Gastrodia elata under-forest cultivation decision system and method based on ecological simulation

Abstract

This invention relates to the field of smart agriculture technology, specifically to a decision-making system and method for Gastrodia elata cultivation under forest cover based on ecological simulation. The system includes: a data acquisition module for collecting environmental monitoring signals from the target cultivation area and historical growth data of the target plants; and a niche assessment module for calculating the niche suitability index of each planting unit based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area, in response to the environmental monitoring signals. This invention generates a niche suitability index by calculating the microclimate characteristic difference sequence between adjacent planting units, enabling precise location of specific coordinates of environmental deviations during the decision-making process. This allows the system to identify areas of sudden changes in local temperature and humidity gradients or abnormal soil water potential, improving the accuracy of environmental perception from the plot level to the planting unit level, and providing a reliable data foundation for subsequent differentiated regulation.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture technology, specifically to a decision-making system and method for the cultivation of Gastrodia elata under forest canopy based on ecological simulation. Background Technology

[0002] In the modern ecological cultivation industry of Chinese medicinal herbs, the cultivation of Gastrodia elata under forest cover is the core model for achieving high-quality production of medicinal and edible herbs. Its essence is to simulate the wild ecological niche through microenvironmental regulation, maximizing the accumulation of effective components in the tubers under the constraint of limited forest land resources. However, this dynamic coupling process of environmental simulation and growth metabolism places extremely high demands on spatiotemporal precision, which existing traditional cultivation decision-making systems often cannot handle, mainly due to the following fundamental defects: First, traditional decision-making systems can only monitor macro-meteorology and cannot capture the microclimate characteristics of understory planting units. Since Gastrodia elata is extremely sensitive to the growth environment and requires specific soil moisture and aeration, traditional methods cannot calculate the temperature and humidity gradient, light differences and soil factor diffusion rates between adjacent planting units, resulting in the inability to identify local heat island effects or drought patches. Often, it is only discovered when the plants wilt or rot, missing the best control window. In addition, traditional techniques treat forest land as a homogeneous production space, ignoring the heterogeneity of ecological niches. In reality, due to differences in slope, aspect, and vegetation cover, the suitability of different plots varies greatly. This leads to the need for a one-size-fits-all approach to water and fertilizer application and pest and disease control, which wastes resources and fails to provide precise rejuvenation for weak seedlings, resulting in significant hidden yield reductions. Summary of the Invention

[0003] To achieve the above objectives, the present invention provides the following technical solution: a decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation, comprising: The data acquisition module is used to collect environmental monitoring signals from the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass and tuber morphology indicators from past growth cycles. The niche assessment module is used to calculate the niche suitability index of each planting unit based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area in response to environmental monitoring signals; the niche suitability index reflects the degree of environmental deviation of each planting unit. An anomaly identification module is used to compare and analyze all niche suitability indices to identify each abnormal cultivation unit. The signal generation module is used to determine the ecological regulation trigger signal of the target cultivation area based on the number of abnormal cultivation units and the time persistence characteristics of the niche suitability index of all abnormal cultivation units. The microenvironment regulation module is used to respond to the ecological regulation trigger signal, determine the target microenvironment regulation signal based on the correlation characteristics of the historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of the abnormal cultivation units; and dynamically regulate the target cultivation area with the target microenvironment regulation signal to obtain the optimized cultivation area. The parameter optimization module is used to acquire real-time biometric data of all target plants in the optimized cultivation area. Based on the spatial and temporal distribution characteristics of the real-time biometric data, it constructs matching growth response feature vectors and determines the target optimization parameters of the optimized cultivation area based on the comparison and analysis results of the growth response feature vectors. The strategy execution module is used to process real-time biometric data with target optimization parameters and execute cultivation decision strategies that match the processing results.

[0004] Preferably, the niche suitability index of each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area, including: Collect microclimate characteristic data for each planting unit within the target cultivation area at the current moment; the microclimate characteristic data includes soil moisture gradient, instantaneous air temperature value, and rate of change of canopy transmittance; By comparing the microclimate characteristic data of two adjacent planting units pairwise, calculating the absolute difference and relative rate of change of the characteristic values, a microclimate characteristic difference sequence is obtained. The temporal variation trend of microclimate characteristic data of each planting unit is extracted. Combined with the microclimate characteristic difference sequence, the coupling relationship between the internal characteristic stability of the unit and the characteristic difference of the external neighbor is analyzed, and the niche deviation vector representing environmental pressure is calculated. Spatial neighborhood diffusion simulation was performed on the niche deviation vector, and the cumulative effect of the vector within a continuous time window and the radius of influence on surrounding units were statistically analyzed. The niche suitability index of each planting unit was obtained through weighted fusion processing.

[0005] Preferably, the coupling relationship between the stability of internal characteristics of the analysis unit and the differences in characteristics of external neighbors is analyzed to calculate the niche deviation vector characterizing environmental pressure, including: Extract the microclimate characteristic data of each planting unit within a continuous time window, calculate the ratio of the standard deviation to the range of the characteristic values, and obtain the internal stability index that reflects the degree of environmental fluctuation within the unit. We obtained an external difference index that reflects the degree of separation between the unit and the external environment by weighted summation of the numerical values ​​in the microclimate characteristic difference sequence. Based on the internal stability index and external variability index of all planting units, the global mean of the internal stability index and the global mean of the external variability index are calculated to generate an ideal stable equilibrium point that represents the current best ecological state. The Euclidean distance between the feature point of the current planting unit and the ideal stable equilibrium point is calculated, and the sign is determined by combining the change direction of the differential sequence to obtain the niche deviation vector representing environmental pressure.

[0006] Preferably, a comparative analysis of all niche suitability indices is performed to identify each cultivation aberration unit, including: The ecological niche suitability index of all planting units is compared with the preset ideal ecological niche benchmark value one by one. Planting units with ecological niche suitability index lower than the benchmark value are selected, and the spatial coordinate information of these units is extracted to generate initial deviation unit distribution data. Based on the niche suitability index and initial deviation unit distribution data of each planting unit, the topological distance and exponential gradient difference between each planting unit and its neighboring initial deviation units are calculated to obtain the spatial anomalous clustering degree; whereby the spatial anomalous clustering degree reflects the degree of local environmental deterioration. The trajectory of the niche suitability index change of each unit in the initial deviation unit distribution data within a continuous time window is tracked, and the duration and fluctuation range of the index being lower than the benchmark value are calculated to obtain the persistence deviation coefficient, which characterizes the degree of abnormal stubbornness. By combining the spatial anomalous clustering degree and the continuous deviation coefficient of each planting unit, logical rules are used to filter out the set of units that are spatially continuous and whose deviation coefficient exceeds the preset sensitivity threshold, and finally determine them as cultivation anomalous units.

[0007] Preferably, the ecological regulation triggering signal for the target cultivation area is determined based on the number of anomalous cultivation units and the temporal persistence characteristics of the niche suitability index of all anomalous cultivation units, including: The number of abnormal cultivation units was used as a spatial breadth indicator and the persistence deviation coefficient was used as a temporal depth indicator. They were weighted and fused to obtain a comprehensive pressure index that characterizes the overall ecological pressure accumulation in the region. Based on the stress comprehensive index and the spatial coordinate data of the cultivation abnormal units, the spatial neighborhood of all cultivation abnormal units is traversed, the number of continuously distributed abnormal unit clusters and the maximum coverage radius are counted, and a diffusion risk factor reflecting the spatial connectivity of abnormalities is generated. Based on the statistical distribution characteristics of diffusion risk factors, the average density and dispersion coefficient of all anomalous unit clusters are calculated to generate a dynamic clustering discrimination threshold; whereby the dynamic clustering discrimination threshold reflects the current anomalous clustering pattern. By combining the comprehensive stress index and diffusion risk factor of each abnormal cultivation unit, a risk characteristic sequence is constructed. This sequence is then scanned using a step-by-step threshold rule: the diffusion risk factor is compared with a dynamic clustering discrimination threshold. When the comprehensive stress index exceeds the first preset threshold and the diffusion risk factor is greater than zero, a primary warning signal is generated; when the comprehensive stress index exceeds the second preset threshold and the diffusion risk factor exceeds the dynamic clustering discrimination threshold, a medium-level intervention signal is generated; and when the comprehensive stress index exceeds the third preset threshold, an emergency control signal is generated. Primary warning signals, intermediate intervention signals, and emergency regulation signals are encoded and identified as ecological regulation trigger signals.

