Precise cultivation decision system and method for rubus parvifolius l.

Abstract

This invention relates to the field of cultivation decision-making technology, and discloses a precise cultivation decision-making system and method for *Drynaria fortunei*, comprising: a stage determination module for determining the growth stage and establishing batch files based on the bottle removal date and total number of leaves; a data acquisition module for collecting epiphytic-related data, environmental and substrate data, and medicinal quality data according to the evaluation cycle; an index calculation module for calculating the epiphytic adaptation index and the medicinal quality index and determining the median of the target interval; a block determination module for comparing the index with the target interval of the growth stage and determining the decision block type; a parameter generation module for generating irrigation, shading, nutrient solution, and substrate moisture content parameters based on the decision block type; an operation execution module for outputting operation cards and recording execution data; and a review and update module for periodically reviewing and updating the growth stage. This invention achieves refined control and full-cycle dynamic management of the *Drynaria fortunei* cultivation process.

Description

Technical Field

[0001] This invention belongs to the field of cultivation decision technology, specifically relating to a precision cultivation decision system and method for Drynaria fortunei. Background Technology

[0002] Drynaria fortunei is a perennial plant belonging to the Pyrrosiaceae family. Its growth process spans multiple stages, including adaptation after being removed from the pot, shaping in pots, and quality accumulation. Environmental conditions and management strategies have a significant impact on its medicinal quality. In traditional cultivation methods, producers typically rely on experience to judge the growth status, adjusting irrigation, shading, and nutrient supply by manually observing rhizome epiphytes, leaf quantity, degree of hardening, and simple environmental monitoring results. However, the growth rhythm of Drynaria fortunei is complex, and its requirements for water, light, and nutrients vary significantly at different stages. Experience-based management cannot guarantee the consistency and controllability of the cultivation process, easily leading to delayed judgment of growth stages and management measures deviating from the plant's needs, thereby affecting the accumulation of effective components and the quality stability of the finished medicinal material.

[0003] Existing cultivation and management models lack systematic data recording and quantitative analysis mechanisms, making it impossible to dynamically monitor the epiphytic ability, environmental adaptability, and medicinal quality formation process of plants. They also lack mathematical models to support phased optimization decisions. Especially after the large-scale transfer of tissue culture seedlings into cultivation systems, relying on manual judgment of phase progression and adjustment of management parameters will fail to meet the needs of refined and standardized production. Summary of the Invention

[0004] This invention provides a precision cultivation decision-making system and method for Drynaria fortunei, which solves the technical problems in related technologies, such as the lack of quantitative evaluation of epiphytic performance and medicinal quality, the difficulty in dynamically adjusting cultivation parameters according to the actual state of the plant, and the lack of unified data basis for stage advancement, which leads to unstable and untraceable cultivation process.

[0005] This invention provides a precision cultivation decision system for Drynaria fortunei, comprising:

[0006] The stage determination module is used to determine the growth stage of the target batch based on the bottle-out date and the total number of leaves of the target batch of Drynaria fortunei, and to create a batch file containing the bottle-out date and evaluation period.

[0007] The data acquisition module is used to collect epiphytic-related data, environmental and matrix data, and medicinal quality data of the target batch in each evaluation cycle, and write them into the batch file;

[0008] The index calculation module is used to calculate the epiphytic adaptation index and the medicinal quality index based on epiphytic related data and medicinal quality data, and to determine the corresponding target interval median.

[0009] The block determination module is used to compare the epiphytic adaptation index and the medicinal quality index with the target range of the corresponding growth stage to determine the decision block type of the target batch.

[0010] The parameter generation module is used to generate final decision parameters based on the decision block type and the basic settings based on the growth stage, combined with linear correction rules. The final decision parameters include: final irrigation interval, final shading level, final nutrient solution concentration, and substrate moisture content target.

[0011] The operation execution module is used to generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file.

[0012] The re-evaluation and update module is used to re-evaluate the epiphytic adaptation index and medicinal quality index recorded in the batch file according to the evaluation cycle, determine whether the growth stage target is met, and update the growth stage.

[0013] Furthermore, the growth stage of the target batch is determined, and a batch file is established, including:

[0014] Step 11: Obtain the bottle exit date and the total number of leaves in the first evaluation, generate a unique batch identifier for the target batch, and bind the bottle exit date and batch identifier as the time reference and batch reference, respectively.

[0015] Step 12: Obtain the evaluation date during the evaluation, calculate the elapsed time after exiting the bottle based on the difference between the evaluation date and the bottle exit date, obtain the total number of leaves at the evaluation time, and determine the growth stage at the evaluation time based on the combination relationship between the elapsed time after exiting the bottle and the total number of leaves with the time threshold and the leaf number threshold. The growth stages include: bottle exit stage, potted plant shaping stage and quality consolidation stage.

[0016] Step 13: Create and initialize a batch profile based on the batch identifier, bottled date, evaluation period, and growth stage marker.

