is set to once every 3 minutes. The multispectral sensors collect reflectance spectral data of Scutellaria baicalensis plants in the 450nm, 550nm, 650nm, and 760nm bands from each grid plot within the planting area. The infrared thermal imaging sensors collect infrared thermal radiation data of the canopy of Scutellaria baicalensis plants in the corresponding grid plot. The two types of sensor data are integrated one-to-one according to the acquisition time and plot location to form multi-source Scutellaria baicalensis sensor data. A median filtering algorithm is used. Multi-source Scutellaria baicalensis sensor data were filtered using a 5×5 matrix window. Spectral and infrared thermal radiation values ​​from the multi-source Scutellaria baicalensis sensor data were iterated through the matrix window, and the median of all values ​​within each window was used to replace the original value at the center of the window, thus removing random noise. Linear interpolation was then used to fill in missing values ​​in the filtered data. The processed data was then reorganized and sorted according to plot location and acquisition band to generate multi-source Scutellaria baicalensis sensor filtered data. This data includes multi-band spectral and canopy infrared thermal radiation filtered values ​​for each grid plot, and all data are precisely matched according to a fixed time series and plot coordinates.

[0019] Step S12: Based on the preset Scutellaria baicalensis crown cluster features, perform Scutellaria baicalensis multi-source sensor filter data to identify Scutellaria baicalensis multi-source crown cluster features and generate Scutellaria baicalensis multi-source crown cluster feature data; In this embodiment of the invention, a pre-defined characteristic index system for Scutellaria baicalensis crown clusters is established. This system includes four core indicators: crown cluster projected area, crown cluster height, crown cluster leaf reflectance characteristics, and crown cluster temperature distribution characteristics. The crown cluster projected area is defined as the projected outline area of ​​a single Scutellaria baicalensis crown on the ground; the crown cluster height is defined as the vertical distance from the top of the crown to the ground; the crown cluster leaf reflectance characteristics are defined as the ratio of the reflectance spectra in the 650nm and 760nm bands; and the crown cluster temperature distribution characteristics are defined as the mean distribution of the crown's infrared thermal radiation data. Using this pre-defined Scutellaria baicalensis crown cluster characteristic index system as the identification basis, [the following is a description of the system and its components]. Feature extraction and identification were performed on the multi-source sensor filtering data of Scutellaria baicalensis. Through grayscale processing and contour extraction of multi-band spectral filtering values, the crown projection area and crown height of each Scutellaria baicalensis plant in each grid plot were calculated. The crown leaf reflectance characteristics were obtained by calculating the ratio of the 650nm and 760nm band filtering values. The crown temperature distribution characteristics were obtained by averaging the infrared thermal radiation filtering values. The four types of feature indicators obtained by extraction and identification were integrated according to the individual Scutellaria baicalensis plants, and then classified and summarized according to the grid plots. The specific values ​​of the crown feature indicators of all individual Scutellaria baicalensis plants were marked for each grid plot.

[0020] Step S13: Analyze the plant density and canopy temperature of Scutellaria baicalensis based on the multi-source crown cluster characteristic data, and generate plant density-canopy temperature data of Scutellaria baicalensis. In this embodiment of the invention, using multi-source crown cluster characteristic data of Scutellaria baicalensis as the core analytical basis, the plant density and canopy temperature of Scutellaria baicalensis in each grid plot are quantitatively analyzed. The plant density analysis adopts a plant-by-plant counting method combined with area conversion. First, the crown cluster characteristic indicators of individual Scutellaria baicalensis plants in each grid plot in the multi-source crown cluster characteristic data of Scutellaria baicalensis are marked and counted one by one to obtain the actual number of individual Scutellaria baicalensis plants in each grid plot. Then, based on the fixed area of ​​4m × 4m of the grid plot, the number of Scutellaria baicalensis plants per square meter is converted, which is the plant density value of the corresponding plot, in units of plants / square meter. The canopy temperature analysis employs a weighted average calculation method. The projected area of ​​the canopy cluster of each individual Scutellaria baicalensis plant in the multi-source canopy cluster characteristic data is used as the weighting coefficient. The canopy temperature distribution characteristic values ​​of all individual Scutellaria baicalensis plants within each grid plot are multiplied by the corresponding weighting coefficient. All products are then summed, and finally divided by the sum of the projected areas of the canopy clusters within that plot to obtain the average canopy temperature value of the corresponding plot, in °C. The plot coordinates, plant density values, and average canopy temperature values ​​of each grid plot are integrated one-to-one and sorted according to the horizontal and vertical order of the plot coordinates.

[0021] Step S14: Based on the plant density-canopy temperature data and the multi-source crown cluster feature data of Scutellaria baicalensis, perform multi-dimensional morphological calibration of Scutellaria baicalensis crown clusters to generate multi-dimensional morphological calibration data of Scutellaria baicalensis crown clusters; In this embodiment of the invention, based on the plant density value and average canopy temperature value in the Scutellaria baicalensis plant density-canopy temperature data, and combined with the canopy projection area, canopy height, canopy leaf reflectance characteristics, and canopy temperature distribution characteristics in the multi-source canopy feature data of Scutellaria baicalensis, multi-dimensional morphological calibration of Scutellaria baicalensis canopy is carried out. First, the multi-dimensional morphological calibration dimensions are set as density correlation dimension, temperature correlation dimension, and morphological feature dimension. The density correlation dimension is based on the plant density value and is divided into three calibration levels: <30 plants / m², 30-50 plants / m², and >50 plants / m². The temperature correlation dimension is based on the average canopy temperature value and is divided into three calibration levels: <25℃, 25-30℃, and >30℃. The morphological feature dimension is based on the combined calibration of canopy projection area, canopy height, and canopy leaf reflectance characteristics. The following classifications were used to determine the classification of plots: Level 1: Canopy cluster projection area < 0.05㎡, Canopy cluster height < 20cm, Leaf reflectance ratio < 0.8; Level 2: Canopy cluster projection area 0.05-0.1㎡, Canopy cluster height 20-30cm, Leaf reflectance ratio 0.8-1.2; Level 3: Canopy cluster projection area > 0.1㎡, Canopy cluster height > 30cm, Leaf reflectance ratio > 1.2. For each grid plot, corresponding values ​​were extracted from the Scutellaria baicalensis plant density-canopy temperature data and the Scutellaria baicalensis multi-source canopy cluster characteristic data. The three dimensions of the classification were then calibrated according to the above standards. The three classification levels of each plot were then coded according to the density level + temperature level + morphology level. The specific values ​​corresponding to each classification level were also labeled. The plot coordinates, multi-dimensional classification levels, coding results, and specific values ​​were then integrated.

[0022] Step S15: Based on the multidimensional morphological calibration data of Scutellaria baicalensis crown clusters, perform multidimensional crown cluster type association classification of Scutellaria baicalensis and generate multidimensional crown cluster type association data of Scutellaria baicalensis.

[0023] In this embodiment of the invention, based on the multidimensional morphological calibration data of Scutellaria baicalensis crown clusters, a multidimensional crown cluster type association classification of Scutellaria baicalensis is carried out. First, a multidimensional crown cluster type classification system is established. This system uses the calibration levels of density association dimension, temperature association dimension, and morphological feature dimension as core classification factors. The calibration levels of the three classification factors are combined in pairs and three-dimensionally correlated to form 27 basic crown cluster types. Each basic crown cluster type has a unique corresponding level code. For example, density level 1 + temperature level 1 + morphology level 1 corresponds to crown cluster type code 111, and density level 1 + temperature level 1 + morphology level 2 corresponds to crown cluster type code 112. Similarly, for each grid plot in the Scutellaria baicalensis crown cluster multidimensional morphological calibration data, the coding results of its multidimensional calibration level are extracted. The plots are then classified into the corresponding basic crown cluster type categories according to the coding results. The plots of each crown cluster type are then summarized, and the number of plots, plot coordinates, density values, canopy temperature values, and specific morphological feature values ​​of each plot are labeled. At the same time, the average values ​​of plots of the same crown cluster type are calculated to obtain the core value average of each crown cluster type. The coding, category features, included plot information, and core value average of all crown cluster types are integrated and sorted according to the coding order.

[0024] Furthermore, step S2 includes the following steps: Step S21: Identify the growth interval difference of Scutellaria baicalensis crown clusters based on the multidimensional crown cluster type association data, and generate Scutellaria baicalensis crown cluster growth interval difference data; In this embodiment of the invention, the codes for all crown cluster types, the plant density values ​​of the corresponding plots, the canopy temperature values, and the core morphological feature values ​​are first extracted from the data. For each crown cluster type, the plant density values, canopy temperature values, canopy projection area, canopy height, and leaf reflectance ratio of all plots included in it are calculated within numerical intervals. The extreme value method is used to determine the numerical intervals of each indicator, that is, the maximum value among all values ​​of a certain indicator under the same crown cluster type is taken as the upper limit of the interval, and the minimum value is taken as the lower limit of the interval, thus clarifying the specific numerical interval range of each growth indicator for each crown cluster type. Then, the numerical intervals of the same crown cluster type are calculated. The interval difference of each indicator within the type is calculated, which is the upper bound minus the lower bound of the indicator value interval. At the same time, the overlap of the numerical intervals of the same indicator between different crown cluster types is calculated, which is the percentage of the intersection range of the numerical intervals of the same indicator of different crown cluster types divided by the union range. Then, the crown cluster types are classified according to their codes, and the numerical intervals, interval differences, and interval overlap of the same indicator between different types of each crown cluster type are accurately associated with the corresponding plot coordinates. Finally, the identification results of all crown cluster types are sorted in the order of coding, and the indicator interval characteristics and inter-type difference characteristics of each crown cluster type are labeled.