[0008] Preferably, the target microenvironment regulation signal is determined based on the correlation characteristics of historical growth data of all planting units in the target cultivation area and the niche suitability index of abnormal cultivation units, including: Based on the level of the ecological regulation trigger signal, the historical niche suitability index fluctuation curve of the corresponding level in the preset historical abnormal response database is matched; the environmental factor correction trajectory accompanying the growth rate rebound in the historical niche suitability index fluctuation curve is extracted to generate the historical best response benchmark template. Based on the time series of the niche suitability index of all planting units, it is aligned with the historical best response benchmark template, and the vertical deviation integral of the current index curve and the historical recovery trajectory on the time axis is calculated to obtain the demand gap parameter characterizing the degree of damage to growth potential. Based on the spatial coordinates of cultivation anomaly units, and superimposed with microclimate characteristic difference sequences, the dominant environmental limiting factors that lead to the decline of the current ecological niche suitability index are identified. Combined with demand gap parameters, factor-gap correlation pairs are constructed. Retrieve the preset physical control equipment capability parameter table for the target cultivation area to obtain the maximum operating power, adjustment accuracy range, and equipment response lag time of the control equipment; Based on the dominant environmental constraint factor type and the magnitude of the demand gap parameter in the factor-gap correlation pair, combined with the equipment response lag time, the running time and intensity level of the control equipment are calculated using linear mapping rules to generate a target microenvironment adjustment signal for each cultivation abnormality unit.

[0009] Preferably, the target cultivation area is dynamically adjusted using the target microenvironment adjustment signal to obtain an optimized cultivation area, including: Protocol parsing is performed on the target microenvironment regulation signal to extract the action command sequence of the control equipment and the theoretical environmental parameter change curves generated by the accompanying actions; combined with the spatial coordinates of the cultivation anomaly unit, the action command sequence is mapped to the specific physical device address to generate a spatiotemporal operation command set containing timestamps and device IDs; The diffusion parameters of environmental factors in the microclimate characteristic data of the target cultivation area are used to correct the change curve of theoretical environmental parameters. Then, the microclimate characteristic data of the target cultivation area is compared with the corrected change curve of theoretical environmental parameters point by point to calculate the dynamic deviation sequence between the actual environmental state and the theoretical target, and obtain the real-time deviation parameters that characterize the lag of equipment execution. Based on real-time deviation parameters and equipment response lag time, an error compensation field reflecting the spatiotemporal diffusion characteristics of environmental factors is constructed using environmental factor diffusion parameters. Feedforward control logic is used to correct the spatiotemporal operation instruction set and generate dynamic compensation adjustment instructions containing lead time or increment. The dynamic compensation and adjustment command is sent to the physical control equipment in the target cultivation area for execution. The real-time ecological niche suitability index is retrieved simultaneously to determine whether the suitability index of abnormal units has risen back to the normal threshold range. Units that have risen to the standard are marked as optimized units. The spatial proportion and continuous distribution status of all optimized units are statistically analyzed. When the proportion of optimized units exceeds the preset standard and the spatial distribution is continuous, the area with continuous distribution is directly marked as the optimized cultivation area.

[0010] Preferably, real-time biometric data of all target plants in the optimized cultivation area are acquired. Based on the spatial and temporal distribution characteristics of the real-time biometric data, matching growth response feature vectors are constructed. Based on the comparative analysis of the growth response feature vectors, the target optimization parameters for the optimized cultivation area are determined, including: Using the spatial vector boundary of the optimized cultivation area as the search range, the plant height growth and leaf chlorophyll content of all target plants in the area at the current moment are collected to generate real-time biometric data. Based on real-time biological characteristic data, the spatial variation function of plant height difference coefficient and chlorophyll content among adjacent plants in the cultivation area is calculated and optimized to generate a spatial distribution characteristic sequence reflecting the uniformity of population growth. Search the historical growth archive of the target cultivation area, extract the historical growth rate benchmark curve corresponding to the current growth stage, combine the absolute value of real-time biological feature data and the rate of change of spatial distribution feature sequence within a continuous time window, calculate the dynamic time curvature distance between the current growth trend and the historical benchmark curve, and generate a time distribution feature sequence that reflects the consistency of the growth trend. The spatial distribution feature sequence and the temporal distribution feature sequence are weighted and fused to construct the current growth response feature vector; Search the preset historical high-yield cultivation archive, obtain the historical growth response feature vectors of historical successful cases and the corresponding cultivation management parameter sets, and perform similarity matching between the current growth response feature vector and the historical growth response feature vectors; When the similarity matching result is greater than the preset matching threshold, the average value of the parameters in the cultivation management parameter set corresponding to the historical successful cases is extracted as the target optimization parameter for the cultivation area.

[0011] Preferably, the real-time biometric data is processed using target optimization parameters, and a cultivation decision-making strategy matching the processing results is executed, including: The theoretical fertilization amount in the target optimization parameters is weighted and fused with the leaf chlorophyll content in real-time biological characteristic data to calculate the actual parameter adjustment amount for the current plant status; The system retrieves a preset table of physical control equipment capacity parameters, maps actual parameter adjustments to equipment operating power and duration, and generates a set of agronomic operation instructions containing equipment IDs and timestamps. The agronomic operation instruction set is sent to the execution mechanism of the optimized cultivation area to drive the operation of physical control equipment to execute the cultivation decision strategy.

[0012] The decision-making method for Gastrodia elata cultivation under forest cover based on ecological simulation is applicable to the aforementioned decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation, including: Collect environmental monitoring signals from the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass and tuber morphology indicators from past growth cycles; In response to environmental monitoring signals, the niche suitability index of each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area; wherein, the niche suitability index reflects the degree of environmental deviation of each planting unit; Comparative analysis of all niche suitability indices was conducted to identify each cultivation aberration unit. Based on the number of abnormal cultivation units and the temporal persistence characteristics of the niche suitability index of all abnormal cultivation units, the ecological regulation triggering signal of the target cultivation area is determined. In response to the ecological regulation trigger signal, the target microenvironment regulation signal is determined based on the correlation characteristics of historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of abnormal cultivation units; the target cultivation area is dynamically regulated by the target microenvironment regulation signal to obtain the optimized cultivation area; Real-time biometric data of all target plants in the optimized cultivation area are obtained. Based on the spatial and temporal distribution characteristics of the real-time biometric data, matching growth response feature vectors are constructed. Based on the comparison and analysis results of the growth response feature vectors, the target optimization parameters of the optimized cultivation area are determined. Real-time biometric data are processed using target optimization parameters, and cultivation decision-making strategies that match the processing results are executed.

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention generates a niche suitability index by calculating the microclimate characteristic difference sequence between adjacent planting units, which can accurately locate the specific coordinates of environmental deviations. This enables the system to identify local temperature and humidity gradient abrupt changes or areas of abnormal soil water potential, improving the accuracy of environmental perception from the plot level to the planting unit level, and providing a reliable data foundation for subsequent differentiated and precise regulation. This invention analyzes the duration and spread trend of abnormal cultivation units, automatically generates ecological regulation trigger signals, and has a certain feedforward prediction capability. This enables the system to intervene in the early stage of growth inhibition by fine-tuning microenvironmental factors, avoiding the waste of resources caused by uniform water and fertilizer application across the entire area, and reducing the risk of growth inhibition caused by environmental stress. This invention integrates the correlation features of historical growth data with the spatiotemporal distribution vector of real-time biological features. By matching the similarity with historical high-yield records, it dynamically derives target optimization parameters. The system maps these parameters into device commands and issues them directly, ensuring that each Gastrodia elata plant receives the most precise supply that matches its current growth stage. This makes the cultivation strategy no longer a fixed empirical value, but an optimal solution that fluctuates with the plant's real-time metabolic state, effectively improving the efficiency of Gastrodia elata biomass accumulation and effective component conversion. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the overall system architecture in one embodiment of the present invention; Figure 2 This is a schematic flowchart of the overall method in one embodiment of the present invention.

[0015] In the diagram: 1. Data acquisition module; 2. Niche assessment module; 3. Anomaly identification module; 4. Signal generation module; 5. Microenvironment regulation module; 6. Parameter optimization module; 7. Strategy execution module. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1, please refer to Figure 1 This invention provides a technical solution: a decision-making system for the cultivation of Gastrodia elata under forests based on ecological simulation, comprising: Data acquisition module 1 is used to collect environmental monitoring signals of the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass and tuber morphology indicators of past growth cycles. Niche assessment module 2 is used to calculate the niche suitability index of each planting unit based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area in response to environmental monitoring signals; wherein, the niche suitability index reflects the degree of environmental deviation of each planting unit; Anomaly identification module 3 is used to compare and analyze all niche suitability indices to identify each abnormal cultivation unit; The signal generation module 4 is used to determine the ecological regulation trigger signal of the target cultivation area based on the number of cultivation anomalous units and the time persistence characteristics of the ecological niche suitability index of all cultivation anomalous units. The microenvironment regulation module 5 is used to respond to the ecological regulation trigger signal, determine the target microenvironment regulation signal based on the correlation characteristics of the historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of the abnormal cultivation units; and dynamically regulate the target cultivation area with the target microenvironment regulation signal to obtain the optimized cultivation area. The parameter optimization module 6 is used to acquire real-time biological characteristic data of all target plants in the optimized cultivation area, construct matching growth response feature vectors based on the spatial and temporal distribution characteristics of the real-time biological characteristic data, and determine the target optimization parameters of the optimized cultivation area based on the comparison and analysis results of the growth response feature vectors. Strategy execution module 7 is used to process real-time biometric data with target optimization parameters and execute cultivation decision strategies that match the processing results.