[0017] Furthermore, the epiphytic-related data include: rhizome attachment length, total rhizome length, number of root hair segments, total number of root segments, number of leaves meeting hardening criteria, and total number of leaves;

[0018] Environmental and substrate data include: temperature, relative humidity, shading level, and substrate moisture content;

[0019] The medicinal quality data includes the content of naringin and neostigmine.

[0020] Furthermore, based on epiphytic data and medicinal quality data, the epiphytic adaptation index and medicinal quality index are calculated, and the corresponding target interval medians are determined, including:

[0021] Step 21: Obtain the attachment length ratio by the ratio of the rhizome attachment length to the total rhizome length; obtain the root hair density ratio by the ratio of the number of root segments with root hairs to the total number of root segments; obtain the leaf hardening ratio by the ratio of the number of leaves that meet the hardening standard to the total number of leaves; and obtain the epiphytic adaptation index by weighted summation and normalization of the three ratios.

[0022] Step 22: Calculate the ratio of naringin content to the target naringin content, and the ratio of neosedin content to the target neosedin content. Weight the sum of the two ratios and normalize them to obtain the medicinal quality index.

[0023] Step 23: Based on the preset target ranges for epiphytic adaptation index and medicinal quality index, take the arithmetic mean of the lower limit and upper limit of each target range to determine the median of the target ranges for epiphytic adaptation index and medicinal quality index.

[0024] Furthermore, target ranges for the epiphytic adaptation index and medicinal quality index are set according to different growth stages. When both the epiphytic adaptation index and the medicinal quality index of the target batch are outside the corresponding target range, it is determined to be a double-deficient area; when the epiphytic adaptation index is within the corresponding target range, but the medicinal quality index is outside the corresponding target range, it is determined to be an ecologically compliant but quality-deficient area; when the medicinal quality index is within the corresponding target range, but the epiphytic adaptation index is outside the corresponding target range, it is determined to be an ecologically deficient but quality-compliant area; when both the epiphytic adaptation index and the medicinal quality index are within the corresponding target range, it is determined to be a double-compliant area.

[0025] Furthermore, a buffer zone for the target range is constructed before determining the decision block type, including:

[0026] Step 31: Set buffer zones outside the upper and lower boundaries of the target ranges for the epiphytic adaptation index and the drug quality index, respectively;

[0027] Step 32: When the epiphytic adaptation index or drug quality index of the target batch falls into the corresponding buffer zone, the decision block type of the previous evaluation cycle remains unchanged.

[0028] Step 33: When the epiphytic adaptation index or drug quality index of the target batch exceeds the buffer zone or enters the corresponding target zone, a decision block determination is performed.

[0029] Furthermore, based on the decision block type and the basic settings based on the growth stage, and combined with linear correction rules, the final decision parameters are generated, including:

[0030] Step 41: Obtain basic settings. The difference between the epiphytic adaptation index and the median of the target range of the epiphytic adaptation index for the current growth stage is taken as the epiphytic deviation. The difference between the medicinal quality index and the median of the target range of the medicinal quality index for the current growth stage is taken as the quality deviation. The basic settings include: basic irrigation interval, basic shading level, basic nutrient solution concentration, and basic substrate moisture content.

[0031] Step 42: Multiply the epiphytic deviation by the corresponding irrigation interval correction factor and add it to the basic irrigation interval to obtain the uncorrected irrigation interval; multiply the epiphytic deviation by the shading level correction factor and add it to the basic shading level to obtain the uncorrected shading level; multiply the quality deviation by the nutrient solution concentration correction factor and add it to the basic nutrient solution concentration to obtain the uncorrected nutrient solution concentration; and determine the correction items to be executed according to the decision block type to form an uncorrected decision parameter set; wherein, the basic substrate moisture content is not included in the correction.

[0032] Step 43: Perform constraint correction on the uncorrected set of decision parameters and the basic matrix moisture content, and output the final decision parameters.

[0033] Furthermore, the corrections to be implemented based on the decision block type include:

[0034] If the decision block type is a double-insufficient area, then correction operations are performed on the basic irrigation interval, basic shading level, and basic nutrient solution concentration.

[0035] If the decision block type is an ecologically deficient but quality-compliant area, then only the basic irrigation interval and basic shading level will be corrected, and the basic nutrient solution concentration will not be corrected.

[0036] If the decision block type is an area with insufficient ecological quality, only the basic nutrient solution concentration will be corrected, while the basic irrigation interval and basic shading level will not be corrected.

[0037] If the decision block type is a dual-standard zone, then the basic irrigation interval, basic shading level, and basic nutrient solution concentration will all use the corresponding parameters from the previous evaluation cycle.

[0038] Furthermore, a reassessment is conducted based on the epiphytic adaptation index and medicinal quality index recorded in the batch file according to the evaluation cycle, and the growth stage is updated, including:

[0039] Step 51: Read the epiphytic adaptation index and medicinal quality index of the previous evaluation cycle from the batch file, read the current growth stage, and obtain the target range of epiphytic adaptation index and medicinal quality index corresponding to the growth stage.