[0025] Step S22: Analyze the deviation of the growth stage of Scutellaria baicalensis crown clusters based on the difference data of the growth interval of Scutellaria baicalensis crown clusters, and generate the deviation data of the growth stage of Scutellaria baicalensis crown clusters; In this embodiment of the invention, a standardized growth range benchmark system for Scutellaria baicalensis is first established. This system, based on the physiological characteristics of Scutellaria baicalensis at different growth stages, clarifies the standard numerical ranges for various growth indicators during the rapid growth phase, stable growth phase, and slow growth phase. Specifically, during the rapid growth phase, the standard ranges are: plant density 40-50 plants / m², canopy temperature 26-30℃, canopy projection area 0.08-0.12m², canopy height 25-35cm, and leaf reflectance ratio 1.0-1.3. During the stable growth phase, the standard ranges are: plant density 30-40 plants / m², canopy temperature 24-26℃, and canopy projection area 0.05-0.08m². The standard ranges for crown height are 20-25cm, leaf reflectance ratio is 0.8-1.0, plant density during the slow-growth period is 20-30 plants / m², canopy temperature is 22-24℃, crown projection area is 0.03-0.05m², crown height is 15-20cm, and leaf reflectance ratio is 0.6-0.8. Then, the actual value ranges of various growth indicators for each crown type are extracted from the crown growth range difference data of *Scutellaria baicalensis*. These actual value ranges are compared with the standard value ranges for the corresponding growth cycle in the standardized growth range benchmark system. For each indicator, the deviation between the actual range and the standard range is calculated using the following formula: , This represents the overall deviation of the crown growth stage in a single plot. The total number of core growth indicators is 5, which is taken here. For the first The actual median of the growth index range. For the first The growth index corresponds to the median of the standard interval for the growth stage. The deviation of each individual indicator is summed and the average value is taken as the comprehensive deviation of the land parcel. After the calculation is completed, the land parcel coordinates, the code of the crown cluster type, the median of the actual interval of each indicator, the median of the standard interval, and the comprehensive deviation value are integrated according to the corresponding relationship.

[0026] Step S23: Based on the deviation data of Scutellaria baicalensis crown growth stage and the plant density-canopy temperature data, perform confidence analysis on the multidimensional growth state of Scutellaria baicalensis to generate confidence data on the multidimensional growth state of Scutellaria baicalensis.

[0027] In this embodiment of the invention, the comprehensive deviation of all plots in the deviation data of Scutellaria baicalensis crown growth stage is first extracted. A first confidence level is assigned according to the comprehensive deviation: 95 for a comprehensive deviation ≤ 5%, 90 for 5%-10%, 85 for 10%-15%, 80 for 15%-20%, 70 for 20%-30%, and 60 for > 30%. The first confidence level value is calculated for each plot according to this standard, generating the first confidence level value for the Scutellaria baicalensis crown growth stage. First, a baseline of confidence level data is generated. Then, the first confidence level values ​​for all plots in this baseline data are extracted, and their overall average is calculated. Subsequently, the difference between the first confidence level value for each plot and the overall average is calculated; this difference is the Scutellaria baicalensis growth mean deviation value. After calculating the mean deviation values ​​for all plots, Scutellaria baicalensis growth mean deviation data is generated. Simultaneously, the canopy temperature values ​​for all plots in the Scutellaria baicalensis plant density-canopy temperature data are extracted, and the overall average canopy temperature for all plots is calculated. Then, the average canopy temperature for each plot is calculated. The ratio of the canopy temperature value of each plot to the overall average is called the Scutellaria baicalensis canopy temperature ratio. After calculating the ratio for all plots, Scutellaria baicalensis canopy temperature ratio data is generated. This data is then normalized to map the ratio values ​​to the range of 0-100. The normalized canopy temperature ratio data is then weighted with the deviation data of the Scutellaria baicalensis growth mean at a weight of 7:3. The result is used as the base value for the second confidence level. Finally, the base value is adjusted according to the linear mapping rule. The numerical values ​​are converted into a second confidence level value of 0-100 to generate second confidence level data for Scutellaria baicalensis growth. Finally, the first confidence level data and the second confidence level data for Scutellaria baicalensis growth are weighted and averaged at a ratio of 6:4 to obtain the confidence level value of the multidimensional growth status of each plot. This value ranges from 0 to 100. The higher the value, the more reliable the judgment result of the growth status of Scutellaria baicalensis. The plot coordinates, the first confidence level value, the second confidence level value, and the multidimensional status confidence level value are accurately correlated and integrated.

[0028] Furthermore, step S23 includes the following steps: Step S231: Perform a first confidence analysis on the growth stage deviation data of Scutellaria baicalensis crown clusters to generate first confidence data on the growth of Scutellaria baicalensis. In this embodiment of the invention, the plot coordinates, deviation range of individual growth indicators, and comprehensive deviation value of all grid plots in the data are first extracted. The comprehensive deviation is the arithmetic mean of the deviation ranges of five indicators: plant density, canopy temperature, canopy projection area, canopy height, and leaf reflectance ratio. A quantitative assignment rule for the first confidence level of Scutellaria baicalensis growth is pre-set. This rule uses the comprehensive deviation as the core criterion and assigns gradient values ​​according to numerical ranges: 95 for a comprehensive deviation ≤ 5%, 90 for a comprehensive deviation of 5%-10% (excluding 5% and including 10%), 85 for a comprehensive deviation of 10%-15% (excluding 10% and including 15%), and 85 for a comprehensive deviation of 15%-20% (excluding 10% and including 15%). The following values ​​are assigned: 80 for deviations between 15% and 20%; 70 for deviations between 20% and 30%; and 60 for deviations greater than 30%. This assignment rule covers all deviation ranges without overlap or omission. Following this rule, each plot in the deviation data for the Scutellaria baicalensis crown growth stage is matched with its corresponding first confidence level value. The matching process strictly adheres to the boundary definition standards of the value ranges. After assigning values ​​to all plots, the plot coordinates are integrated with their corresponding first confidence levels. The integrated data is then arranged according to the horizontal and vertical sorting rules of the plot coordinates. Simultaneously, the corresponding deviation value and its range are labeled for each plot.

[0029] Step S232: Perform mean deviation analysis on Scutellaria baicalensis growth based on the first confidence level data to generate mean deviation data for Scutellaria baicalensis growth; In this embodiment of the invention, the first confidence level values ​​and corresponding coordinates of all plots in the data are extracted. The arithmetic mean method is used to calculate the overall average of the first confidence level values ​​of all plots. The calculation process includes the values ​​of all plots without any removal or filtering, and the average result is retained to two decimal places. After the overall average is calculated, the mean deviation is calculated for each plot. A positive mean deviation indicates that the first confidence level value of the plot is higher than the overall average level, a negative mean deviation indicates that the first confidence level value of the plot is lower than the overall average level, and a mean deviation of 0 indicates that the first confidence level value of the plot is consistent with the overall average level. After the mean deviation of all plots is calculated according to the above formula, the plot coordinates, the first confidence level value of a single plot, the overall average of all plots, and the mean deviation value of a single plot are precisely correlated in four directions. Then, all data are arranged according to the horizontal and vertical sorting rules of the plot coordinates, and the positive or negative attribute of the mean deviation is marked for each plot.

[0030] Step S233: Calculate the multi-canopy temperature ratio of Scutellaria baicalensis based on the plant density-canopy temperature data, and generate multi-canopy temperature ratio data of Scutellaria baicalensis. In this embodiment of the invention, the average canopy temperature value and corresponding coordinates of all plots in the data are first extracted. The arithmetic mean method is then used to calculate the overall average canopy temperature value of all plots. The calculation includes the canopy temperature values ​​of all plots, and the result is retained to one decimal place. This average value serves as the overall baseline value for canopy temperature within the Scutellaria baicalensis planting area. After calculating the overall average value, a multi-canopy temperature ratio is calculated for each plot. This ratio reflects the relative relationship between the canopy temperature of a single plot and the overall canopy temperature of the region. A ratio greater than 1 indicates that the canopy temperature of the plot is higher than the overall regional level; a ratio less than 1 indicates that the canopy temperature of the plot is lower than the overall regional level; and a ratio of 1 indicates that the canopy temperature of the plot is consistent with the overall regional level. After calculating the canopy temperature ratios of all plots according to the above formula, the plot coordinates, the average canopy temperature of a single plot, the overall average canopy temperature of all plots, and the canopy temperature ratio of a single plot are precisely correlated in four directions. Then, all data are arranged according to the horizontal and vertical sorting rules of the plot coordinates, and the relationship between the temperature ratio and 1 is marked for each plot.

[0031] Step S234: Based on the multi-canopy temperature ratio data of Scutellaria baicalensis and the mean deviation data of Scutellaria baicalensis growth, perform second confidence analysis on the growth of Scutellaria baicalensis to generate second confidence data on the growth of Scutellaria baicalensis; In this embodiment of the invention, the canopy temperature ratio of all plots in the Scutellaria baicalensis multi-canopy temperature ratio data is first extracted, and the ratio is then normalized to map the ratio value to a range of 60-100. The normalization calculation formula is as follows: ,in This is the normalized temperature value. This represents the canopy temperature ratio for a single plot. This represents the minimum canopy temperature ratio across all plots. This represents the maximum canopy temperature ratio across all plots. Next, the average growth deviation of each plot in the *Scutellaria baicalensis* growth mean deviation data is extracted. This value is then linearly corrected and its range is defined using the following formula: If The value is 100. The value is then taken as 60, and the corrected result is rounded down to the nearest integer. Corrected mean deviation This represents the mean deviation value for growth of a single plot. After the above processing, the normalized temperature value and the corrected mean deviation value are weighted at a fixed weight of 7:3 to obtain the baseline value for the second confidence level. The weighting calculation formula is as follows: Calculate and retain the integers, where This serves as the baseline value for the second confidence level; subsequently, an interval validation is performed on the baseline value for the second confidence level. Then the final second confidence level value is taken as 100. Therefore, the final second confidence level value is taken as 60; in other cases, it is directly taken as... As the final second confidence level value; finally, the coordinates of each plot, the corresponding normalized temperature value, the corrected mean deviation value, the second confidence level base value, and the final second confidence level value are precisely integrated according to a one-to-one correspondence to generate the second confidence level data for Scutellaria baicalensis growth.