[0018] It should be noted that environmental monitoring signals specifically refer to the physical parameters collected in real time by IoT sensors deployed in the understory planting area, including soil temperature, soil moisture, air temperature and humidity, light intensity, and carbon dioxide concentration. For example, the volumetric water content percentage data collected by soil moisture sensors buried around the rhizosphere, or the photosynthetically active radiation value collected by light sensors above the canopy. Historical growth data refers to the records of crop phenotypic and yield traits stored in the system database for past complete growth cycles, including plant height, biomass, and tuber morphology indicators. Specifically, plant height refers to the vertical height from the base of the stem to the apical growing point; biomass refers to the fresh and dry weight in grams per plant or per unit area; and tuber morphology indicators include the long diameter, short diameter, thickness, and plumpness grade of the tuber. For example, a data set of data recorded in the previous growth cycle showing that the fresh weight of a single hemp plant was 50 grams, the long diameter of the tuber was 8 centimeters, and the plumpness grade was level one. A planting unit refers to the smallest management grid into which the target cultivation area is spatially divided. It is usually divided into square or rectangular plots with sides of 1 to 2 meters based on the understory terrain or the placement of the mushroom sticks. The difference in microclimate characteristics refers to the gradient rate of change of environmental factors between adjacent planting units. Specifically, it is expressed as the absolute value or relative ratio of the difference in soil moisture, temperature, or light intensity. For example, the soil moisture of unit A1 is 60%, while that of the adjacent unit A2 is only 45%. The difference in moisture gradient between the two is the difference in microclimate characteristics. The niche suitability index is a dimensionless numerical indicator used to quantitatively evaluate the degree to which the environmental conditions of the current planting unit match the optimal growth requirements of Gastrodia elata. This index is derived by calculating the deviation between the current unit's microclimate characteristics and those of historically high-yield units. The value range is usually between 0 and 1, with a value closer to 1 indicating a more suitable environment. An abnormal cultivation unit refers to a planting unit whose niche suitability index is lower than a preset threshold or shows an abnormal downward trend. The system determines this by comparing the index values ​​of all units horizontally. For example, when the average index for the entire field is 0.8, units with an index lower than 0.5 are identified as abnormal cultivation units, which may specifically manifest as specific planting tray areas where root hypoxia is caused by waterlogging. Temporal persistence characteristics refer to the performance of the niche suitability index of abnormal cultivation units over a continuous time dimension. Specifically, this includes the number of days the abnormality persists or the consistency of index fluctuations. For example, if the suitability index of an abnormal unit is below 0.4 for five consecutive days without any signs of recovery, it exhibits a high-risk temporal persistence characteristic. Ecological regulation trigger signals are instruction markers generated by the system based on the number of abnormal units and temporal characteristics. These signals are used to determine whether to activate regulation equipment. For instance, when the proportion of abnormal units exceeds 10% and the duration exceeds 3 days, a high-priority trigger signal is generated to instruct the external shading system to deploy. The correlation characteristics of historical growth data refer to the relationship between historical yield and environmental factors among different planting units. For example, historical data analysis shows that in a unit with a certain slope aspect, soil moisture and biomass are significantly positively correlated, while in another slope aspect, the correlation with light duration is stronger. This correlation pattern is called the correlation characteristics. The target microenvironment regulation signal is a specific set of equipment control parameters, including the percentage of shade net opening, the opening duration of the drip irrigation pipe solenoid valve, and the fan speed. For example, if the system calculates that soil moisture needs to be increased by 5% based on the correlation characteristics, it will generate a regulation signal for drip irrigation for 10 minutes. Optimized cultivation areas refer to regions where the ecological niche suitability index has been significantly improved and the number of abnormal units has decreased after microenvironmental regulation, meaning that environmental parameters have been corrected to a state suitable for the growth of Gastrodia elata. Real-time biometric data refers to plant morphology data acquired in real time during the current growth cycle through image recognition or portable devices, including real-time plant height, leaf area index, and relative chlorophyll content. Spatial distribution characteristics refer to the degree of dispersion or clustering of biometric data in horizontal space, specifically described by the coefficient of variation or standard deviation. For example, if the standard deviation of plant height in a certain area is less than 5 cm, it indicates a spatial distribution characteristic with high growth uniformity. Temporal distribution characteristics refer to the rate of change or cumulative amount of biometric data on the vertical time axis. For example, the cumulative increase in plant height over 7 consecutive days reaches 2 cm, or the daily average biomass accumulation rate during the tuber enlargement period. The growth response feature vector is a multidimensional data set composed of spatial and temporal distribution characteristics, used to characterize the current growth potential of the plant. For example, a vector composed of two feature values, high plant height uniformity and fast daily growth rate, represents a healthy and rapid growth state. The target optimization parameters are specific agronomic operation values ​​derived from the comparative analysis results, including fertilizer type, fertilizer amount, and pesticide concentration. For example, if the system determines that the current stage is a critical period for tuber enlargement and the growth vigor is weak, it will output the target optimization parameter of applying 5 kg of high potassium water-soluble fertilizer per mu. The cultivation decision strategy is the final execution plan, which includes the specific operation time, operation location, and operation content. For example, the strategy is "to spray foliar fertilizer on unit 3 of area B at 8:00 am with a concentration of 0.3%", and the system will directly drive the plant protection drone or irrigation equipment to perform the action accordingly.

[0019] In an optional embodiment, the niche suitability index of each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area, including: Collect microclimate characteristic data for each planting unit within the target cultivation area at the current moment; the microclimate characteristic data includes soil moisture gradient, instantaneous air temperature value, and rate of change of canopy transmittance; By comparing the microclimate characteristic data of two adjacent planting units pairwise, calculating the absolute difference and relative rate of change of the characteristic values, a microclimate characteristic difference sequence is obtained. It should be noted that microclimate characteristic data refers to refined environmental parameters collected at the scale of a single planting unit. This includes not only absolute values ​​but also dynamic change indicators, specifically soil moisture gradients (e.g., the difference in soil moisture at different depths within a unit), instantaneous air temperature values ​​(e.g., 25.6℃ recorded by a sensor at a certain moment), and the rate of change in canopy transmittance (e.g., the rate of change from 50% to 40% transmittance within one hour). These data directly reflect the real-time microenvironmental state of the rhizosphere and canopy of *Gastrodia elata*. The microclimate characteristic difference sequence is a data chain generated by comparing the characteristic data of two spatially adjacent planting units time-by-time. Specifically, it is calculated by extracting the absolute difference in characteristic values ​​between two adjacent units (e.g., the difference between soil moisture of 60% in unit A and 45% in unit B is 15%) and the relative rate of change (e.g., the relative change in temperature, such as a 2℃ increase in unit A and a 1℃ increase in unit B within one hour). These differences are then arranged in chronological order to form a sequence. This sequence intuitively describes the drastic gradient changes in environmental factors between adjacent plots. The temporal variation trend of microclimate characteristic data of each planting unit is extracted. Combined with the microclimate characteristic difference sequence, the coupling relationship between the internal characteristic stability of the unit and the characteristic difference of the external neighbor is analyzed, and the niche deviation vector representing environmental pressure is calculated. It should be noted that the temporal trend refers to the evolution direction of microclimate characteristic data within a single planting unit over a period of time. The system uses continuously collected data to determine whether the environment of the unit is trending towards stability, deterioration, or fluctuation, such as a continuous downward trend in soil moisture over three consecutive days. Coupling analysis refers to combining the characteristic stability within the unit (such as small fluctuations in its own moisture content) with the characteristic differences of its external neighbors (such as large moisture differences with adjacent units) for comprehensive judgment. This is used to determine the source of environmental pressure. For example, when the moisture content within a unit is stable but significantly lower than that of surrounding units, it indicates that the unit has specific water deficit pressure. The niche deviation vector is a set of multi-dimensional indicators generated based on the above coupling analysis. It is used to quantitatively characterize the degree and direction of the current environment of the planting unit deviating from the optimal growth range of Gastrodia elata. Each dimension in the vector corresponds to the magnitude of a type of environmental pressure. For example, a deviation vector may simultaneously contain values ​​for both "soil moisture deficit" and "excessive temperature." The larger the value, the more severe the deviation. This vector is essentially a digital abstraction of the environmental stress state. Spatial neighborhood diffusion simulation was performed on the niche deviation vector, and the cumulative effect of the vector within a continuous time window and the radius of influence on surrounding units were statistically analyzed. The niche suitability index of each planting unit was obtained through weighted fusion processing. It should be noted that spatial neighborhood diffusion simulation refers to simulating the process of environmental pressure propagating and attenuating to surrounding plots on a digital map. The system calculates the range and intensity of the impact of the pressure of a certain anomalous unit on surrounding units. For example, the low temperature pressure of the central unit will have a strong impact on the adjacent units 1 and 2, and a weak impact on the more distant unit 5. The cumulative effect within a continuous time window refers to the total cumulative amount of environmental pressure over a continuous period of time. For example, if a unit is in a low temperature state for 5 consecutive days, its cumulative effect value will be very high. The influence radius refers to the farthest distance that the pressure can reach. The system sets this radius value according to the terrain and obstacles, such as the area within 5 meters of the anomalous unit as the center.