[0040] Step 52: Compare the epiphytic adaptation index with the target interval of the epiphytic adaptation index using a closed interval to generate an epiphytic re-examination marker; compare the medicinal quality index with the target interval of the medicinal quality index using a closed interval to generate a quality re-examination marker.

[0041] Step 53: When both review markers are passed, the next growth stage is determined according to the preset stage progression order, and the next growth stage along with the update time is registered in the batch file; if either review marker fails, the current growth stage remains unchanged, and the reason for keeping it and the recording time are written into the batch file.

[0042] This invention provides a precise decision-making method for cultivating Drynaria fortunei, comprising the following steps:

[0043] Step 61: Based on the bottle-out date and total number of leaves of the target batch of Drynaria fortunei, determine the growth stage of the target batch and establish a batch file including the bottle-out date and evaluation period.

[0044] Step 62: In each evaluation cycle, collect epiphytic-related data, environmental and matrix data, and medicinal quality data for the target batch and write them into the batch file.

[0045] Step 63: Based on epiphytic data and medicinal quality data, calculate the epiphytic adaptation index and medicinal quality index, and determine the corresponding target interval median.

[0046] Step 64: Compare the epiphytic adaptation index and medicinal quality index with the target intervals of the corresponding growth stages to determine the decision block type of the target batch;

[0047] Step 65: Based on the decision block type and the basic settings based on the growth stage, and combined with the linear correction rule, generate the final decision parameters, which include: final irrigation interval, final shading level, final nutrient solution concentration and substrate moisture content target.

[0048] Step 66: Generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file;

[0049] Step 67: Based on the epiphytic adaptation index and medicinal quality index recorded in the batch file, conduct a re-evaluation according to the evaluation cycle to determine whether the growth stage target is met and update the growth stage.

[0050] The beneficial effects of this invention are as follows: By recording and organizing batch-based basic information, epiphytic-related data, environmental and substrate data, and medicinal quality data, this invention provides a clear data foundation for the growth status of plants at different stages; by constructing epiphytic adaptation indices and medicinal quality indices, it quantifies information such as rhizome attachment, root hair development, leaf structure maturity, and the content of major components, facilitating stage-based judgment; based on the target intervals set for each growth stage and combined with the decision block type, this invention can distinguish deviations and provide corresponding management priorities; by calculating and adjusting irrigation, shading, and nutrient solution parameters through linear correction rules, and combined with parameter range constraints, the generated decision parameters are executable and stable; by introducing a stage update method of buffer judgment and periodic review, stage advancement is based on continuous data rather than single fluctuations, improving the continuity and traceability of the cultivation process; overall, this invention forms a process from data collection and index calculation to parameter output and stage updates, improving the standardization and production consistency of Drynaria fortunei cultivation management. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the module of the precision cultivation decision system for Drynaria fortunei of the present invention. Detailed Implementation

[0052] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and implement the subject matter described herein, and changes may be made to the function and arrangement of the elements discussed without departing from the scope of this specification. Various processes or components may be omitted, substituted, or added as needed in the examples. Furthermore, features described in some examples may be combined in other examples.

[0053] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of the present invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in one or more embodiments of the present invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0054] like Figure 1 As shown, the precise cultivation decision-making system for *Drynaria fortunei* includes:

[0055] The stage determination module 1 is used to determine the growth stage of the target batch based on the bottle-out date and the total number of leaves of the target batch of Drynaria fortunei, and to establish a batch file containing the bottle-out date and evaluation period.

[0056] Data acquisition module 2 is used to collect epiphytic-related data, environmental and matrix data, and medicinal quality data of the target batch in each evaluation cycle, and write them into the batch file;

[0057] The index calculation module 3 is used to calculate the epiphytic adaptation index and the medicinal quality index based on epiphytic related data and medicinal quality data, and to determine the corresponding target interval median.

[0058] Block determination module 4 is used to compare the epiphytic adaptation index and medicinal quality index with the target interval of the corresponding growth stage to determine the decision block type of the target batch.

[0059] The parameter generation module 5 is used to generate final decision parameters based on the decision block type and the basic settings based on the growth stage, combined with linear correction rules. The final decision parameters include: final irrigation interval, final shading level, final nutrient solution concentration and substrate moisture content target.

[0060] Operation execution module 6 is used to generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file.

[0061] The re-evaluation and update module 7 is used to conduct re-evaluations based on the epiphytic adaptation index and medicinal quality index recorded in the batch file according to the evaluation cycle, to determine whether the growth stage target is met, and to update the growth stage.

[0062] In one embodiment of the present invention, the growth stage of the target batch of *Drynaria fortunei* is determined based on the bottle-out date and the total number of leaves, and a batch file including the bottle-out date and evaluation period is established, including:

[0063] Step 11: Obtain the bottle removal date and the total number of leaves in the first evaluation, generate a unique batch identifier for the target batch, and bind the bottle removal date and the batch identifier as the time reference and batch reference, respectively; the bottle removal date refers to the date on which the tissue culture seedling is removed from the culture medium and enters the conventional cultivation environment, which represents the time reference when the plant begins to adapt to the natural environment; the total number of leaves refers to the total number of leaves counted at the first evaluation, which is used to represent the basic growth level of the plant.