[0032] Step S235: Based on the first confidence level data and the second confidence level data of Scutellaria baicalensis growth, perform multidimensional state confidence analysis of Scutellaria baicalensis growth to generate multidimensional state confidence data of Scutellaria baicalensis growth.

[0033] In this embodiment of the invention, a multidimensional state confidence analysis of Scutellaria baicalensis growth is conducted based on first and second confidence data. First, the coordinates, first confidence value, and second confidence value of all plots in the two datasets are extracted to ensure complete matching of plot coordinates across the three datasets, with no missing or mismatched values. A pre-defined weighted calculation rule for the multidimensional state confidence is established, with the first confidence value assigned a weight of 60% and the second confidence value assigned a weight of 40%. This weighting is based on the core judgment attribute of growth deviation for the first confidence value and the auxiliary judgment attribute of temperature characteristics and mean deviation for the second confidence value, providing a clear logical basis. A weighted average is then calculated for each plot according to this rule. The formula for calculating the multidimensional state confidence is as follows: ,in This represents the confidence score for the multidimensional growth state. This is the first confidence level value. The second confidence level value is 60-100. A higher value indicates higher accuracy and reliability in determining the growth status of Scutellaria baicalensis in that plot. After calculating the multidimensional confidence level values ​​for all plots, the plot coordinates, the first confidence level value, the second confidence level value, and the multidimensional confidence level values ​​are precisely correlated in four directions. Then, all data are arranged according to the horizontal and vertical sorting rules of the plot coordinates. At the same time, the interval to which the multidimensional confidence level value belongs is marked for each plot. The division criteria are: 90-100 is the high confidence interval, 80-89 is the medium-high confidence interval, 70-79 is the medium confidence interval, and 60-69 is the low confidence interval.

[0034] Furthermore, as an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart of step S3 is shown below. In this embodiment, step S3 includes the following steps: Step S31: Based on the confidence data of the multidimensional growth state of Scutellaria baicalensis, determine the multi-dimensional growth state stage of Scutellaria baicalensis and generate multi-dimensional growth state stage data of Scutellaria baicalensis. In this embodiment of the invention, the plot coordinates and multidimensional growth state confidence values ​​of all grid plots in the data are first extracted. The value range is 60-100. A quantitative judgment standard for the multidimensional growth state stages of Scutellaria baicalensis is pre-set. This standard is based on the multidimensional confidence value as the core dividing basis. According to the value range, different growth stages of Scutellaria baicalensis are corresponding to different growth stages. A confidence value of 90-100 corresponds to the rapid growth period of Scutellaria baicalensis. During this stage, the physiological metabolism of Scutellaria baicalensis plants is active, and the growth rate of plant height and crown width reaches its peak. A confidence value of 80-89 corresponds to the stable growth period of Scutellaria baicalensis. During this stage, the growth rate of Scutellaria baicalensis plants tends to be stable, and various physiological indicators maintain a stable level. A confidence value of 70-79 corresponds to the slow growth period of Scutellaria baicalensis. During this stage, the growth rate of Scutellaria baicalensis plants slows down, and the intensity of physiological metabolism decreases. A confidence value of 60-69 corresponds to the abnormal growth period of Scutellaria baicalensis. During this stage, the growth indicators of Scutellaria baicalensis plants deviate from the standard range, and the planting environment needs to be adjusted accordingly. According to the judgment criteria, each plot in the multidimensional growth state confidence data of Scutellaria baicalensis was matched with the corresponding growth state stage one by one. During the matching process, the numerical interval boundary definition rules were strictly followed, and there were no cross-interval matching cases. After the growth stage judgment of all plots was completed, the plot coordinates, multidimensional confidence values, and matched growth state stages were accurately correlated. The integrated data was arranged according to the horizontal and vertical sorting rules of the plot coordinates, and the core growth characteristics of the growth stage to which each plot belonged were marked.

[0035] Step S32: Based on the multi-layer growth stage data of Scutellaria baicalensis, divide the Scutellaria baicalensis canopy environmental parameter index and generate Scutellaria baicalensis canopy environmental parameter index data; In this embodiment of the invention, based on the multi-stage growth data of Scutellaria baicalensis, the coordinates of all plots and their respective growth stages are first extracted from the data. Combining this with the physiological and environmental requirements of Scutellaria baicalensis at different growth stages, a pre-defined indexing system for Scutellaria baicalensis canopy environmental parameters is established. This system sets a unique soil moisture index range and light intensity index range for each growth stage, and all ranges are quantitative numerical ranges without ambiguity. Specifically, the soil moisture index range for the rapid growth stage is set to 60%-70%, and the light intensity index range is set to... The soil moisture index range is set at 8000-10000 lx, the light intensity index range is set at 50%-60% during the stable growth period, the soil moisture index range is set at 6000-8000 lx during the slow growth period, the soil moisture index range is set at 40%-50% during the slow growth period, the light intensity index range is set at 4000-6000 lx during the slow growth period, and the soil moisture index range is set at 50%-60% during the abnormal growth period, the light intensity index range is set at 5000-7000 lx during the abnormal growth period. This classification system fully matches the core water and light requirements of Scutellaria baicalensis plants at each growth stage. According to this system, for each plot in the multi-layer growth stage data of Scutellaria baicalensis, the corresponding soil moisture index interval and light intensity index interval are matched one by one according to its growth stage. During the matching process, the unique correspondence between the growth stage and the index interval is strictly followed. After the parameter index matching of all plots is completed, the plot coordinates, the growth stage, the matched soil moisture index interval, and the light intensity index interval are accurately correlated in four directions. The integrated data is arranged according to the horizontal and vertical sorting rules of the plot coordinates. At the same time, the environmental parameter requirements of the growth stage of each plot are marked.

[0036] Step S33: Perform dynamic matching processing of soil moisture and light intensity of Scutellaria baicalensis based on the Scutellaria baicalensis canopy environmental parameter index data to generate dynamic matching data of soil moisture and light intensity of Scutellaria baicalensis. In this embodiment of the invention, the coordinates, soil moisture index range, and light intensity index range of all plots in the data are extracted. Combined with the actual plot attributes of the Scutellaria baicalensis planting area, dynamic matching processing of soil moisture and light intensity is performed on each plot. The actual plot attributes include soil type, plot slope, and plot orientation. Soil types are categorized as sandy soil, loamy soil, and clay soil. Sandy soil has low water retention, so the median value of the soil moisture index range needs to be increased by 5%. Clay soil has high water retention, so the median value of the soil moisture index range needs to be decreased by 5%. Loamy soil has moderate water retention. The soil moisture index range remains unchanged; the plot slope is divided into 0-5°, 5-15°, and above 15°. The greater the slope, the faster the water evaporates. The moisture range remains unchanged for plots with a slope of 0-5°. The median moisture range for plots with a slope of 5-15° increases by 3%, and the median moisture range for plots above 15° increases by 6%. The plot orientation is divided into south, east, west, and north. South-facing plots receive the most sunlight, so the sunlight range remains unchanged. East- and west-facing plots receive the next most sunlight, with the median sunlight range increasing by 1000 lx. North-facing plots receive the least sunlight, with the median sunlight range increasing by 2000 lx. For each plot, its actual attributes, such as soil type, slope, and orientation, are extracted first. The soil moisture index range and light intensity index range are then fine-tuned according to the above rules. After fine-tuning, a unique soil moisture matching value and light intensity matching value are determined for each plot. The matching value is the arithmetic mean of the fine-tuned index range, retaining the integer part and one decimal place for the percentage. After completing the dynamic matching calculation for all plots, the plot coordinates, the original soil moisture index range, the original light intensity index range, the actual plot attributes, the fine-tuned soil moisture matching value, and the light intensity matching value are precisely correlated in six directions. The integrated data is then arranged according to the horizontal and vertical sorting rules of the plot coordinates.

[0037] Step S34: Construct a multidimensional growth prediction network for Scutellaria baicalensis based on dynamic matching data of soil moisture and light intensity and confidence data of multidimensional growth status of Scutellaria baicalensis; In this embodiment of the invention, the two datasets are first preprocessed by data fusion. Soil moisture matching values ​​and light intensity matching values ​​for all plots in the *Scutellaria baicalensis* soil moisture-light dynamic matching data are extracted. The growth multidimensional state confidence values ​​and growth stages of all plots in the *Scutellaria baicalensis* growth multidimensional state confidence data are also extracted. Plot coordinates are used as the primary key for association. The above data are then fused to form the basic dataset for network construction. Each sample in the basic dataset contains four feature indicators: soil moisture matching value, light intensity matching value, multidimensional confidence value, and growth stage. The basic dataset is then divided into training and testing sets in an 8:2 ratio, ensuring that the proportion of samples at each growth stage is consistent between the training and testing sets, without sample skew. A convolutional neural network (CNN) was used as the basic network framework, with an input layer, hidden layers, and an output layer. The input layer had 4 nodes, corresponding to four feature indicators. The hidden layer consisted of three layers: the first layer had 64 nodes, the second layer had 32 nodes, and the third layer had 16 nodes. All hidden layers used a linear rectified activation function to achieve non-linear feature mapping. The output layer had 2 nodes, corresponding to the predicted soil moisture and light intensity values ​​for each growth stage of *Scutellaria baicalensis*. The training set was input into the network for iterative training. Mean squared error was used as the loss function, and gradient descent was used to update the network weights and biases. The number of iterations was set to 1000, and the learning rate was 0.001. After each iteration, the network's prediction accuracy was verified using a test set, and the prediction error on the test set was calculated. Training stopped when the prediction error was ≤3% or the maximum number of iterations was reached. After training, the network's performance was validated to ensure that it could accurately predict soil moisture and light intensity for each growth stage of *Scutellaria baicalensis*, thus completing the construction of the multi-dimensional growth prediction network for *Scutellaria baicalensis*.