[0020] In an optional embodiment, the coupling relationship between the stability of features within the analysis unit and the differences in features between external neighbors is analyzed to calculate the niche deviation vector characterizing environmental pressure, including: Extract the microclimate characteristic data of each planting unit within a continuous time window, calculate the ratio of the standard deviation to the range of the characteristic values, and obtain the internal stability index that reflects the degree of environmental fluctuation within the unit. It should be noted that the internal stability index is a ratio calculated by statistically analyzing the fluctuations in environmental data of a single planting unit over a continuous period of time. Specifically, it is obtained by dividing the standard deviation and range of the characteristic values. The standard deviation reflects the degree to which the data deviates from the average, and the range reflects the maximum range of data fluctuation. This index is used to measure whether the internal environment of the unit is stable. For example, if the soil moisture of a planting unit is 51%, 52%, and 50.5% for 10 consecutive hours, the values ​​are very close, the calculated standard deviation and range are both small, and the ratio is also small, indicating that the internal environment of the unit is highly stable. Conversely, if the humidity fluctuates drastically between 40% and 70%, the calculated ratio is large, indicating that the internal environment is extremely unstable. We obtained an external difference index that reflects the degree of separation between the unit and the external environment by weighted summation of the numerical values ​​in the microclimate characteristic difference sequence. It should be noted that the external dissimilarity index is the sum obtained by multiplying each value in the microclimate characteristic difference sequence by its corresponding weight coefficient. The weight coefficients are set according to the degree of influence of different environmental factors on the growth of Gastrodia elata. This index is used to quantify the degree of separation between the current unit and its surrounding environment. For example, the system sets the weight of soil moisture to 0.5, temperature to 0.3, and light intensity to 0.2. If the humidity difference between a unit and its neighboring units is 10%, the temperature difference is 3℃, and the difference in light intensity variation rate is 5%, a comprehensive value is obtained after weighted summation. The larger this value, the more significant the difference between the unit and its surrounding environment, indicating that it is in an isolated and abnormal state. Based on the internal stability index and external variability index of all planting units, the global mean of the internal stability index and the global mean of the external variability index are calculated to generate an ideal stable equilibrium point that represents the current best ecological state. It should be noted that the ideal stable equilibrium point is a virtual reference coordinate point, generated by calculating the arithmetic mean of the internal stability index and the external variability index of all planting units. This point represents the theoretically optimal ecological state of the entire cultivation area, that is, the state with the least internal fluctuation and the most harmonious relationship with the external environment. For example, if the average internal stability index of the entire plot is 0.3 and the average external variability index is 0.4, then the point formed by coordinates 0.3 and 0.4 is the ideal stable equilibrium point. Units located at or near this point are considered to be in the optimal growth environment, while units far from this point are under environmental pressure. The Euclidean distance between the feature point of the current planting unit and the ideal stable equilibrium point is calculated, and the sign is determined by combining the change direction of the differential sequence to obtain the niche deviation vector representing environmental pressure. It should be noted that the niche deviation vector is a comprehensive indicator that includes both magnitude and direction. Its value is obtained by measuring the straight-line distance from the characteristic points of the current planting unit to the ideal stable equilibrium point in a two-dimensional coordinate system. The sign is determined based on the changing trend of the microclimate characteristic difference sequence. A positive value indicates excessive or rapid environmental pressure, while a negative value indicates insufficient or slow environmental factors. For example, if the internal stability of the current unit is 0.5 and the external variability is 0.6, and there is a straight-line distance from the ideal equilibrium points of 0.3 and 0.4 in the coordinate system, assuming the calculated distance is 0.28, and the difference sequence shows that environmental factors are continuously deteriorating, then the niche deviation vector is positive 0.28, representing significant positive environmental pressure. If the difference sequence shows that the environment is improving, then it may be negative, representing that the pressure is being released.

[0021] In an alternative embodiment, a comparative analysis of all niche suitability indices is performed to identify individual cultivation anomalous units, including: The ecological niche suitability index of all planting units is compared with the preset ideal ecological niche benchmark value one by one. Planting units with ecological niche suitability index lower than the benchmark value are selected, and the spatial coordinate information of these units is extracted to generate initial deviation unit distribution data. It should be noted that the preset ideal ecological niche benchmark is a fixed scoring standard set by the system to determine whether the environment of the planting unit is in an ideal state. This value is usually derived from historical data statistics on the optimal growth conditions of Gastrodia elata. For example, the system sets the ideal benchmark to 0.85. When the ecological niche suitability index of a planting unit is 0.9, it is judged as normal, while an index of 0.7 is judged as below the benchmark. The initial deviation unit distribution data refers to the data set formed by recording the specific geographical coordinates of all planting units below the benchmark after filtering them out. For example, the system marks three planting units numbered A1, B3, and C5 on the electronic map and records their latitude and longitude coordinates or grid numbers. The set of these coordinate points constitutes the initial deviation unit distribution data, which intuitively shows the initial location of the abnormal points. Based on the niche suitability index and initial deviation unit distribution data of each planting unit, the topological distance and exponential gradient difference between each planting unit and its neighboring initial deviation units are calculated to obtain the spatial anomalous clustering degree; whereby the spatial anomalous clustering degree reflects the degree of local environmental deterioration. It should be noted that topological distance refers to the number of connected steps between the current planting unit and its initial deviation units in the spatial grid structure, rather than the linear geometric distance. It reflects the spatial spread and adjacency relationship of anomalies. For example, if a normal unit is adjacent to an anomalous unit, the topological distance between them is 1; if there is a normal unit in between, the topological distance is 2. The exponential gradient difference refers to the difference between the niche suitability index of the current unit and the index of the surrounding anomalous units. For example, if the index of the current unit is 0.8 and the average index of the surrounding anomalous units is 0.6, the difference of 0.2 is the exponential gradient difference. Spatial anomaly clustering is a value calculated by combining topological distance and exponential gradient difference, used to describe the severity and concentration of environmental degradation in a local area. For example, when a unit is surrounded by multiple anomalous neighbors (small topological distance) and has a large difference in exponent (large gradient difference), the calculated spatial anomaly clustering value will be very high, indicating that a serious environmental degradation patch is forming in the area. The trajectory of the niche suitability index change of each unit in the initial deviation unit distribution data within a continuous time window is tracked, and the duration and fluctuation range of the index being lower than the benchmark value are calculated to obtain the persistence deviation coefficient, which characterizes the degree of abnormal stubbornness. It should be noted that the niche suitability index change trajectory refers to the index value change curve of a certain initial deviation unit over a continuous period of time; duration refers to the number of days or hours that the unit's index is continuously below the benchmark value; and fluctuation range refers to the range of fluctuation of the index within this duration. The persistence deviation coefficient is an indicator calculated by combining the duration and fluctuation range, used to measure the persistence of the anomaly; for example, if a unit's index is below the benchmark value for 5 consecutive days and the daily value fluctuates slightly around 0.6, it indicates that the anomaly is very persistent, and the calculated persistence deviation coefficient will be high; conversely, if the index only occasionally falls below the benchmark value, the coefficient will be low. By combining the spatial abnormal clustering degree and the continuous deviation coefficient of each planting unit, logical rules are used to filter out the set of units that are spatially continuous and whose deviation coefficient exceeds the preset sensitivity threshold, and finally determine them as abnormal cultivation units. It should be noted that logical rules refer to a set of screening conditions set internally by the system to accurately identify the target that truly needs to be processed from numerous candidate units; preset sensitivity thresholds are critical values ​​set for the persistent deviation coefficient, and only those exceeding this value are considered valid anomalies; for example, the system sets the logical rules as follows: the spatial anomaly clustering value must be greater than 10, and the persistent deviation coefficient must be greater than 0.5. The final determined cultivation anomaly unit is a set of units that simultaneously satisfy the characteristics of spatial continuous distribution and high persistence; for example, the three units D1, D2, and D3 in area D are spatially connected (spatial continuous distribution), and their persistent deviation coefficients all exceed 0.5. Based on this, the system determines the set of these three units as a cultivation anomaly unit and generates a red alert area.