[0064] Step 12: During the evaluation, obtain the evaluation date. Calculate the elapsed time between the evaluation date and the bottle-out date, representing the actual growth time of *Drynaria fortunei* from bottle-out to the current evaluation point. This is used to determine the growth stage. Obtain the total number of leaves at the evaluation time. Determine the growth stage at the evaluation time based on the combination of the elapsed time, the total number of leaves, and the time and leaf number thresholds. The growth stages include: bottle-out stage, pot-plant shaping stage, and quality consolidation stage, corresponding to three different growth stages: adaptation growth of *Drynaria fortunei* tissue culture seedlings, structural stabilization formation, and improvement of medicinal quality, respectively. Specifically, when the elapsed time of the target batch is lower than the first time threshold and the total number of leaves is lower than the first leaf number threshold, the target batch is determined to be in the bottle-out stage. When the elapsed time is between the first and second time thresholds and the total number of leaves is between the first and second leaf number thresholds, the target batch is determined to be in the pot-plant shaping stage. When the elapsed time exceeds the second time threshold and the total number of leaves reaches the second leaf number threshold, the target batch is determined to be in the quality consolidation stage.

[0065] Step 13: Create and initialize a batch profile based on the batch identifier, bottle release date, evaluation cycle, and growth stage marker; the batch profile is used to record all collected data, index calculation results, decision parameters, and stage update information of the target batch throughout the entire cycle.

[0066] This embodiment establishes a clear, traceable, and calculable growth stage label and file structure for the target batch of Drynaria fortunei, realizing full-process data management from the starting point of growth to subsequent cycles.

[0067] In one embodiment of the present invention, the epiphytic-related data is used to reflect the binding ability, physiological stability, and leaf development status of *Drynaria fortunei* plants during the epiphytic stage; the epiphytic-related data includes: rhizome attachment length, total rhizome length, number of root segments with root hairs, total number of root segments, number of leaves meeting hardening criteria, and total number of leaves; rhizome attachment length refers to the effective attachment length of the rhizome in close contact with the epiphytic medium or cultivation substrate, the total rhizome length is the overall measured length of the rhizome; the number of root segments with root hairs is the number of root segments with obvious root hair growth, the total number of root segments is the number of all root segments; the number of leaves meeting hardening criteria refers to the number of leaves whose leaf structure meets the hardening conditions.

[0068] Environmental and substrate data are used to reflect the external conditions of the cultivation environment of Drynaria fortunei, including temperature, relative humidity, shading level and substrate moisture content. Temperature and relative humidity reflect the climatic conditions of the cultivation environment, shading level reflects the light regulation intensity of the cultivation facility, and substrate moisture content reflects the moisture content of the cultivation substrate. These parameters can comprehensively describe the external environment for the growth of Drynaria fortunei.

[0069] Medicinal quality data are used to assess the quality maturity of Drynaria fortunei, including the content of naringin and neostigmine, both of which are important active ingredients in Drynaria fortunei, and their content levels can reflect the quality accumulation of the plant in the later stages of growth.

[0070] In one embodiment of the present invention, based on epiphytic related data and medicinal quality data, an epiphytic adaptation index and a medicinal quality index are calculated, and the corresponding target interval median is determined, including:

[0071] Step 21: The attachment length ratio is obtained by the ratio of the rhizome attachment length to the total length of the rhizome. This ratio is used to represent the degree of attachment between the plant's rhizome and the cultivation substrate. The root hair density ratio is obtained by the ratio of the number of root segments with root hairs to the total number of root segments. This ratio is used to reflect the maturity of the leaf structure. The leaf hardening ratio is obtained by the ratio of the number of leaves that have reached the hardening standard to the total number of leaves. These three ratios reflect the plant's adaptability during the epiphytic process from different dimensions. The three ratios are weighted and summed and normalized by dividing by the sum of the weights to obtain the epiphytic adaptation index. This index represents the overall adaptation level during the epiphytic period.

[0072] Step 22: Calculate the ratio of naringin content to the target naringin content, and the ratio of neostigmine content to the target neostigmine content. Weight the sum of the two ratios and normalize them to obtain the medicinal quality index. The two ratios are used to represent the degree of accumulation of effective ingredients in the target batch, and the medicinal quality index is used to reflect the medicinal quality level of Drynaria fortunei at the current growth stage.

[0073] Step 23: Based on the preset target ranges for epiphytic adaptability index and medicinal quality index, take the arithmetic mean of the lower and upper limits of each target range to determine the median of the target ranges for epiphytic adaptability index and medicinal quality index. The target ranges are set based on industry experience, variety characteristics, and historical production data.