[0038] Step S35: Perform environmental parameter index matching processing for the growth stage of Scutellaria baicalensis based on the Scutellaria baicalensis multidimensional growth prediction network to generate Scutellaria baicalensis growth stage environmental parameter index matching data.

[0039] In this embodiment of the invention, the constructed Scutellaria baicalensis multidimensional growth prediction network is used as the core tool to carry out the environmental parameter index matching processing of Scutellaria baicalensis growth stage. First, the plot coordinates, growth stage, and multidimensional confidence scores of all plots in the multi-layer growth stage data of Scutellaria baicalensis are extracted. The growth stage and multidimensional confidence scores of each plot are used as network input features and input into the Scutellaria baicalensis multidimensional growth prediction network according to the preset feature input order. The network performs feature extraction and nonlinear operation on the input features according to the trained weights and biases, and outputs the predicted soil moisture and light intensity values ​​corresponding to the plot. The predicted values ​​retain one decimal place and one integer place as percentages, which are the optimal environmental parameter values ​​for the growth stage of the plot. After completing network predictions for all plots, the prediction results are validated a second time. The predicted soil moisture and light intensity values ​​output by the network are compared with the matching values ​​in the dynamic matching data of Scutellaria baicalensis soil moisture and light intensity. If the deviation between the predicted value and the matching value is ≤5%, the network predicted value is directly used as the environmental parameter index matching value for that plot. If the deviation is >5%, the network predicted value is used as the core, and the mean is corrected by combining the dynamic matching value. The corrected value is used as the final environmental parameter index matching value. The correction formula is as follows: ,in For the single-parameter final environment parameter index matching value, These are the single-parameter predicted values ​​output by the network. This corresponds to the dynamic matching value for a single parameter. After completing the prediction and verification correction for all plots, the plot coordinates, growth stage, network input features, network prediction value, verification correction basis, final soil moisture index matching value, and final light intensity index matching value are precisely correlated in seven ways. The integrated data is arranged according to the horizontal and vertical sorting rules of the plot coordinates, and the core adaptation features of the environmental parameter index matching value are marked for each plot.

[0040] Furthermore, step S34 includes the following steps: Step S341: Analyze the changes in the environmental matching growth parameters of Scutellaria baicalensis based on the dynamic matching data of soil moisture and light, and generate the environmental matching growth parameter change data of Scutellaria baicalensis. In this embodiment of the invention, the coordinates, soil moisture matching values, light intensity matching values, growth stages, and related fine-tuning criteria of all grid plots in the data are extracted. Environmental matching growth parameter variation analysis is conducted for each of the four growth stages of Scutellaria baicalensis: rapid growth, stable growth, slow growth, and abnormal growth. A parameter gradient variation calculation method is used, with growth stage as the vertical dimension and soil moisture and light intensity as the horizontal dimensions. The gradient changes in soil moisture matching values ​​and light intensity matching values ​​are calculated for the same plot from the slow growth stage to the stable growth stage and then to the rapid growth stage. The gradient change is the difference between the matching values ​​of the later growth stage and the matching values ​​of the previous growth stage. Simultaneously, the dispersion of soil moisture matching values ​​and light intensity matching values ​​for the same growth stage in different plots are calculated. The dispersion is calculated using the standard deviation formula to reflect the degree of parameter difference between different plots at the same stage. For plots in the abnormal growth stage, the difference between their soil moisture and light intensity matching values ​​and the standard matching values ​​of the stable growth stage is calculated separately to clarify the deviation of abnormal parameters. During the analysis, all calculation results are retained to one decimal place. Then, the parameter gradient changes, dispersion, and deviation changes of each plot are classified according to the growth stage. The plot coordinates, growth stage, soil moisture matching value, light intensity matching value, parameter gradient changes, dispersion, and deviation changes are accurately correlated in all aspects. At the same time, the parameter change trend of each plot is marked as rising, falling, or stable. After sorting by growth stage and plot coordinates,

[0041] Step S342: Process the confidence weight matrix of Scutellaria baicalensis growth based on the multidimensional state confidence data of Scutellaria baicalensis growth to generate the confidence weight matrix data of Scutellaria baicalensis growth; In this embodiment of the invention, based on the confidence data of Scutellaria baicalensis growth multidimensional state, the coordinates of all plots and the confidence values ​​of growth multidimensional state are first extracted from the data. These values ​​range from 60 to 100. A matrix construction method is then used to process the Scutellaria baicalensis growth confidence weight matrix. First, according to the grid layout rules of the planting area, a two-dimensional matrix is ​​constructed, with the horizontal coordinate of the plot as the row dimension and the vertical coordinate as the column dimension, corresponding one-to-one with the actual plot distribution in the planting area. The number of rows and columns in the matrix is ​​exactly the same as the number of rows and columns in the grid of the planting area, and each position in the matrix corresponds to a unique plot coordinate. Then, the confidence values ​​of growth multidimensional state of all plots are normalized. The normalization calculation formula is as follows: ,in This represents the normalized confidence weight value for a single land parcel. This represents the confidence score of the original multidimensional growth state of a single plot of land. This represents the minimum confidence value of the multidimensional growth state of all plots. To obtain the maximum confidence value of the multidimensional growth state of all plots, the basic weight matrix is ​​then subjected to row normalization and column normalization. Row normalization is calculated by dividing all element values ​​in a single row of the matrix by the sum of the elements in that row, and column normalization is calculated by dividing all element values ​​in a single column of the matrix by the sum of the elements in that column. After the two processing steps, all matrix element values ​​are stably located in the 0-1 range. The higher the element value, the greater the confidence weight of the corresponding plot and the greater the influence on subsequent network training. Finally, the matrix row and column numbers, corresponding plot coordinates, original confidence values, normalized confidence weight values, and final matrix element values ​​are precisely correlated to generate the Scutellaria baicalensis growth confidence weight matrix data.

[0042] Step S343: Based on the Scutellaria baicalensis growth confidence weight matrix data and the Scutellaria baicalensis environment matching growth parameter change data, select the Scutellaria baicalensis multidimensional growth network sample set and generate Scutellaria baicalensis multidimensional growth network sample set data; In this embodiment of the invention, two datasets are first fused using plot coordinates as the primary key. Core feature indicators such as matrix element values, growth stage, soil moisture matching value, light intensity matching value, parameter gradient change, and dispersion are extracted from each plot in the fused dataset. All core feature indicators for each plot are integrated into an independent sample, forming an initial sample set. A weighted threshold screening method is used to perform the first screening of the initial sample set. A preset matrix element value screening threshold of 0.05 is used to remove samples with matrix element values ​​< 0.05, retaining samples with matrix element values ​​≥ 0.05. This screening rule ensures that the retained samples have high confidence weights and strong data reliability. The sample set after the first screening is then stratified according to growth stage, ensuring that samples from the rapid growth stage, stable growth stage, slow growth stage, and abnormal growth stage each account for 25%, achieving a balanced distribution of growth stages in the sample set and avoiding training skew caused by an excessively high proportion of samples from a single stage. Subsequently, the stratified sample set was validated for feature effectiveness. The coefficient of variation (COP) of each feature index for each sample was calculated. The COP is the ratio of the standard deviation to the mean. Invalid feature samples with COP < 0.1 were removed, and samples with significant differences in feature indices and high effectiveness were retained. Finally, all valid samples after screening, stratification, and validation were divided into training and testing subsets in an 8:2 ratio. Within each subset, samples at each growth stage were evenly distributed. Then, the plot coordinates, core feature indices, subset to which the sample belongs, and screening criteria of all samples were integrated and sorted by sample number.

[0043] Step S344: Construct a Scutellaria baicalensis multidimensional growth prediction network based on the preset machine learning network framework and the sample set data of the Scutellaria baicalensis multidimensional growth network.