[0022] In an optional embodiment, an ecological regulation trigger signal for the target cultivation area is determined based on the number of anomalous cultivation units and the temporal persistence characteristics of the niche suitability index of all anomalous cultivation units, including: The number of abnormal cultivation units was used as a spatial breadth indicator and the persistence deviation coefficient was used as a temporal depth indicator. They were weighted and fused to obtain a comprehensive pressure index that characterizes the overall ecological pressure accumulation in the region. It should be noted that the spatial breadth index is a quantitative parameter used to measure the spatial extent of anomalies. In this system, it is directly represented by the number of anomalous cultivation units. It describes the impact range on a "surface" scale, i.e., how many planting plots simultaneously experienced problems. The temporal depth index is a quantitative parameter used to measure the duration and persistence of anomalies over time. In this system, it is represented by the persistence deviation coefficient. It describes the cumulative effect on a "line" scale, i.e., how long the problem lasted and whether it recurred. The comprehensive stress index is a weighted comprehensive score used to measure the total ecological stress faced by the entire target cultivation area. During calculation, the spatial breadth represented by the number of anomalous units and the temporal persistence depth represented by the persistence deviation coefficient are combined. For example, assuming there are 50 anomalous units and the persistence deviation coefficient is as high as 0.9, the comprehensive stress index obtained after weighted fusion may be 0.85. The higher the value, the greater the overall ecological risk faced by the area. Based on the stress comprehensive index and the spatial coordinate data of the cultivation abnormal units, the spatial neighborhood of all cultivation abnormal units is traversed, the number of continuously distributed abnormal unit clusters and the maximum coverage radius are counted, and a diffusion risk factor reflecting the spatial connectivity of abnormalities is generated. It's important to note that an anomalous unit cluster refers to a collection of interconnected and continuously distributed anomalous units in spatial geography, rather than scattered isolated points. It reflects whether the anomalous area has formed patches or bands of deterioration. For example, on an electronic map, if units A1, A2, and A3 are closely adjacent and all identified as anomalous, they constitute an anomalous unit cluster containing three members. Conversely, if unit B5 is anomalous but its neighbors are normal, it is an isolated point and does not belong to any cluster. The system identifies these clusters to determine whether environmental deterioration is contagious and prone to spread. The diffusion risk factor is an indicator calculated based on the spatial distribution of anomalous units, used to determine whether the anomalous situation will spread to the surrounding area. Specifically, it is generated by statistically analyzing the number of connected anomalous unit clusters and the maximum radius of their coverage. For example, if the system detects three continuously distributed anomalous unit clusters, with the largest cluster spreading 5 meters outward from its center, the diffusion risk factor generated based on these spatial coordinates is 4.2. A higher value indicates a higher risk of the anomalous area becoming a contiguous area. Based on the statistical distribution characteristics of diffusion risk factors, the average density and dispersion coefficient of all anomalous unit clusters are calculated to generate a dynamic clustering discrimination threshold; whereby the dynamic clustering discrimination threshold reflects the current anomalous clustering pattern. It should be noted that statistical distribution characteristics refer to the numerical distribution pattern and regularity of a set of data, used to describe whether the data is clustered together or dispersed, and the degree of uniformity of distribution; average compactness is an indicator that measures how close the units within an anomalous cluster are, calculated by the average distance between all pairs of units within the cluster; the coefficient of dispersion is a relative indicator used to measure the degree of data fluctuation or dispersion, eliminating the influence of dimensions, and used to determine whether the size of the anomalous clusters is uniform; the dynamic clustering discrimination threshold is a critical value that changes with the current anomalous distribution pattern, used to define whether anomalous units are loosely distributed or tightly clustered, and is obtained by calculating the average compactness and coefficient of dispersion of all anomalous unit clusters; for example, if the average distance between units in all current anomalous clusters is very close, the calculated average compactness is 0.8, the coefficient of dispersion is 0.2, and the generated dynamic clustering discrimination threshold is 0.5, meaning that as long as the compactness of the anomalous cluster exceeds 0.5, it is considered a high-risk cluster; By combining the comprehensive stress index and diffusion risk factor of each abnormal cultivation unit, a risk characteristic sequence is constructed. This sequence is then scanned using a step-by-step threshold rule: the diffusion risk factor is compared with a dynamic clustering discrimination threshold. When the comprehensive stress index exceeds the first preset threshold and the diffusion risk factor is greater than zero, a primary warning signal is generated; when the comprehensive stress index exceeds the second preset threshold and the diffusion risk factor exceeds the dynamic clustering discrimination threshold, a medium-level intervention signal is generated; and when the comprehensive stress index exceeds the third preset threshold, an emergency control signal is generated. It should be noted that the tiered threshold rule is a hierarchical judgment logic. It generates signals by comparing the comprehensive pressure index with three different preset thresholds and diffusion risk factors layer by layer. For example, if the first preset threshold is set to 0.6, the second to 0.8, and the third to 0.95, when the comprehensive pressure index of a certain area is 0.7 and the diffusion risk factor is greater than 0, a primary warning signal is triggered; when the index rises to 0.85 and the diffusion risk factor exceeds the dynamic clustering discrimination threshold of 0.5, a medium-level intervention signal is triggered; and when the index reaches 0.98, an emergency control signal is directly triggered. Primary early warning signals, intermediate intervention signals, and emergency control signals are encoded and identified as ecological control trigger signals. It should be noted that the ecological regulation trigger signal is to convert the above judgment results into machine-recognizable instruction codes, usually using different numbers or characters to represent different levels of urgency; for example, the primary warning signal is encoded as the number 1, which means that only monitoring is required; the intermediate intervention signal is encoded as the number 2, which means that the shade net needs to be turned on; and the emergency regulation signal is encoded as the number 3, which means that the sprinkler and fan system needs to be started immediately. The system directly calls the corresponding equipment control program based on these codes.

[0023] In an optional embodiment, the target microenvironment regulation signal is determined based on the correlation characteristics of historical growth data of all planting units in the target cultivation area and the niche suitability index of abnormal cultivation units, including: Based on the level of the ecological regulation trigger signal, the historical niche suitability index fluctuation curve of the corresponding level in the preset historical abnormal response database is matched; the environmental factor correction trajectory accompanying the growth rate rebound in the historical niche suitability index fluctuation curve is extracted to generate the historical best response benchmark template. It should be noted that the historical anomaly response database is a pre-established database used to store various environmental anomalies that have occurred in past planting cycles and their corresponding niche suitability index change curves. For example, the database records the complete process data of an index drop caused by high temperature and drought in a certain plot in the summer of 2022, and the subsequent rebound of the index through irrigation measures. These historical curves serve as reference standards to guide current regulation. The historical best response benchmark template is a standardized correction trajectory extracted from the historical anomaly response database, specifically referring to environmental factor change paths that are accompanied by a significant rebound in crop growth rate. For example, the system extracts a specific trajectory of "soil moisture increasing from 40% to 60% accompanied by a 2°C drop in temperature," defining it as the best recovery template for this type of anomaly, representing the most effective direction of environmental correction. Based on the time series of the niche suitability index of all planting units, it is aligned with the historical best response benchmark template, and the vertical deviation integral of the current index curve and the historical recovery trajectory on the time axis is calculated to obtain the demand gap parameter characterizing the degree of damage to growth potential. It should be noted that the demand gap parameter is a value obtained by calculating the cumulative vertical deviation of the current niche suitability index curve from the historical best response benchmark template over time. It is used to quantify the severity of the damage to growth potential. For example, the difference between the current curve and the historical template at the same time point is subtracted, and the difference is accumulated over 24 consecutive hours to obtain a value such as 0.35. The larger this value is, the greater the gap between the current environment and the optimal recovery path, and the more severe the damage to crop growth potential. Based on the spatial coordinates of cultivation anomaly units, and superimposed with microclimate characteristic difference sequences, the dominant environmental limiting factors that lead to the decline of the current ecological niche suitability index are identified. Combined with demand gap parameters, factor-gap correlation pairs are constructed. It should be noted that the dominant environmental limiting factor is the most critical environmental element leading to the decline in the index, identified by analyzing the specific spatial location of the abnormal cultivation unit and the difference sequence of its surrounding microclimate characteristics. For example, in an abnormal unit, the system finds that its soil moisture is 20% lower than its neighbors, while the differences in light and temperature are relatively small, thus determining that insufficient soil moisture is the dominant limiting factor causing the current anomaly. The factor-gap correlation pair is a data combination that binds the identified dominant environmental limiting factor with the calculated demand gap parameter to clarify the correspondence between "what is lacking" and "how much is lacking". For example, the system generates a data pair with the content "soil moisture -0.35", indicating that the current main limiting factor is soil moisture and the gap degree is 0.35, which provides a direct basis for subsequent precise regulation. Retrieve the preset physical control equipment capability parameter table for the target cultivation area to obtain the maximum operating power, adjustment accuracy range, and equipment response lag time of the control equipment; It should be noted that the physical control equipment capability parameter table is a pre-entered hardware performance list of the system, which records in detail the physical limits and accuracy indicators of all actuators in the field, including the maximum operating power, minimum adjustment accuracy, and response lag time from the issuance of the command to the action of the equipment; for example, the table records that the maximum flow rate of a certain type of drip irrigation pump is 5 cubic meters per hour, the adjustment accuracy is 5%, and there is a lag time of 10 seconds from power-on to water discharge. These parameters limit the boundaries of the generation of control commands; Based on the dominant environmental constraint factor type and the magnitude of the demand gap parameter in the factor-gap correlation pair, combined with the equipment response lag time, the running time and intensity level of the control equipment are calculated using linear mapping rules to generate a target microenvironmental regulation signal for each abnormal cultivation unit. It should be noted that the linear mapping rule is a computational logic that converts demand gap parameters into specific equipment action instructions. It directly calculates the operating intensity and duration of the equipment according to the size of the gap, and deducts the equipment response lag time. For example, when the demand gap parameter is 0.35, the mapping rule calculates that the intensity of the drip irrigation system needs to be turned on is 80%, and the duration is 25 minutes. Taking into account the 10-second equipment start-up lag, the final result is a target microenvironment adjustment signal of "high-intensity drip irrigation for 25 minutes after a 10-second delay".