[0074] Through the above-mentioned index construction and target interval median determination process, this embodiment realizes the quantification of epiphytic adaptability and medicinal quality, enabling complex biological growth information to be transformed into numerical values ​​that can be used for automatic decision-making, and providing a unified computational basis for decision block type determination, linear correction and growth stage update.

[0075] In one embodiment of the present invention, target ranges for epiphytic adaptation index and medicinal quality index are set according to different growth stages. When both the epiphytic adaptation index and the medicinal quality index of a target batch are outside the corresponding target ranges, it is determined to be a double deficiency zone, indicating that the target batch has not met the required index ranges for that growth stage in terms of both epiphytic state and medicinal quality. When the epiphytic adaptation index is within the corresponding target range, but the medicinal quality index is outside the corresponding target range, it is determined to be an ecologically adequate quality deficiency zone, indicating that the epiphytic growth performance meets the requirements, but the medicinal quality has not met the corresponding standard. When the medicinal quality index is within the corresponding target range, but the epiphytic adaptation index is outside the corresponding target range, it is determined to be an ecologically inadequate quality compliance zone, indicating that the medicinal quality meets the standard, but the epiphytic performance deviates from the requirements of that growth stage. When both the epiphytic adaptation index and the medicinal quality index are within the corresponding target ranges, it is determined to be a double compliance zone, indicating that the batch meets the stage requirements in terms of both epiphytic performance and medicinal quality.

[0076] Through the above-mentioned determination method, the system can classify the growth status of target batches in a phased and structured manner based on a unified target interval system, so as to achieve the synchronization and consistency of growth regulation and quality regulation, and provide a reliable data foundation for the precision cultivation decision system of the present invention.

[0077] In one embodiment of the present invention, constructing a buffer zone for the target interval before determining the decision block type includes:

[0078] Step 31: Set buffer zones outside the upper and lower boundaries of the target intervals for the epiphytic adaptation index and the drug quality index, respectively, to determine whether the index changes are sufficient to trigger the update of the decision block type.

[0079] Step 32: When the epiphytic adaptation index or drug quality index of the target batch falls into the corresponding buffer zone, keep the decision block type of the previous evaluation cycle unchanged to avoid repeated adjustments to the growth regulation strategy due to slight fluctuations.

[0080] Step 33: When the epiphytic adaptation index or drug quality index of the target batch exceeds the buffer zone or enters the corresponding target zone, a decision block determination is performed.

[0081] Through the above-mentioned buffering mechanism, the present invention achieves the continuity and stability of the growth regulation logic, avoids decision oscillations caused by data disturbances near the stage boundary, and enables the decision system to maintain a consistent indicator judgment system over a long evaluation period.

[0082] In one embodiment of the present invention, the final decision parameters are generated based on the decision block type and the basic settings based on the growth stage, combined with a linear correction rule, including:

[0083] Step 41: Obtain the basic settings. The difference between the epiphytic adaptation index and the median of the target range for the epiphytic adaptation index at the current growth stage is taken as the epiphytic deviation, and the difference between the medicinal quality index and the median of the target range for the medicinal quality index at the current growth stage is taken as the quality deviation. The basic settings include: basic irrigation interval, basic shading level, basic nutrient solution concentration, and basic substrate moisture content. The above two types of deviations are used to indicate the degree to which the target batch deviates from the standard state at this growth stage in terms of epiphytic performance and medicinal quality, respectively, providing a quantitative basis for subsequent corrections.

[0084] Step 42: The system corrects the basic settings according to the linear correction rule. Specifically, it multiplies the epiphytic deviation by the corresponding irrigation interval correction coefficient and adds it to the basic irrigation interval to obtain the uncorrected irrigation interval; it multiplies the epiphytic deviation by the shading level correction coefficient and adds it to the basic shading level to obtain the uncorrected shading level; it multiplies the quality deviation by the nutrient solution concentration correction coefficient and adds it to the basic nutrient solution concentration to obtain the uncorrected nutrient solution concentration; and it determines the correction items to be executed according to the decision block type, forming an uncorrected decision parameter set; wherein, the basic substrate moisture content is not included in the correction.

[0085] Step 43 involves constraining and correcting the uncorrected set of decision parameters and the basic substrate moisture content. This includes comparing each parameter against a preset allowable range, limiting values ​​outside the range to the boundary, and outputting the final decision parameters. The final set of decision parameters includes the final irrigation interval, final shading level, final nutrient solution concentration, and final substrate moisture content, and can be directly applied to the cultivation operations of the target batch.

[0086] This embodiment establishes a linear mapping relationship between deviation and correction coefficient to achieve quantitative correction of cultivation parameters based on the basic settings, making the decision generation process continuous and interpretable. By performing block type screening and range constraint correction on the correction results, the final decision parameters that conform to the stage characteristics are generated, enabling the cultivation strategy to be adjusted in real time according to batch performance. This transforms the cultivation of Drynaria fortunei from experience-based management to index-driven standardized management, achieving precision, stability and traceability of the cultivation process.