[0044] In this embodiment of the invention, the preset machine learning network framework is a deep feedforward neural network. This framework includes a three-layer core structure: an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is set to 8, which correspond to the soil moisture matching value, light intensity matching value, soil moisture gradient change, light intensity gradient change, soil moisture dispersion, light intensity dispersion, growth stage encoding value, and matrix element values ​​in the Scutellaria baicalensis growth confidence weight matrix data, respectively. The growth stage encoding value is divided into rapid growth stage 1, stable growth stage 2, slow growth stage 3, and abnormal growth stage 4. Phase 4 involves quantitative encoding. Four hidden layers are used: the first layer has 128 nodes, the second layer has 64 nodes, the third layer has 32 nodes, and the fourth layer has 16 nodes. All hidden layers employ a linear rectified activation function to achieve non-linear mapping and deep extraction of feature indicators. Batch normalization is applied after each hidden layer to eliminate training bias caused by differences in feature dimensions. The output layer has two nodes, corresponding to the predicted ideal soil moisture and ideal light intensity at the Scutellaria baicalensis growth stage. A linear activation function is used in the output layer to ensure the quantitative accuracy of the predicted values. In the network construction process, a subset of training samples from the Scutellaria baicalensis multidimensional growth network sample set is input into the input layer. Feature indicators are then passed to each hidden layer for deep feature extraction according to the forward propagation rule. Finally, the output layer outputs the predicted value. Mean squared error is used as the network loss function to quantify the deviation between the predicted value and the actual sample value. An adaptive moment estimation optimization algorithm is used to update the weights and biases of each layer of the network. The network learning rate is set to 0.001, and the maximum number of iterations is 2000. After each iteration, a subset of test samples is input into the network for accuracy verification. The mean absolute error of the test set is calculated. Training stops when the mean absolute error is ≤2% or the maximum number of iterations is reached. After training stops, the network weights and biases are fixed and saved, completing the final determination of the network structure and parameters. Simultaneously, the network's generalization ability is verified by inputting new land parcel samples that were not included in the training to verify the accuracy of the prediction results. Finally, the construction of the Scutellaria baicalensis multidimensional growth prediction network is completed.

[0045] Furthermore, as an embodiment of the present invention, reference is made to... Figure 3 As shown, Figure 1 A detailed flowchart of step S4 is shown below. In this embodiment, step S4 includes the following steps: Step S41: Analyze the ideal planting environment parameters of Scutellaria baicalensis based on the index matching data of environmental parameters during the growth stage of Scutellaria baicalensis, and generate the ideal planting environment parameters of Scutellaria baicalensis. In this embodiment of the invention, the coordinates, growth stage, final soil moisture index matching value, final light intensity index matching value, and the verification and correction basis for parameter matching of all grid plots are first extracted from the data. A parameter feature extraction and standardized integration method is used to analyze the ideal planting environment parameters for Scutellaria baicalensis. For each plot, the soil moisture index matching value and light intensity index matching value, after network prediction and secondary verification and correction, are directly extracted as core ideal parameters. These values ​​represent the optimal environmental parameter values ​​for the corresponding growth stage, combined with the actual attributes of the plot. Soil moisture values ​​are retained to one decimal place, and light intensity values ​​are retained to an integer place. During the analysis, the ideal parameters for each plot are categorized according to the growth stages of Scutellaria baicalensis: rapid growth period, stable growth period, slow growth period, and abnormal growth period. Simultaneously, the physiological requirements of the growth stage corresponding to the ideal parameters are labeled for each plot. For example, an ideal soil moisture of 60%-70% during the rapid growth period corresponds to a high demand for water absorption by the plant's roots. After extracting the ideal parameters for all plots, the plot coordinates are precisely correlated with the corresponding ideal soil moisture value and ideal light intensity value. During the correlation process, it is ensured that each plot has only one set of unique ideal planting environment parameters, with no duplication or mismatch. Then, the integrated data is systematically arranged according to the horizontal and vertical sorting rules of the plot coordinates, while removing all invalid and duplicate data.

[0046] Step S42: Based on the ideal planting environment parameters of Scutellaria baicalensis, compare the actual planting environment parameters of Scutellaria baicalensis to generate comparison data of actual planting environment parameters of Scutellaria baicalensis; In this embodiment of the invention, the ideal planting environment parameters for Scutellaria baicalensis are used as a benchmark for comparison. The actual planting environment parameters are then compared. First, IoT sensors deployed in the Scutellaria baicalensis planting area collect actual environmental parameters. Soil moisture sensors are buried at a depth of 20 cm in the center of each grid plot, and light intensity sensors are installed 50 cm above the canopy of each grid plot. Both types of sensors are set to collect data every 5 minutes, for a total of 12 sets of actual data collected over one hour. Each set of soil moisture and light intensity data is then filtered for valid values, removing abnormal data that exceed reasonable ranges. The arithmetic mean of the 12 sets of valid data is then calculated, and this average is used as the actual soil moisture value and actual light intensity value for the corresponding plot. The average soil moisture value is retained to one decimal place, and the average light intensity value is retained to an integer number. After collecting and calculating the actual environmental parameters for all plots, the ideal soil moisture and ideal light intensity values ​​from the ideal planting environment parameters for Scutellaria baicalensis were precisely matched with the collected and calculated actual soil moisture and actual light intensity values, using the plot coordinates as the primary key. During the matching process, it was ensured that the ideal and actual parameters for the same plot corresponded completely, with no cross-matching. Subsequently, the plot coordinates, ideal soil moisture values, ideal light intensity values, actual soil moisture values, and actual light intensity values ​​were systematically integrated and arranged according to the horizontal and vertical sorting rules of the plot coordinates. The collection time of the actual parameters and the location of the sensor equipment were also marked for each plot.

[0047] Step S43: Calculate the deviation of Scutellaria baicalensis planting environment parameters based on the comparison data of actual planting environment parameters, and generate Scutellaria baicalensis planting environment parameter deviation data; In this embodiment of the invention, a method combining quantitative difference and percentage deviation is used to calculate the deviation of environmental parameters for Scutellaria baicalensis cultivation. First, the plot coordinates, ideal soil moisture value, ideal light intensity value, actual soil moisture value, and actual light intensity value of all plots are extracted from the data. Deviation calculations are then performed separately for the soil moisture and light intensity parameters. Soil moisture deviation calculation is divided into absolute deviation value and relative deviation degree; a positive value represents that the actual value is higher than the ideal value, and a negative value represents that the actual value is lower than the ideal value. The formula for calculating the relative deviation degree of soil moisture is as follows: ,in This represents the relative deviation of soil moisture. This represents the actual soil moisture value. The ideal soil moisture value is used, and the result is rounded to the nearest integer, reflecting the proportion of deviation between the actual value and the ideal value. The formula for the absolute deviation of light intensity is: ,in This represents the absolute deviation of light intensity. This represents the actual light intensity value for a single plot of land. This represents the ideal light intensity value for a single plot of land; the formula for the relative deviation of light intensity is... The results are rounded to the nearest integer to reflect the deviation of the actual light intensity from the ideal value. To determine the relative deviation of light intensity, the four indicators were calculated for each plot of land strictly according to the arithmetic operation rules, with no calculation errors throughout the process. After the calculation was completed, the five data points of plot coordinates, absolute deviation of soil moisture, relative deviation of soil moisture, absolute deviation of light intensity, and relative deviation of light intensity were accurately correlated and arranged in a regular manner according to the horizontal and vertical sorting rules of plot coordinates. At the same time, the positive and negative attributes of the corresponding deviation value and the range to which the deviation belongs were marked for each plot.

[0048] Step S44: Based on the deviation data of Scutellaria baicalensis planting environment parameters and the confidence data of Scutellaria baicalensis growth multidimensional state, conduct Scutellaria baicalensis planting parameter fit analysis to generate Scutellaria baicalensis planting parameter fit data.

[0049] In this embodiment of the invention, firstly, the plot coordinates, relative deviation of soil moisture, and relative deviation of light intensity of all plots are extracted from the deviation data of Scutellaria baicalensis planting environment parameters. Then, the confidence values ​​of the multidimensional growth states of the corresponding plots are extracted from the confidence data of Scutellaria baicalensis growth states. The two sets of data are accurately fused using the plot coordinates as the primary key, ensuring a complete match between the deviation data and the confidence values ​​for the same plot. A weighted comprehensive calculation method is used to calculate the planting parameter fit. First, the relative deviations of soil moisture and light intensity are calculated using an equal-weighted average to obtain the comprehensive deviation. The calculation formula is as follows: ,in For the overall deviation, This represents the relative deviation of soil moisture. The relative deviation from light intensity is calculated, and the result is rounded to one decimal place. The confidence scores for the multidimensional growth states are then normalized to reflect the weighted influence of confidence on fitness; higher values ​​indicate a greater weighted influence. Finally, the core fitness calculation is performed using the following formula: ,in This refers to the planting parameter fit value. For the overall deviation, To normalize the confidence level, the results are rounded to integers, ranging from 0 to 100. Higher values ​​indicate better compatibility between actual and ideal planting parameters, while lower values ​​indicate poorer compatibility. The compatibility score was calculated for each plot using the formula described above, strictly adhering to the order and rules of computation. After calculating the compatibility score for all plots, a precise seven-way correlation was established between plot coordinates, relative deviation of soil moisture, relative deviation of light intensity, confidence score of multidimensional growth status, normalized confidence level, comprehensive deviation, and compatibility score of planting parameters. These were then arranged according to the horizontal and vertical sorting rules of the plot coordinates. Simultaneously, each plot was categorized into compatibility levels based on its compatibility score: 90-100 for excellent compatibility, 80-89 for good compatibility, 70-79 for medium compatibility, 60-69 for acceptable compatibility, and 0-59 for unsuitable compatibility. This generated the compatibility score data for Scutellaria baicalensis planting parameters.