[0024] In an optional embodiment, the target cultivation area is dynamically adjusted using a target microenvironment adjustment signal to obtain an optimized cultivation area, including: Protocol parsing is performed on the target microenvironment regulation signal to extract the action command sequence of the control equipment and the theoretical environmental parameter change curves generated by the accompanying actions; combined with the spatial coordinates of the cultivation anomaly unit, the action command sequence is mapped to the specific physical device address to generate a spatiotemporal operation command set containing timestamps and device IDs; It should be noted that protocol parsing refers to the system breaking down and translating the received target microenvironment adjustment signal according to predetermined communication rules, extracting the specific equipment action steps and the theoretically expected changes in environmental parameters. For example, after receiving an adjustment signal, the system extracts the action command "open the shade net to 50% opening" and the theoretically expected decrease in light intensity from 8000 lx to 4000 lx. The spatiotemporal operation instruction set is an executable command queue generated by binding abstract action commands with specific physical locations and time points. For example, combining the spatial coordinates of the cultivation anomaly unit, the system maps the instruction "turn on sprinkler irrigation" to the specific "Solenoid Valve No. 3 in Area A" and adds a timestamp of "10:00 AM", ultimately generating a specific instruction containing the device ID, action parameters, and timestamp. The diffusion parameters of environmental factors in the microclimate characteristic data of the target cultivation area are used to correct the change curve of theoretical environmental parameters. Then, the microclimate characteristic data of the target cultivation area is compared with the corrected change curve of theoretical environmental parameters point by point to calculate the dynamic deviation sequence between the actual environmental state and the theoretical target, and obtain the real-time deviation parameters that characterize the lag of equipment execution. It should be noted that environmental factor diffusion parameters are physical property parameters describing the speed and range of environmental elements (such as moisture and temperature) propagation in soil or air, used to correct theoretical variation curves. For example, water infiltration is fast in sandy soil, so the diffusion parameter is set to 0.5; while infiltration is slow in clay, so the diffusion parameter is set to 0.2. The system uses this parameter to adjust the theoretical humidity variation curve to better match the actual diffusion speed. The dynamic deviation sequence is a chain of differences obtained by comparing the actual monitored environmental data with the corrected theoretical target value time by time, used to reflect the gap between the equipment's performance and expectations. For example, the theoretical target is for soil moisture to reach 60% at 10:10 AM, but the actual monitoring shows only 55%, resulting in a negative 5% deviation value. At 10:20 AM, the theoretical value is 65% and the actual value is 62%, resulting in a negative 3% deviation value. This sequence of deviation values ​​arranged by time is the dynamic deviation sequence. The real-time deviation parameter is a comprehensive index calculated based on the dynamic deviation sequence, used to quantify the degree of lag in equipment execution. For example, if the system statistics show that the deviation value exceeds 5% for three consecutive time points, the calculated real-time deviation parameter is 0.15. The larger this value, the less the equipment can keep up with the changing environmental requirements. Based on real-time deviation parameters and equipment response lag time, an error compensation field reflecting the spatiotemporal diffusion characteristics of environmental factors is constructed using environmental factor diffusion parameters. Feedforward control logic is used to correct the spatiotemporal operation instruction set and generate dynamic compensation adjustment instructions containing lead time or increment. It should be noted that the error compensation field is a virtual field model constructed using environmental factor diffusion parameters and equipment response lag time. This model is used to predict the error distribution at future moments and calculate the compensation amount. For example, based on the water flow diffusion velocity and the 10-second lag time required for the water pump to start, the system constructs a field model that predicts the downstream unit will still be short of water within the next 5 minutes. This generates a feedforward control command containing either "start 5 seconds earlier" or "increase the spray volume by 10%." The dynamic compensation adjustment command is the final execution command after correction by the error compensation field, containing the advance amount or additional increment added to offset the lag. For example, the original command is 10 minutes of irrigation, but the system calculates based on the error compensation field that an additional 2 minutes of compensation is needed to achieve the target, resulting in a final dynamic compensation adjustment command of "12 minutes of irrigation." The dynamic compensation and adjustment command is sent to the physical control equipment in the target cultivation area for execution. The real-time ecological niche suitability index is retrieved simultaneously to determine whether the suitability index of abnormal units has risen back to the normal threshold range. Units that have risen to the standard are marked as optimized units. It should be noted that an optimized unit refers to a planting unit whose niche suitability index has recovered from an abnormal state to a normal range after regulation. For example, if a unit's suitability index was previously only 0.5, but after sprinkler irrigation regulation it recovered to 0.85 (above the normal threshold of 0.8), the system will mark this unit as an optimized unit. Statistically analyze the spatial proportion and continuous distribution status of all optimized units. When the proportion of optimized units exceeds the preset standard and the spatial distribution is continuous, the area with the continuous distribution is directly marked as the optimized cultivation area. It should be noted that an optimized cultivation area refers to a plot of land composed of continuously distributed optimized units, and the proportion of these units reaches a preset standard. For example, if the system detects that there are 10 consecutive units in area B that are marked as optimized units, and these 10 units account for more than 80% of the total area of ​​area B and are spatially connected, then area B will be directly marked as an optimized cultivation area.

[0025] In an optional embodiment, real-time biometric data of all target plants in the optimized cultivation area are acquired. Based on the spatial and temporal distribution characteristics of the real-time biometric data, matching growth response feature vectors are constructed. Based on the comparison and analysis results of the growth response feature vectors, the target optimization parameters for the optimized cultivation area are determined, including: Using the spatial vector boundary of the optimized cultivation area as the search range, the plant height growth and leaf chlorophyll content of all target plants in the area at the current moment are collected to generate real-time biometric data. It should be noted that real-time biometric data refers to specific indicator values ​​that reflect the current physiological state of plants, collected in real time within the optimized cultivation area. These mainly include plant height growth and leaf chlorophyll content. For example, if the system collects data at 10:00 AM on plant A1 within the optimized area, its plant height has increased by 2.5 cm in the past 24 hours, and its leaf chlorophyll content is 45 SPAD, these specific values ​​constitute the real-time biometric data. Based on real-time biological characteristic data, the spatial variation function of plant height difference coefficient and chlorophyll content among adjacent plants in the cultivation area is calculated and optimized to generate a spatial distribution characteristic sequence reflecting the uniformity of population growth. It should be noted that the spatial distribution characteristic sequence is a set of data obtained by calculating the growth differences between adjacent plants within a region. It is used to describe the uniformity of population growth, specifically through the plant height difference coefficient and the spatial variation function of chlorophyll content. The plant height difference coefficient reflects the dispersion of the height of adjacent plants, while the spatial variation function reflects the spatial continuity of chlorophyll. For example, if the calculation shows that the plant height difference coefficient between adjacent plants in the optimized region is only 0.1 and the spatial variation function value of chlorophyll content is 0.2, it indicates that the plant growth is very uniform. The resulting set of numerical sequences representing high uniformity is the spatial distribution characteristic sequence. Conversely, if the difference coefficient reaches 0.5, the sequence values ​​will increase significantly, reflecting uneven growth. Search the historical growth archive of the target cultivation area, extract the historical growth rate benchmark curve corresponding to the current growth stage, combine the absolute value of real-time biological feature data and the rate of change of spatial distribution feature sequence within a continuous time window, calculate the dynamic time curvature distance between the current growth trend and the historical benchmark curve, and generate a time distribution feature sequence that reflects the consistency of the growth trend. It should be noted that the historical growth archive is a database storing basic data on all past growth cycles of the target cultivation area, including growth rate records at different stages; the historical growth rate baseline curve is a standard growth trajectory extracted from this database for a specific time period; the dynamic time curvature distance is a calculation method that measures the morphological similarity between the current growth trend and the historical standard curve. It calculates the difference by non-linearly aligning the time axes of the two curves, and is unaffected by minor stretching or shrinking on the time axis. It is specifically used to compare whether the trends of the two curves are consistent. For example, comparing the current plant height growth curve with the historical high-yield curve of the same period, the calculated curvature distance is 0.15. The smaller the value, the closer the current trend is to the historical best trend; if the curvature distance exceeds 0.3, it indicates that the growth trend has deviated significantly. The spatial distribution feature sequence and the temporal distribution feature sequence are weighted and fused to construct the current growth response feature vector; It should be noted that the growth response feature vector is a comprehensive index that combines the spatial distribution feature sequence reflecting spatial evenness and the temporal distribution feature sequence reflecting temporal trend consistency according to their respective importance weights. The weights here are fixed proportions that are pre-set based on the sensitivity of different growth stages to evenness or trend. For example, if the spatial features are given a weight of 60% and the temporal features a weight of 40%, after weighted fusion, a vector value containing two dimensions, such as 0.85 and 0.88, is generated. This vector fully represents the current growth response state of the crop. Search the preset historical high-yield cultivation archive, obtain the historical growth response feature vectors of historical successful cases and the corresponding cultivation management parameter sets, and perform similarity matching between the current growth response feature vector and the historical growth response feature vectors; When the similarity matching result is greater than the preset matching threshold, the average value of the parameters in the cultivation management parameter set corresponding to the historical successful cases is extracted as the target optimization parameter for the cultivation area. It's important to note that the historical high-yield cultivation archive is a high-level database distinct from the basic archive. It specifically stores data on successful historical cases of achieving high yields, including the corresponding growth response feature vectors and the cultivation management parameter sets at the time. Similarity matching compares the currently generated growth response feature vector with historical vectors in this database, calculating their closeness in multidimensional space. For example, if the system retrieves a high-yield case from the same period in 2022, with historical growth response feature vectors of 0.9 and 0.91, the similarity between the current vector and the historical vector is calculated to be as high as 0.92, exceeding the preset matching threshold of 0.9, thus indicating a successful match. The target optimization parameters are the average values ​​of cultivation management parameters extracted from historical successful cases after a successful similarity match. These parameters include specific physical indicators such as irrigation amount, fertilization amount, and light regulation duration. For example, if the matched historical successful case had an irrigation amount of 25 mm and a fertilization amount of 15 kg per hectare, the system extracts the average of these parameters and directly uses them as the target optimization parameters for the current optimized cultivation area, i.e., 25 mm of irrigation and 15 kg per hectare of fertilization.