[0087] In one embodiment of the present invention, determining the correction items to be executed based on the decision block type includes:

[0088] If the decision block type is a double-deficient area, then the basic irrigation interval, basic shading level and basic nutrient solution concentration are all modified to improve both epiphytic ability and medicinal quality.

[0089] If the decision block type is an ecologically deficient but quality-compliant area, then only the basic irrigation interval and basic shading level will be modified, and the basic nutrient solution concentration will not be modified. It will be used to improve the epiphytic environment, while the basic nutrient solution concentration will remain unchanged.

[0090] If the decision block type is an area with insufficient ecological quality, only the basic nutrient solution concentration will be corrected, while the basic irrigation interval and basic shading level will not be corrected, in order to specifically enhance the accumulation of the main active ingredients, while the irrigation interval and shading level will remain at the basic values.

[0091] If the decision block type is a dual-standard zone, the basic irrigation interval, basic shading level, and basic nutrient solution concentration will all use the corresponding parameters from the previous evaluation cycle to ensure that the parameters that have reached a stable state remain consistent in subsequent cycles.

[0092] Through the aforementioned differentiated correction mechanism, this invention achieves parameter selection correction based on decision block type, enabling parameter adjustment actions to accurately correspond to the deviation direction of the target batch, avoiding unnecessary parameter disturbances, improving the pertinence and stability of the cultivation process, and making the cultivation management of different growth stages of Drynaria fortunei more in line with physiological needs, which is conducive to achieving the system goal of precision cultivation and quality stabilization.

[0093] In one embodiment of the present invention, the operation execution module is used to perform specific cultivation operations on the target batch and form a structured operation record after generating the final decision parameters. The module first constructs a batch operation card based on the final decision parameters. The batch operation card is a set of parameters used to guide the target batch in performing irrigation, shading adjustment, nutrient solution preparation, and substrate moisture content control within the current evaluation period, including fields for final irrigation interval, final shading level, final nutrient solution concentration, and final substrate moisture content.

[0094] After generating the batch operation card, the operation execution module performs cultivation operations on the target batch according to the parameters defined in the operation card. The cultivation operations include triggering irrigation events according to the final irrigation interval, adjusting the light shading ratio according to the final shading level, preparing and supplying nutrient solution according to the final nutrient solution concentration, and controlling the moisture content of the substrate.

[0095] At the end of each cultivation cycle, the operation execution module acquires the actual execution data for that cycle, including irrigation execution records, shading adjustment records, nutrient solution supply records, and substrate moisture content monitoring records. Based on epiphytic data and medicinal quality data, the epiphytic adaptation index and medicinal quality index for that cycle are recalculated, and the two indices and the corresponding actual execution data are written into the batch file.

[0096] Through the above-described operational process, this invention enables the accurate implementation of final decision parameters into actual cultivation operations and the formation of standardized periodic execution records. This transforms the cultivation process of Drynaria fortunei from traditional experience-based management to parameter-driven refined management, achieving controllability, traceability, and reusability of cultivation behavior. It also provides stable and continuous data support for index calculation and decision block determination in subsequent cycles.

[0097] In one embodiment of the present invention, a re-evaluation is conducted according to the evaluation cycle based on the epiphytic adaptation index and medicinal quality index recorded in the batch file, and the growth stage is updated, including:

[0098] Step 51: Read the epiphytic adaptation index and medicinal quality index of the previous evaluation cycle from the batch file, read the current growth stage, and obtain the target range of epiphytic adaptation index and medicinal quality index corresponding to the growth stage.

[0099] Step 52: Compare the epiphytic adaptability index with the target interval of the epiphytic adaptability index using a closed interval to generate an epiphytic re-examination marker; compare the medicinal quality index with the target interval of the medicinal quality index using a closed interval to generate a quality re-examination marker; the closed interval comparison refers to determining whether the index value is between the lower limit and the upper limit of the target interval, including boundary values, to determine whether the index meets the stage requirements; the two re-examination markers respectively reflect the compliance status of epiphytic adaptability and medicinal quality, including pass and fail;

[0100] Step 53: When both review marks are passed, the next growth stage is determined according to the preset stage progression order, such as moving from the bottle-out stage to the pot-forming stage, and from the pot-forming stage to the quality consolidation stage. The next growth stage, along with the update time, is then recorded in the batch file. If either review mark fails, the current growth stage remains unchanged, and the reason for maintaining it and the recording time are written into the batch file.

[0101] By adopting an index-based phase update mechanism, this invention enables strict phase thresholds and review logic for the growth management of different stages of Drynaria fortunei, realizing the transformation from experience-based judgment to model-driven scientific phase management, and improving the accuracy, continuity and traceability of phase management.

[0102] This invention also provides a method for precise cultivation decision-making of Drynaria fortunei, including the following steps:

[0103] Step 61: Based on the bottle-out date and total number of leaves of the target batch of Drynaria fortunei, determine the growth stage of the target batch and establish a batch file including the bottle-out date and evaluation period.