[0050] Furthermore, step S44 includes the following steps: Step S441: Calculate the deviation of soil moisture and light intensity based on the deviation data of Scutellaria baicalensis planting environment parameters, and generate soil moisture-light intensity deviation data; In this embodiment of the invention, an amplitude quantification integration method is used to calculate the deviation amplitudes of soil moisture and light intensity. For soil moisture deviation, the relative deviation is used as the core quantification indicator, combined with the positive and negative attributes of the absolute deviation value for amplitude calibration. The relative deviation of soil moisture is directly used as the soil moisture deviation amplitude value, retaining integer values, while simultaneously labeling the positive and negative attributes of the corresponding absolute deviation value, clarifying whether the actual soil moisture value is higher or lower than the ideal value. For light intensity deviation, the relative deviation is also used as the core quantification indicator, combined with the positive and negative attributes of the absolute deviation value for calibration. The relative deviation of light intensity is used as the light intensity deviation amplitude value, retaining integer values, and labeling the corresponding deviation trend. When extracting and calibrating the two deviation amplitude values ​​for each plot, the data correspondence is strictly followed to ensure that the deviation amplitude value accurately matches the plot coordinates and deviation trend. Then, the arithmetic mean method is used to calculate the comprehensive deviation amplitude value for each plot, which comprehensively reflects the overall deviation degree of the plot's environmental parameters. After calculating the deviation of all plots, the plot coordinates, soil moisture deviation and trend, light intensity deviation and trend, and overall deviation are precisely correlated in five aspects. The integrated data is then systematically arranged according to the horizontal and vertical sorting rules of the plot coordinates, while invalid calculation results are removed.

[0051] Step S442: Based on the confidence data of Scutellaria baicalensis growth multidimensional state, perform confidence weighting processing on the ideal planting parameters of Scutellaria baicalensis to generate confidence weighted data of ideal planting parameters of Scutellaria baicalensis; In this embodiment of the invention, based on the confidence data of Scutellaria baicalensis growth multidimensional state, the plot coordinates and growth multidimensional state confidence values ​​of all plots in the data are first extracted. These values ​​range from 60 to 100. A linear weighted assignment method is then used to perform weighted processing of the confidence values ​​for the ideal planting parameters of Scutellaria baicalensis. First, the growth multidimensional state confidence values ​​are normalized. The normalization calculation formula is as follows: ,in The normalized confidence coefficient is... To calculate the confidence score for the multidimensional growth state, the result is rounded to three decimal places. This coefficient is used as the base value for confidence score weighting, achieving a proportional scaling of the confidence score from the 60-100 range to the 0.6-1.0 range, ensuring that the range of weighting coefficients conforms to the computational logic. Based on the normalized confidence score, weighting coefficients are assigned to soil moisture and light intensity. Since soil moisture and light intensity have equally important effects on the growth state of Scutellaria baicalensis, the normalized confidence score is directly used as the weighting coefficient for soil moisture and light intensity. The two weighting coefficients are completely identical and rounded to three decimal places. Simultaneously, a comprehensive weighting coefficient is calculated for each plot. The comprehensive weighting coefficient is the same as the normalized confidence score and serves as the core weighting basis for subsequent comprehensive fitness calculations. After calculating the weighting coefficients for all plots, the plot coordinates, original growth multidimensional state confidence values, normalized confidence coefficients, soil moisture weighting coefficients, light intensity weighting coefficients, and comprehensive weighting coefficients are precisely correlated in six directions and arranged according to the horizontal and vertical sorting rules of the plot coordinates to ensure that each weighting coefficient of each plot corresponds one-to-one with the original confidence value, with no mismatches or omissions.

[0052] Step S443: Based on the soil moisture-light intensity deviation data and the confidence weighted data of Scutellaria baicalensis ideal planting parameters, calculate the basic value of Scutellaria baicalensis planting parameter fit, and generate the basic value data of Scutellaria baicalensis planting parameter fit. In this embodiment of the invention, firstly, using the plot coordinates as the primary key, the two sets of data are precisely fused. The fused data is then used to extract the soil moisture deviation amplitude, light intensity deviation amplitude, soil moisture weighting coefficient, light intensity weighting coefficient, and comprehensive weighting coefficient for each plot, ensuring that the amplitude data and weighting coefficients for the same plot are completely matched without any cross-fusion. The weighted product summation method is used to calculate the basic fit value; the core calculation formula is as follows: ,in This represents the baseline value for the suitability of Scutellaria baicalensis planting parameters for a single plot. A higher value indicates a greater weighted deviation between the actual planting parameters and the ideal planting parameters, resulting in poorer suitability. Conversely, a lower value indicates a smaller weighted deviation and better suitability. This represents the deviation of soil moisture in a single plot. This is a weighted coefficient for soil moisture content in a single plot. This represents the deviation of light intensity from the average intensity of a single plot of land. The calculation process strictly follows the order of first performing individual weighted product calculations and then performing overall arithmetic summation to ensure the accuracy of the calculation results throughout the process. After calculating for each plot, the eight data points—plot coordinates, soil moisture deviation, light intensity deviation, soil moisture weighting coefficient, light intensity weighting coefficient, soil moisture deviation weighting value, light intensity deviation weighting value, and basic fitness value—are precisely correlated and arranged in a regular manner according to the plot coordinate horizontal and vertical sorting rules.

[0053] Step S444: Perform Scutellaria baicalensis planting parameter fit analysis based on the basic value data of Scutellaria baicalensis planting parameter fit, and generate Scutellaria baicalensis planting parameter fit data.

[0054] In this embodiment of the invention, a numerical inverse transformation and gradation method is used to conduct a fitness analysis of Scutellaria baicalensis planting parameters. First, a linear inverse transformation is performed on the baseline fitness value to convert it into a fitness value in the range of 0-100. The formula is as follows: ,in The values ​​represent the fit of Scutellaria baicalensis planting parameters. The formula uses the baseline value for adaptability, rounding the calculation results to the nearest integer. This formula achieves a proportional inverse mapping from the baseline value range of 0-200 to the range of 0-100. A higher adaptability value indicates a better match between the actual and ideal planting parameters, while a lower value indicates a worse match. After conversion, quantitative adaptability levels are assigned based on the adaptability value: 90-100 is Level 1 adaptability, indicating a high degree of match between the actual and ideal parameters, requiring no adjustment to the planting environment; 80-89 is Level 2 adaptability, indicating a basic match between the actual and ideal parameters, requiring only minor environmental adjustments; 70-79 is Level 3 adaptability, indicating a certain deviation between the actual and ideal parameters, requiring targeted environmental adjustments; 60-69 is Level 4 adaptability, indicating a significant deviation between the actual and ideal parameters, requiring substantial environmental adjustments; and 0-59 is Level 5 adaptability, indicating a severe deviation between the actual and ideal parameters, requiring urgent environmental adjustments. After converting the fit score and calibrating the fit level for each plot, specific environmental adjustment directions were marked for each plot based on the deviation trends of soil moisture and light intensity, such as high soil moisture or low light intensity. Finally, the plot coordinates, base fit score, fit score value, fit level, soil moisture deviation trend, light intensity deviation trend, and environmental adjustment direction were precisely correlated in seven aspects, and the integrated data was systematically arranged according to the horizontal and vertical sorting rules of the plot coordinates.

[0055] Furthermore, step S5 includes the following steps: Step S51: Analyze the variation range of Scutellaria baicalensis growth environment based on the adaptation data of Scutellaria baicalensis planting parameters, and generate data on the variation range of Scutellaria baicalensis growth environment; In this embodiment of the invention, a time-series gradient calculation method is used to analyze the range of changes in the growth environment of Scutellaria baicalensis. First, the fitness values ​​of the planting area for 24 consecutive hours are collected, with the collection time interval set to 1 hour. Each plot corresponds to 24 fitness values ​​at different time points. For each plot, the difference between the fitness values ​​of two adjacent time points is calculated sequentially. This difference is the range of environmental change in a single time period. A positive value represents an increase in fitness and a change in the environment towards the ideal state, while a negative value represents a decrease in fitness and a deviation from the ideal state. The difference is rounded to an integer. Then, the average absolute value of the 24 ranges of environmental change in a single time period is calculated as the 24-hour average range of environmental change for that plot. The calculation formula is: 24-hour average range of environmental change = Σ|range of environmental change in a single time period| / 24. The result is rounded to one decimal place. This value quantitatively reflects the overall degree of drastic change in the plot's environment. Simultaneously, the maximum and minimum adaptability values ​​for each plot within 24 hours are calculated. The difference between these values ​​represents the extreme environmental change range, rounded to the nearest integer, reflecting the maximum fluctuation range of the plot's environment. The environmental change trend for each plot is also marked, determined by the linear fitting slope of the 24-hour adaptability values: a slope > 0 indicates an upward trend, a slope = 0 indicates a stable trend, and a slope < 0 indicates a downward trend. After calculating the change range and marking the trends for all plots, the plot coordinates, 24 single-period environmental change range values, 24-hour average environmental change range value, extreme environmental change range value, and environmental change trend are comprehensively and accurately correlated, and the data is integrated according to the horizontal and vertical sorting rules of the plot coordinates.

[0056] Step S52: Based on the data on the range of changes in the growth environment of Scutellaria baicalensis, perform matching processing on the growth and environmental change adaptability of Scutellaria baicalensis to generate Scutellaria baicalensis growth-environmental change adaptability matching data; In this embodiment of the invention, firstly, the plot coordinates, 24-hour average environmental change amplitude, and environmental change trend of all plots are extracted from the growth environment change amplitude data. Then, the growth multidimensional state confidence values ​​of the corresponding plots are extracted from the growth multidimensional state confidence data. Using the plot coordinates as the primary key, the two sets of data are accurately fused to ensure a complete match between the environmental change data and the confidence values ​​for the same plot. A numerical ratio determination method is used for fitness matching. First, the 24-hour average environmental change amplitude is normalized. The normalization calculation formula is as follows: ,in This represents the normalized range of environmental changes. The 24-hour average environmental change amplitude is calculated, rounded to three decimal places, and mapped to the 0-1 interval. The normalized change amplitude is then compared to the confidence score of the growth multidimensional state using the following formula: ,in The growth-environment change fitness ratio is a core indicator for determining fitness level. The confidence score for the multidimensional growth states is calculated, with results rounded to three decimal places. This ratio is the core indicator for fitness matching. A pre-defined quantitative fitness matching standard is used: a fitness ratio ≤ 0.1 indicates high fitness, meaning the Scutellaria baicalensis growth state is fully adapted to environmental changes; 0.1-0.2 indicates moderate fitness, meaning the Scutellaria baicalensis growth state is basically adapted to environmental changes with only slight discomfort; 0.2-0.3 indicates low fitness, meaning the Scutellaria baicalensis growth state is difficult to adapt to environmental changes with significant discomfort; and > 0.3 indicates maladaptation, meaning the Scutellaria baicalensis growth state is completely unable to adapt to environmental changes, and growth is severely affected. Fitness levels are determined for each plot according to this standard. Simultaneously, considering the environmental change trend and confidence score, points of mismatch in fitness are marked for each plot, such as low confidence scores during an upward trend and high confidence scores during a downward trend. After completing the fitness determination and labeling of all plots, the plot coordinates, 24-hour average environmental change amplitude, growth multidimensional state confidence value, fitness ratio, fitness level, and adaptation conflict points are precisely correlated in six aspects.