[0026] In an optional embodiment, real-time biometric data is processed with target optimization parameters, and a cultivation decision-making strategy matching the processing results is executed, including: The theoretical fertilization amount in the target optimization parameters is weighted and fused with the leaf chlorophyll content in real-time biological characteristic data to calculate the actual parameter adjustment amount for the current plant status; It should be noted that the actual parameter adjustment amount is the final execution value obtained by comprehensively calculating the theoretical fertilizer amount in the target optimization parameters and the real-time monitored leaf chlorophyll content. It is used to correct the deviation between the theoretical value and the actual needs of the plant. For example, the theoretical fertilizer amount in the target optimization parameters is 10 kg per hectare, but real-time monitoring shows that the leaf chlorophyll content is too high, indicating that the plant is nutritious. After weighted calculation (such as chlorophyll accounting for 40%), the system will adjust the actual fertilizer amount to 8 kg per hectare to achieve precision fertilization. Retrieve the preset physical control equipment capacity parameter table, map the actual parameter adjustment amount to the equipment operating power and operation time, and generate an agronomic operation instruction set containing equipment ID and timestamp; It should be noted that equipment operating power and operation time are physical indicators that convert abstract parameter adjustments into specific equipment actions. Operating power determines the intensity of the equipment's work, while operation time determines the duration of the work. For example, if the system calculates that 2 kg of fertilizer needs to be added, based on the equipment capacity parameter table, this is mapped to "operating power 60%" and "operation time 20 minutes," ensuring the equipment operates efficiently within a safe range. The agronomic operation instruction set is a structured command queue containing specific equipment identification, action parameters, and execution time points, used to directly command hardware equipment actions. For example, the system generates an instruction with the content "Equipment ID: Fertilizer Pump No. 3 in Area A, Operating Power: 60%, Operation Time: 20 minutes, Timestamp: 14:30:00," which clearly specifies which equipment is operating, at what time, and in what state. The agronomic operation instruction set is sent to the execution mechanism in the optimized cultivation area to drive the operation of physical control equipment to execute cultivation decision-making strategies; It should be noted that the actuator refers to the hardware device that actually performs physical actions in the field, such as solenoid valves, motors, and fans. After receiving a set of instructions, they generate mechanical actions to change the environment. For example, when the instruction set is issued, the motor inside fertilizer pump No. 3 in area A starts, driving the blades to rotate and inject fertilizer solution into the pipeline. This physical action is completed by the actuator. The cultivation decision strategy refers to a set of logical rules that the system automatically generates and executes agronomic operations based on the current plant status and environmental data, covering the entire process from data calculation to equipment action. For example, if the strategy stipulates that fertilization should be reduced when the chlorophyll content is higher than 50 SPAD, the system automatically completes the calculation, generates instructions, and drives the equipment to execute them. This entire set of automated logic is the cultivation decision strategy.

[0027] Example 2, please refer to Figure 2 This invention provides a technical solution: a decision-making method for Gastrodia elata cultivation under forest based on ecological simulation, applicable to the aforementioned decision-making system for Gastrodia elata cultivation under forest based on ecological simulation, comprising: S1. Collect environmental monitoring signals from the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass, and tuber morphology indicators from past growth cycles. S2. In response to environmental monitoring signals, the niche suitability index of each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area; wherein, the niche suitability index reflects the degree of environmental deviation of each planting unit. S3. Compare and analyze all niche suitability indices to identify each cultivation aberration unit; S4. Based on the number of abnormal cultivation units and the time persistence characteristics of the niche suitability index of all abnormal cultivation units, determine the ecological regulation trigger signal of the target cultivation area. S5. In response to the ecological regulation trigger signal, determine the target microenvironment regulation signal based on the correlation characteristics of the historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of the abnormal cultivation units; use the target microenvironment regulation signal to dynamically regulate the target cultivation area to obtain the optimized cultivation area. S6. Obtain real-time biometric data of all target plants in the optimized cultivation area. Based on the spatial and temporal distribution characteristics of the real-time biometric data, construct matching growth response feature vectors. Based on the comparison and analysis results of the growth response feature vectors, determine the target optimization parameters of the optimized cultivation area. S7. Process real-time biometric data using target optimization parameters and execute cultivation decision-making strategies that match the processing results.

[0028] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation, characterized in that, include: The data acquisition module is used to collect environmental monitoring signals from the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass and tuber morphology indicators from past growth cycles. The niche assessment module is used to calculate the niche suitability index of each planting unit based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area in response to environmental monitoring signals; the niche suitability index reflects the degree of environmental deviation of each planting unit. An anomaly identification module is used to compare and analyze all niche suitability indices to identify each abnormal cultivation unit. The signal generation module is used to determine the ecological regulation trigger signal of the target cultivation area based on the number of abnormal cultivation units and the time persistence characteristics of the niche suitability index of all abnormal cultivation units. The microenvironment regulation module is used to respond to the ecological regulation trigger signal, determine the target microenvironment regulation signal based on the correlation characteristics of the historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of the abnormal cultivation units; and dynamically regulate the target cultivation area with the target microenvironment regulation signal to obtain the optimized cultivation area. The parameter optimization module is used to acquire real-time biometric data of all target plants in the optimized cultivation area. Based on the spatial and temporal distribution characteristics of the real-time biometric data, it constructs matching growth response feature vectors and determines the target optimization parameters of the optimized cultivation area based on the comparison and analysis results of the growth response feature vectors. The strategy execution module is used to process real-time biometric data with target optimization parameters and execute cultivation decision strategies that match the processing results.

2. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 1, characterized in that, The niche suitability index for each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area, including: Collect microclimate characteristic data for each planting unit within the target cultivation area at the current moment; the microclimate characteristic data includes soil moisture gradient, instantaneous air temperature value, and rate of change of canopy transmittance; By comparing the microclimate characteristic data of two adjacent planting units pairwise, calculating the absolute difference and relative rate of change of the characteristic values, a microclimate characteristic difference sequence is obtained. The temporal variation trend of microclimate characteristic data of each planting unit is extracted. Combined with the microclimate characteristic difference sequence, the coupling relationship between the internal characteristic stability of the unit and the characteristic difference of the external neighbor is analyzed, and the niche deviation vector representing environmental pressure is calculated. Spatial neighborhood diffusion simulation was performed on the niche deviation vector, and the cumulative effect of the vector within a continuous time window and the radius of influence on surrounding units were statistically analyzed. The niche suitability index of each planting unit was obtained through weighted fusion processing.

3. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 2, characterized in that, The coupling relationship between the stability of features within an analytical unit and the differences in features between its external neighbors is analyzed, and the niche deviation vector characterizing environmental pressure is calculated, including: Extract the microclimate characteristic data of each planting unit within a continuous time window, calculate the ratio of the standard deviation to the range of the characteristic values, and obtain the internal stability index that reflects the degree of environmental fluctuation within the unit. We obtained an external difference index that reflects the degree of separation between the unit and the external environment by weighted summation of the numerical values ​​in the microclimate characteristic difference sequence. Based on the internal stability index and external variability index of all planting units, the global mean of the internal stability index and the global mean of the external variability index are calculated to generate an ideal stable equilibrium point that represents the current best ecological state. The Euclidean distance between the feature point of the current planting unit and the ideal stable equilibrium point is calculated, and the sign is determined by combining the change direction of the differential sequence to obtain the niche deviation vector representing environmental pressure.

4. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 3, characterized in that, A comparative analysis of all niche suitability indices was conducted to identify individual cultivation aberration units, including: The ecological niche suitability index of all planting units is compared with the preset ideal ecological niche benchmark value one by one. Planting units with ecological niche suitability index lower than the benchmark value are selected, and the spatial coordinate information of these units is extracted to generate initial deviation unit distribution data. Based on the niche suitability index and initial deviation unit distribution data of each planting unit, the topological distance and exponential gradient difference between each planting unit and its neighboring initial deviation units are calculated to obtain the spatial anomalous clustering degree; whereby the spatial anomalous clustering degree reflects the degree of local environmental deterioration. The trajectory of the niche suitability index change of each unit in the initial deviation unit distribution data within a continuous time window is tracked, and the duration and fluctuation range of the index being lower than the benchmark value are calculated to obtain the persistence deviation coefficient, which characterizes the degree of abnormal stubbornness. By combining the spatial anomalous clustering degree and the continuous deviation coefficient of each planting unit, logical rules are used to filter out the set of units that are spatially continuous and whose deviation coefficient exceeds the preset sensitivity threshold, and finally determine them as cultivation anomalous units.

5. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 4, characterized in that, Based on the number of anomalous cultivation units and the temporal persistence characteristics of the niche suitability index of all anomalous cultivation units, ecological regulation trigger signals for the target cultivation area are determined, including: The number of abnormal cultivation units was used as a spatial breadth indicator and the persistence deviation coefficient was used as a temporal depth indicator. They were weighted and fused to obtain a comprehensive pressure index that characterizes the overall ecological pressure accumulation in the region. Based on the stress comprehensive index and the spatial coordinate data of the cultivation abnormal units, the spatial neighborhood of all cultivation abnormal units is traversed, the number of continuously distributed abnormal unit clusters and the maximum coverage radius are counted, and a diffusion risk factor reflecting the spatial connectivity of abnormalities is generated. Based on the statistical distribution characteristics of diffusion risk factors, the average density and dispersion coefficient of all anomalous unit clusters are calculated to generate a dynamic clustering discrimination threshold; whereby the dynamic clustering discrimination threshold reflects the current anomalous clustering pattern. By combining the comprehensive stress index and diffusion risk factor of each abnormal cultivation unit, a risk characteristic sequence is constructed. This sequence is then scanned using a step-by-step threshold rule: the diffusion risk factor is compared with a dynamic clustering discrimination threshold. When the comprehensive stress index exceeds the first preset threshold and the diffusion risk factor is greater than zero, a primary warning signal is generated; when the comprehensive stress index exceeds the second preset threshold and the diffusion risk factor exceeds the dynamic clustering discrimination threshold, a medium-level intervention signal is generated; and when the comprehensive stress index exceeds the third preset threshold, an emergency control signal is generated. Primary warning signals, intermediate intervention signals, and emergency regulation signals are encoded and identified as ecological regulation trigger signals.

6. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 5, characterized in that, Based on the correlation characteristics of historical growth data of all planting units in the target cultivation area and the niche suitability index of abnormal cultivation units, the target microenvironment regulation signals are determined, including: Based on the level of the ecological regulation trigger signal, the historical niche suitability index fluctuation curve of the corresponding level in the preset historical abnormal response database is matched; the environmental factor correction trajectory accompanying the growth rate rebound in the historical niche suitability index fluctuation curve is extracted to generate the historical best response benchmark template. Based on the time series of the niche suitability index of all planting units, it is aligned with the historical best response benchmark template, and the vertical deviation integral of the current index curve and the historical recovery trajectory on the time axis is calculated to obtain the demand gap parameter characterizing the degree of damage to growth potential. Based on the spatial coordinates of cultivation anomaly units, and superimposed with microclimate characteristic difference sequences, the dominant environmental limiting factors that lead to the decline of the current ecological niche suitability index are identified. Combined with demand gap parameters, factor-gap correlation pairs are constructed. Retrieve the preset physical control equipment capability parameter table for the target cultivation area to obtain the maximum operating power, adjustment accuracy range, and equipment response lag time of the control equipment; Based on the dominant environmental constraint factor type and the magnitude of the demand gap parameter in the factor-gap correlation pair, combined with the equipment response lag time, the running time and intensity level of the control equipment are calculated using linear mapping rules to generate a target microenvironment adjustment signal for each cultivation abnormality unit.

7. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 6, characterized in that, The target cultivation area is dynamically adjusted using the target microenvironment regulation signal to obtain an optimized cultivation area, including: Protocol parsing is performed on the target microenvironment regulation signal to extract the action command sequence of the control equipment and the theoretical environmental parameter change curves generated by the accompanying actions; combined with the spatial coordinates of the cultivation anomaly unit, the action command sequence is mapped to the specific physical device address to generate a spatiotemporal operation command set containing timestamps and device IDs; The diffusion parameters of environmental factors in the microclimate characteristic data of the target cultivation area are used to correct the change curve of theoretical environmental parameters. Then, the microclimate characteristic data of the target cultivation area is compared with the corrected change curve of theoretical environmental parameters point by point to calculate the dynamic deviation sequence between the actual environmental state and the theoretical target, and obtain the real-time deviation parameters that characterize the lag of equipment execution. Based on real-time deviation parameters and equipment response lag time, an error compensation field reflecting the spatiotemporal diffusion characteristics of environmental factors is constructed using environmental factor diffusion parameters. Feedforward control logic is used to correct the spatiotemporal operation instruction set and generate dynamic compensation adjustment instructions containing lead time or increment. The dynamic compensation and adjustment command is sent to the physical control equipment in the target cultivation area for execution. The real-time ecological niche suitability index is retrieved simultaneously to determine whether the suitability index of abnormal units has risen back to the normal threshold range. Units that have risen to the standard are marked as optimized units. The spatial proportion and continuous distribution status of all optimized units are statistically analyzed. When the proportion of optimized units exceeds the preset standard and the spatial distribution is continuous, the area with continuous distribution is directly marked as the optimized cultivation area.

8. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 7, characterized in that, Real-time biometric data of all target plants in the optimized cultivation area are obtained. Based on the spatial and temporal distribution characteristics of the real-time biometric data, matching growth response feature vectors are constructed. Based on the comparative analysis of the growth response feature vectors, the target optimization parameters for the optimized cultivation area are determined, including: Using the spatial vector boundary of the optimized cultivation area as the search range, the plant height growth and leaf chlorophyll content of all target plants in the area at the current moment are collected to generate real-time biometric data. Based on real-time biological characteristic data, the spatial variation function of plant height difference coefficient and chlorophyll content among adjacent plants in the cultivation area is calculated and optimized to generate a spatial distribution characteristic sequence reflecting the uniformity of population growth. Search the historical growth archive of the target cultivation area, extract the historical growth rate benchmark curve corresponding to the current growth stage, combine the absolute value of real-time biological feature data and the rate of change of spatial distribution feature sequence within a continuous time window, calculate the dynamic time curvature distance between the current growth trend and the historical benchmark curve, and generate a time distribution feature sequence that reflects the consistency of the growth trend. The spatial distribution feature sequence and the temporal distribution feature sequence are weighted and fused to construct the current growth response feature vector; Search the preset historical high-yield cultivation archive, obtain the historical growth response feature vectors of historical successful cases and the corresponding cultivation management parameter sets, and perform similarity matching between the current growth response feature vector and the historical growth response feature vectors; When the similarity matching result is greater than the preset matching threshold, the average value of the parameters in the cultivation management parameter set corresponding to the historical successful cases is extracted as the target optimization parameter for the cultivation area.

9. The decision-making system for Gastrodia elata cultivation under forest cover based on ecological simulation according to claim 8, characterized in that, Real-time biometric data are processed using target optimization parameters, and cultivation decision-making strategies that match the processing results are executed, including: The theoretical fertilization amount in the target optimization parameters is weighted and fused with the leaf chlorophyll content in real-time biological characteristic data to calculate the actual parameter adjustment amount for the current plant status; The system retrieves a preset table of physical control equipment capacity parameters, maps actual parameter adjustments to equipment operating power and duration, and generates a set of agronomic operation instructions containing equipment IDs and timestamps. The agronomic operation instruction set is sent to the execution mechanism of the optimized cultivation area to drive the operation of physical control equipment to execute the cultivation decision strategy.

10. A decision-making method for Gastrodia elata understory cultivation based on ecological simulation, applicable to the decision-making system for Gastrodia elata understory cultivation based on ecological simulation as described in any one of claims 1-9, characterized in that, include: Collect environmental monitoring signals from the target cultivation area and historical growth data of the target plants; among which, historical growth data includes plant height, biomass and tuber morphology indicators from past growth cycles; In response to environmental monitoring signals, the niche suitability index of each planting unit is calculated based on the differences in microclimate characteristics between adjacent planting units within the target cultivation area; wherein, the niche suitability index reflects the degree of environmental deviation of each planting unit; Comparative analysis of all niche suitability indices was conducted to identify each cultivation aberration unit. Based on the number of abnormal cultivation units and the temporal persistence characteristics of the niche suitability index of all abnormal cultivation units, the ecological regulation triggering signal of the target cultivation area is determined. In response to the ecological regulation trigger signal, the target microenvironment regulation signal is determined based on the correlation characteristics of historical growth data of all planting units in the target cultivation area and the ecological niche suitability index of abnormal cultivation units; the target cultivation area is dynamically regulated by the target microenvironment regulation signal to obtain the optimized cultivation area; Real-time biometric data of all target plants in the optimized cultivation area are obtained. Based on the spatial and temporal distribution characteristics of the real-time biometric data, matching growth response feature vectors are constructed. Based on the comparison and analysis results of the growth response feature vectors, the target optimization parameters of the optimized cultivation area are determined. Real-time biometric data are processed using target optimization parameters, and cultivation decision-making strategies that match the processing results are executed.

Images