[0104] Step 62: In each evaluation cycle, collect epiphytic-related data, environmental and matrix data, and medicinal quality data for the target batch and write them into the batch file.

[0105] Step 63: Based on epiphytic data and medicinal quality data, calculate the epiphytic adaptation index and medicinal quality index, and determine the corresponding target interval median.

[0106] Step 64: Compare the epiphytic adaptation index and medicinal quality index with the target intervals of the corresponding growth stages to determine the decision block type of the target batch;

[0107] Step 65: Based on the decision block type and the basic settings based on the growth stage, and combined with the linear correction rule, generate the final decision parameters, which include: final irrigation interval, final shading level, final nutrient solution concentration and substrate moisture content target.

[0108] Step 66: Generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file;

[0109] Step 67: Based on the epiphytic adaptation index and medicinal quality index recorded in the batch file, conduct a re-evaluation according to the evaluation cycle to determine whether the growth stage target is met and update the growth stage.

[0110] It should be noted that the interval and threshold sizes are set for ease of comparison. The size of the threshold depends on the amount of sample data and the base number set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless calculations, and the formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0111] The embodiments of the present invention have been described above, but the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms based on the guidance of the present embodiments, all of which are within the protection scope of the present embodiments.

Claims

1. A precision cultivation decision-making system for Drynaria fortunei, characterized in that, include: The stage determination module is used to determine the growth stage of the target batch based on the bottle-out date and the total number of leaves of the target batch of Drynaria fortunei, and to create a batch file containing the bottle-out date and evaluation period. The data acquisition module is used to collect epiphytic-related data, environmental and matrix data, and medicinal quality data of the target batch in each evaluation cycle, and write them into the batch file; The index calculation module is used to calculate the epiphytic adaptation index based on epiphytic related data and the medicinal quality index based on medicinal quality data, and to determine the target interval median values ​​for both the epiphytic adaptation index and the medicinal quality index, including: Step 21: Obtain the attachment length ratio by the ratio of the rhizome attachment length to the total rhizome length; obtain the root hair density ratio by the ratio of the number of root segments with root hairs to the total number of root segments; obtain the leaf hardening ratio by the ratio of the number of leaves that meet the hardening standard to the total number of leaves; and obtain the epiphytic adaptation index by weighted summation and normalization of the three ratios. Step 22: Calculate the ratio of naringin content to target naringin content, and the ratio of neostigmine content to target neostigmine content. Weight the sum of the two ratios and normalize them to obtain the medicinal quality index. Step 23: Based on the preset target ranges for epiphytic adaptation index and medicinal quality index, take the arithmetic mean of the lower limit and upper limit of each target range to determine the median of the target range for epiphytic adaptation index and the median of the target range for medicinal quality index. The block determination module is used to compare the epiphytic adaptation index and the medicinal quality index with the target range of the corresponding growth stage to determine the decision block type of the target batch. The parameter generation module is used to generate final decision parameters based on the decision block type and the basic settings based on the growth stage, combined with linear correction rules. The final decision parameters include: final irrigation interval, final shading level, final nutrient solution concentration, and substrate moisture content target. The operation execution module is used to generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file. The re-evaluation and update module is used to re-evaluate the epiphytic adaptation index and medicinal quality index recorded in the batch file according to the evaluation cycle, determine whether the growth stage target is met, and update the growth stage.

2. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, Determine the growth stage of the target batch and establish a batch file, including: Step 11: Obtain the bottle exit date and the total number of leaves in the first evaluation, generate a unique batch identifier for the target batch, and bind the bottle exit date and batch identifier as the time reference and batch reference, respectively. Step 12: Obtain the evaluation date during the evaluation, calculate the elapsed time after exiting the bottle based on the difference between the evaluation date and the bottle exit date, obtain the total number of leaves at the evaluation time, and determine the growth stage at the evaluation time based on the combination relationship between the elapsed time after exiting the bottle and the total number of leaves with the time threshold and the leaf number threshold. The growth stages include: bottle exit stage, potted plant shaping stage and quality consolidation stage. Step 13: Create and initialize a batch profile based on the batch identifier, bottled date, evaluation period, and growth stage marker.

3. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, The epiphytic data include: rhizome attachment length, total rhizome length, number of root segments with root hairs, total number of root segments, number of leaves that meet the hardening standard, and total number of leaves; Environmental and substrate data include: temperature, relative humidity, shading level, and substrate moisture content; The medicinal quality data includes the content of naringin and neostigmine.

4. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, Target ranges for epiphytic adaptation index and medicinal quality index are set according to different growth stages. When both the epiphytic adaptation index and the medicinal quality index of the target batch are outside the corresponding target range, it is judged as a double deficiency zone; when the epiphytic adaptation index is within the corresponding target range, but the medicinal quality index is outside the corresponding target range, it is judged as an ecologically compliant but quality-deficient zone; when the medicinal quality index is within the corresponding target range, but the epiphytic adaptation index is outside the corresponding target range, it is judged as an ecologically deficient but quality-compliant zone; when both the epiphytic adaptation index and the medicinal quality index are within the corresponding target range, it is judged as a double compliance zone.

5. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, Before determining the decision block type, a buffer zone for the target range is constructed, including: Step 31: Set buffer zones outside the upper and lower boundaries of the target ranges for the epiphytic adaptation index and the drug quality index, respectively; Step 32: When the epiphytic adaptation index or drug quality index of the target batch falls into the corresponding buffer zone, the decision block type of the previous evaluation cycle remains unchanged. Step 33: When the epiphytic adaptation index or drug quality index of the target batch exceeds the buffer zone or enters the corresponding target zone, a decision block determination is performed.

6. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, Based on the decision block type and the basic settings based on the growth stage, the final decision parameters are generated using linear correction rules, including: Step 41: Obtain basic settings. The difference between the epiphytic adaptation index and the median of the target range of the epiphytic adaptation index for the current growth stage is taken as the epiphytic deviation. The difference between the medicinal quality index and the median of the target range of the medicinal quality index for the current growth stage is taken as the quality deviation. The basic settings include: basic irrigation interval, basic shading level, basic nutrient solution concentration, and basic substrate moisture content. Step 42: Multiply the epiphytic deviation by the corresponding irrigation interval correction factor and add it to the basic irrigation interval to obtain the uncorrected irrigation interval; multiply the epiphytic deviation by the shading level correction factor and add it to the basic shading level to obtain the uncorrected shading level; multiply the quality deviation by the nutrient solution concentration correction factor and add it to the basic nutrient solution concentration to obtain the uncorrected nutrient solution concentration; and determine the correction items to be executed according to the decision block type to form an uncorrected decision parameter set; wherein, the basic substrate moisture content is not included in the correction. Step 43: Perform constraint correction on the uncorrected set of decision parameters and the basic matrix moisture content, and output the final decision parameters.

7. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, The necessary corrections, determined based on the decision block type, include: If the decision block type is a double-insufficient area, then correction operations are performed on the basic irrigation interval, basic shading level, and basic nutrient solution concentration. If the decision block type is an ecologically deficient but quality-compliant area, then only the basic irrigation interval and basic shading level will be corrected, and the basic nutrient solution concentration will not be corrected. If the decision block type is an area with insufficient ecological quality, only the basic nutrient solution concentration will be corrected, while the basic irrigation interval and basic shading level will not be corrected. If the decision block type is a dual-standard zone, then the basic irrigation interval, basic shading level, and basic nutrient solution concentration will all use the corresponding parameters from the previous evaluation cycle.

8. The precision cultivation decision-making system for *Drynaria fortunei* according to claim 1, characterized in that, The evaluation cycle is conducted based on the epiphytic adaptation index and medicinal quality index recorded in the batch file, and the growth stage is updated, including: Step 51: Read the epiphytic adaptation index and medicinal quality index of the previous evaluation cycle from the batch file, read the current growth stage, and obtain the target range of epiphytic adaptation index and medicinal quality index corresponding to the growth stage. Step 52: Compare the epiphytic adaptation index with the target interval of the epiphytic adaptation index using a closed interval to generate an epiphytic re-examination marker; compare the medicinal quality index with the target interval of the medicinal quality index using a closed interval to generate a quality re-examination marker. Step 53: When both review markers are passed, the next growth stage is determined according to the preset stage progression order, and the next growth stage along with the update time is registered in the batch file; if either review marker fails, the current growth stage remains unchanged, and the reason for keeping it and the recording time are written into the batch file.

9. A precise cultivation decision-making method for Drynaria fortunei, characterized in that, The precision cultivation decision-making system for *Drynaria fortunei* as described in any one of claims 1-8 includes the following steps: Step 61: Based on the bottle-out date and total number of leaves of the target batch of Drynaria fortunei, determine the growth stage of the target batch and establish a batch file including the bottle-out date and evaluation period. Step 62: In each evaluation cycle, collect epiphytic-related data, environmental and matrix data, and medicinal quality data for the target batch and write them into the batch file. Step 63: Calculate the epiphytic adaptation index based on epiphytic related data, calculate the medicinal quality index based on medicinal quality data, and determine the target range median values ​​for the epiphytic adaptation index and the medicinal quality index respectively. Step 64: Compare the epiphytic adaptation index and medicinal quality index with the target intervals of the corresponding growth stages to determine the decision block type of the target batch; Step 65: Based on the decision block type and the basic settings based on the growth stage, and combined with the linear correction rule, generate the final decision parameters, which include: final irrigation interval, final shading level, final nutrient solution concentration and substrate moisture content target. Step 66: Generate batch operation cards based on the final decision parameters, carry out cultivation operations on the target batch, and write the actual execution data and the corresponding epiphytic adaptation index and medicinal quality index into the batch file; Step 67: Based on the epiphytic adaptation index and medicinal quality index recorded in the batch file, conduct a re-evaluation according to the evaluation cycle to determine whether the growth stage target is met and update the growth stage.

Images