[0057] Step S53: Adjust the precise control parameters for Scutellaria baicalensis plot zoning based on the Scutellaria baicalensis growth-environmental change adaptability matching data, and generate precise control parameter data for Scutellaria baicalensis plot zoning. In this embodiment of the invention, firstly, the plot coordinates, fitness level, and fitness conflict points of all plots are extracted from the fitness matching data. Then, the ideal soil moisture value and ideal light intensity value of the corresponding plot are extracted from the growth stage environmental parameter index matching data. Simultaneously, the actual soil moisture value and actual light intensity value are retrieved from the *Scutellaria baicalensis* planting environmental parameter deviation data. Multiple data sets are fused using plot coordinates as the primary key to ensure that the fitness characteristics, ideal parameters, and actual parameters of the same plot completely correspond. A pre-set graded differentiated precise control rule is established, and the core control parameter adjustment formula is set based on the fitness level. ,in This is the adjustment value after the final calibration of a single parameter. This represents the ideal planting value for a single parameter. This represents the actual planting value for a single parameter. The fitness level adjustment coefficient is set as follows: 0 for highly adapted plots, 0.5 for moderately adapted plots, 1 for low-adapted plots, and 1.05 for poorly adapted plots. A calibration coefficient for environmental change trends is used, with an upward trend value of 0.98, a downward trend value of 1.02, and a stable trend value of 1. If the value of an unsuitable plot exceeds the reasonable parameter range for Scutellaria baicalensis growth after compensation and adjustment, the corresponding reasonable critical value is directly taken. The soil moisture adjustment value is retained to one decimal place, and the light intensity adjustment value is retained to an integer place. After calculating the adjustment values ​​for all plots, the corresponding target soil moisture value and target light intensity value are determined. At the same time, the execution duration of a single control is set according to the adjustment value range: ≤5% corresponds to a duration of 5 minutes, 5%-10% corresponds to a duration of 10 minutes, and >10% corresponds to a duration of 15 minutes. The irrigation equipment output and shading equipment opening and closing parameters are matched synchronously. Finally, the plot coordinates, adaptability level, control adjustment value, target environmental parameters, control duration, and equipment execution parameters are accurately correlated, sorted and integrated according to plot coordinates, and the precise control parameter data for Scutellaria baicalensis plot zoning is generated.

[0058] Step S54: Based on the precise control parameter data of Scutellaria baicalensis plot zoning, perform intelligent control processing of the Scutellaria baicalensis distribution and planting environment to generate intelligent control data of the Scutellaria baicalensis distribution and planting environment.

[0059] In this embodiment of the invention, intelligent regulation and control of the planting environment of Scutellaria baicalensis is carried out. Relying on the 5G Internet of Things intelligent regulation and control system built in the planting park, the regulation parameter data is synchronized to the control terminal of all intelligent regulation and control devices in the park through the wireless data transmission module. The control terminal is bound to the irrigation equipment and shading equipment of each grid plot, and the equipment binding code corresponds completely to the plot coordinates, ensuring that the regulation and control instructions are accurately sent to the equipment of the corresponding plot. The irrigation equipment uses a drip irrigation intelligent irrigation device, buried next to the plant roots in each plot. The control terminal precisely adjusts the soil moisture adjustment value, target soil moisture value, and execution duration in the parameter data according to the plot zoning, and automatically sets the drip irrigation water output and irrigation frequency. The water output is set according to the standard of 0.5L / ㎡ for every 1% of the soil moisture adjustment value. Soil moisture data is collected in real time during irrigation. When the actual soil moisture value reaches the target soil moisture value, the equipment automatically stops irrigation. The shading equipment uses an electric telescopic shading net, which is erected 1 meter above the canopy of each plot. The control terminal automatically sets the opening degree of the shading net according to the light intensity adjustment value, target light intensity value, and execution duration. The opening degree is set according to the standard of 5% opening degree for every 100lx light intensity adjustment value. Light intensity data is collected in real time during the adjustment. When the actual light intensity value reaches the target light intensity value, the equipment automatically stops adjusting. During the control and regulation process, the system records the equipment operating status, control parameter execution, and real-time changes in environmental parameters for each plot of land at one-minute intervals. Simultaneously, the control and regulation results are verified, and the deviation rate between the actual parameters and the target parameters after control is calculated using the following formula: ,in The deviation rate of the parameters after adjustment. These are the actual environmental parameter values ​​after the adjustment is completed. To regulate the target environmental parameter values, a deviation rate of ≤2% is considered a qualified regulation. The entire process records the verification results and various operational data, and finally integrates them to generate intelligent regulation data for the distribution and planting environment of Scutellaria baicalensis.

[0060] This specification provides an IoT-based digital intelligent monitoring system for Scutellaria baicalensis cultivation, used to execute the IoT-based digital intelligent monitoring method for Scutellaria baicalensis cultivation as described above. The IoT-based digital intelligent monitoring system for Scutellaria baicalensis cultivation includes: The Scutellaria baicalensis sensing and acquisition module is used to collect multi-source Scutellaria baicalensis sensing data through an array of IoT sensors. Based on the multi-source Scutellaria baicalensis sensing data, the module analyzes the plant density and canopy temperature of Scutellaria baicalensis to generate plant density-canopy temperature data. Based on the plant density-canopy temperature data, the module performs multi-dimensional canopy cluster type association classification of Scutellaria baicalensis to generate multi-dimensional canopy cluster type association data. The Scutellaria baicalensis multidimensional confidence analysis module is used to perform multidimensional confidence analysis of Scutellaria baicalensis growth status based on multidimensional crown cluster type association data, and generate multidimensional confidence data of Scutellaria baicalensis growth status. The Scutellaria baicalensis growth status prediction module is used to perform Scutellaria baicalensis growth stage environmental parameter index matching processing based on the multidimensional growth status confidence data of Scutellaria baicalensis, and generate Scutellaria baicalensis growth stage environmental parameter index matching data. The Scutellaria baicalensis environmental parameter matching module is used to perform Scutellaria baicalensis planting parameter fit analysis based on the Scutellaria baicalensis growth stage environmental parameter index matching data and Scutellaria baicalensis growth multidimensional state confidence data, and generate Scutellaria baicalensis planting parameter fit data. The Scutellaria baicalensis planting parameter control module is used to intelligently control the distribution and planting environment of Scutellaria baicalensis based on the adaptability data of Scutellaria baicalensis planting parameters, and generate intelligent control data of the distribution and planting environment of Scutellaria baicalensis.

[0061] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0062] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A digital intelligent supervision method for Scutellaria baicalensis Georgi planting based on Internet of Things, characterized in that, Includes the following steps: Step S1: Collect multi-source Scutellaria baicalensis sensor data through the array sensor of the Internet of Things, analyze the plant density and canopy temperature of Scutellaria baicalensis based on the multi-source Scutellaria baicalensis sensor data, and generate Scutellaria baicalensis plant density-canopy temperature data; perform multi-dimensional crown cluster type association classification of Scutellaria baicalensis based on the plant density-canopy temperature data, and generate multi-dimensional crown cluster type association data of Scutellaria baicalensis. Step S2: Perform confidence analysis on the multidimensional growth state of Scutellaria baicalensis based on the multidimensional crown cluster type association data, and generate confidence data on the multidimensional growth state of Scutellaria baicalensis. Step S3: Perform environmental parameter index matching processing on the growth stage of Scutellaria baicalensis based on the multidimensional growth state confidence data, and generate environmental parameter index matching data for the growth stage of Scutellaria baicalensis. Step S4: Based on the index matching data of environmental parameters in the growth stage of Scutellaria baicalensis and the confidence data of multidimensional growth status of Scutellaria baicalensis, conduct a fitness analysis of Scutellaria baicalensis planting parameters and generate fitness data of Scutellaria baicalensis planting parameters; Step S5: Based on the Scutellaria baicalensis planting parameter adaptation data, perform intelligent regulation and control processing of the Scutellaria baicalensis distribution and planting environment to generate intelligent regulation and control data of the Scutellaria baicalensis distribution and planting environment.

2. The Internet of Things-based digital intelligent supervision method for Scutellaria baicalensis planting according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Collect multi-source Scutellaria baicalensis sensor data through the array sensor of the Internet of Things, perform multi-source Scutellaria baicalensis sensor filtering on the multi-source Scutellaria baicalensis sensor data, and generate multi-source Scutellaria baicalensis sensor filtered data. Step S12: Based on the preset Scutellaria baicalensis crown cluster features, perform Scutellaria baicalensis multi-source sensor filter data to identify Scutellaria baicalensis multi-source crown cluster features and generate Scutellaria baicalensis multi-source crown cluster feature data; Step S13: Analyze the plant density and canopy temperature of Scutellaria baicalensis based on the multi-source crown cluster characteristic data, and generate plant density-canopy temperature data of Scutellaria baicalensis. Step S14: Based on the plant density-canopy temperature data and the multi-source crown cluster feature data of Scutellaria baicalensis, perform multi-dimensional morphological calibration of Scutellaria baicalensis crown clusters to generate multi-dimensional morphological calibration data of Scutellaria baicalensis crown clusters; Step S15: Based on the multidimensional morphological calibration data of Scutellaria baicalensis crown clusters, perform multidimensional crown cluster type association classification of Scutellaria baicalensis and generate multidimensional crown cluster type association data of Scutellaria baicalensis. 3.The method of claim 1, wherein the method further comprises: Step S2 includes the following steps: Step S21: Identify the growth interval difference of Scutellaria baicalensis crown clusters based on the multidimensional crown cluster type association data, and generate Scutellaria baicalensis crown cluster growth interval difference data; Step S22: Analyze the deviation of the growth stage of Scutellaria baicalensis crown clusters based on the difference data of the growth interval of Scutellaria baicalensis crown clusters, and generate the deviation data of the growth stage of Scutellaria baicalensis crown clusters; Step S23: Based on the deviation data of Scutellaria baicalensis crown growth stage and the plant density-canopy temperature data, perform confidence analysis on the multidimensional growth state of Scutellaria baicalensis to generate confidence data on the multidimensional growth state of Scutellaria baicalensis.

4. The digital intelligent supervision method for Scutellaria baicalensis Georgi planting based on Internet of Things according to claim 3, characterized in that, Step S23 includes the following steps: Step S231: Perform a first confidence analysis on the growth of Scutellaria baicalensis based on the deviation data of the crown cluster growth stage, and generate the first confidence data of Scutellaria baicalensis growth; Step S232: Perform mean deviation analysis on Scutellaria baicalensis growth based on the first confidence level data to generate mean deviation data for Scutellaria baicalensis growth; Step S233: Calculate the multi-canopy temperature ratio of Scutellaria baicalensis based on the plant density-canopy temperature data, and generate multi-canopy temperature ratio data of Scutellaria baicalensis. Step S234: Based on the multi-canopy temperature ratio data of Scutellaria baicalensis and the mean deviation data of Scutellaria baicalensis growth, perform second confidence analysis on the growth of Scutellaria baicalensis to generate second confidence data on the growth of Scutellaria baicalensis; Step S235: Based on the first confidence level data and the second confidence level data of Scutellaria baicalensis growth, perform multidimensional state confidence analysis of Scutellaria baicalensis growth to generate multidimensional state confidence data of Scutellaria baicalensis growth.

5. The digital intelligent supervision method for Scutellaria baicalensis Georgi planting based on Internet of Things according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Based on the confidence data of the multidimensional growth state of Scutellaria baicalensis, determine the multi-dimensional growth state stage of Scutellaria baicalensis and generate multi-dimensional growth state stage data of Scutellaria baicalensis. Step S32: Based on the multi-layer growth stage data of Scutellaria baicalensis, divide the Scutellaria baicalensis canopy environmental parameter index and generate Scutellaria baicalensis canopy environmental parameter index data; Step S33: Perform dynamic matching processing of soil moisture and light intensity of Scutellaria baicalensis based on the Scutellaria baicalensis canopy environmental parameter index data to generate dynamic matching data of soil moisture and light intensity of Scutellaria baicalensis. Step S34: Construct a multidimensional growth prediction network for Scutellaria baicalensis based on dynamic matching data of soil moisture and light intensity and confidence data of multidimensional growth status of Scutellaria baicalensis; Step S35: Perform Scutellaria baicalensis growth stage environmental parameter index matching processing based on the Scutellaria baicalensis multidimensional growth prediction network to generate Scutellaria baicalensis growth stage environmental parameter index matching data.

6. The digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things as described in claim 5, characterized in that, Step S34 includes the following steps: Step S341: Analyze the changes in the environmental matching growth parameters of Scutellaria baicalensis based on the dynamic matching data of soil moisture and light, and generate the environmental matching growth parameter change data of Scutellaria baicalensis. Step S342: Process the confidence weight matrix of Scutellaria baicalensis growth based on the multidimensional state confidence data of Scutellaria baicalensis growth to generate the confidence weight matrix data of Scutellaria baicalensis growth; Step S343: Based on the Scutellaria baicalensis growth confidence weight matrix data and the Scutellaria baicalensis environment matching growth parameter change data, select the Scutellaria baicalensis multidimensional growth network sample set and generate Scutellaria baicalensis multidimensional growth network sample set data; Step S344: Construct a Scutellaria baicalensis multidimensional growth prediction network based on a preset machine learning network framework and the sample data of the Scutellaria baicalensis multidimensional growth network.

7. The digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things as described in claim 1, characterized in that, Step S4 includes the following steps: Step S41: Analyze the ideal planting environment parameters of Scutellaria baicalensis based on the index matching data of environmental parameters during the growth stage of Scutellaria baicalensis, and generate the ideal planting environment parameters of Scutellaria baicalensis. Step S42: Based on the ideal planting environment parameters of Scutellaria baicalensis, compare the actual planting environment parameters of Scutellaria baicalensis to generate comparison data of actual planting environment parameters of Scutellaria baicalensis; Step S43: Calculate the deviation of Scutellaria baicalensis planting environment parameters based on the comparison data of actual planting environment parameters, and generate Scutellaria baicalensis planting environment parameter deviation data; Step S44: Based on the deviation data of Scutellaria baicalensis planting environment parameters and the confidence data of Scutellaria baicalensis growth multidimensional state, conduct Scutellaria baicalensis planting parameter fit analysis to generate Scutellaria baicalensis planting parameter fit data.

8. The digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things according to claim 7, characterized in that, Step S44 includes the following steps: Step S441: Calculate the deviation of soil moisture and light intensity based on the deviation data of Scutellaria baicalensis planting environment parameters, and generate soil moisture-light intensity deviation data; Step S442: Based on the confidence data of Scutellaria baicalensis growth multidimensional state, perform confidence weighting processing on the ideal planting parameters of Scutellaria baicalensis to generate confidence weighted data of ideal planting parameters of Scutellaria baicalensis; Step S443: Based on the soil moisture-light intensity deviation data and the confidence weighted data of Scutellaria baicalensis ideal planting parameters, calculate the basic value of Scutellaria baicalensis planting parameter fit, and generate the basic value data of Scutellaria baicalensis planting parameter fit. Step S444: Perform Scutellaria baicalensis planting parameter fit analysis based on the basic value data of Scutellaria baicalensis planting parameter fit, and generate Scutellaria baicalensis planting parameter fit data.

9. The digital intelligent monitoring method for Scutellaria baicalensis cultivation based on the Internet of Things according to claim 1, characterized in that, Step S5 includes the following steps: Step S51: Analyze the variation range of Scutellaria baicalensis growth environment based on the adaptation data of Scutellaria baicalensis planting parameters, and generate data on the variation range of Scutellaria baicalensis growth environment; Step S52: Based on the data on the range of changes in the growth environment of Scutellaria baicalensis, perform matching processing on the growth and environmental change adaptability of Scutellaria baicalensis to generate Scutellaria baicalensis growth-environmental change adaptability matching data; Step S53: Adjust the precise control parameters for Scutellaria baicalensis plot zoning based on the Scutellaria baicalensis growth-environmental change adaptability matching data, and generate precise control parameter data for Scutellaria baicalensis plot zoning. Step S54: Based on the precise control parameter data of Scutellaria baicalensis plot zoning, perform intelligent control processing of the Scutellaria baicalensis distribution and planting environment to generate intelligent control data of the Scutellaria baicalensis distribution and planting environment.

10. A digital intelligent monitoring system for Scutellaria baicalensis cultivation based on the Internet of Things, characterized in that, For implementing the IoT-based digital intelligent monitoring method for Scutellaria baicalensis cultivation as described in claim 1, the IoT-based digital intelligent monitoring system for Scutellaria baicalensis cultivation includes: The Scutellaria baicalensis sensing and acquisition module is used to collect multi-source Scutellaria baicalensis sensing data through an array of IoT sensors. Based on the multi-source Scutellaria baicalensis sensing data, the module analyzes the plant density and canopy temperature of Scutellaria baicalensis to generate plant density-canopy temperature data. Based on the plant density-canopy temperature data, the module performs multi-dimensional canopy cluster type association classification of Scutellaria baicalensis to generate multi-dimensional canopy cluster type association data. The Scutellaria baicalensis multidimensional confidence analysis module is used to perform multidimensional confidence analysis of Scutellaria baicalensis growth status based on multidimensional crown cluster type association data, and generate multidimensional confidence data of Scutellaria baicalensis growth status. The Scutellaria baicalensis growth status prediction module is used to perform Scutellaria baicalensis growth stage environmental parameter index matching processing based on the multidimensional growth status confidence data of Scutellaria baicalensis, and generate Scutellaria baicalensis growth stage environmental parameter index matching data. The Scutellaria baicalensis environmental parameter matching module is used to perform Scutellaria baicalensis planting parameter fit analysis based on the Scutellaria baicalensis growth stage environmental parameter index matching data and Scutellaria baicalensis growth multidimensional state confidence data, and generate Scutellaria baicalensis planting parameter fit data. The Scutellaria baicalensis planting parameter control module is used to intelligently control the distribution and planting environment of Scutellaria baicalensis based on the adaptability data of Scutellaria baicalensis planting parameters, and generate intelligent control data of the distribution and planting environment of Scutellaria baicalensis.

Images