Epimedium sagittatum growth quality evaluation method and system based on big data analysis

Abstract

This invention relates to the field of Epimedium sagittatum production technology, and discloses a method and system for evaluating the growth quality of Epimedium sagittatum based on big data analysis. The method includes acquiring growth and morphological data of Epimedium sagittatum in the current planting area, constructing a growth database, analyzing the growth database to obtain environmental suitability indicators; analyzing the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle based on morphological data to obtain medicinal contribution evaluation indicators; constructing a dynamic evaluation model using the suitability indicators and medicinal contribution evaluation indicators, and using the dynamic evaluation model to analyze Epimedium sagittatum to obtain growth quality parameters; establishing a quality change curve based on the growth quality parameters, using the quality change curve to predict the harvest window, and obtaining the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window. This invention achieves accuracy in evaluating the growth quality of Epimedium sagittatum.

Description

Technical Field

[0001] This invention relates to the field of Epimedium sagittatum production technology, and more specifically, to a method and system for evaluating the growth quality of Epimedium sagittatum based on big data analysis. Background Technology

[0002] Epimedium sagittatum, a traditional and precious Chinese medicinal herb, possesses significant clinical effects such as tonifying kidney yang, strengthening muscles and bones, and dispelling wind and dampness. Its market demand has been increasing year by year with the development of the health industry. With the advancement of artificial cultivation and large-scale planting of Epimedium sagittatum, the issue of quality stability during its growth process has gradually gained attention. Epimedium sagittatum mostly grows in semi-shaded, humid environments and is quite sensitive to shading degree, light intensity, temperature and humidity, and soil physicochemical conditions. Environmental differences in different planting areas and different growth stages often lead to variations in plant growth status, the accumulation level of effective components, and the optimal harvesting time.

[0003] However, existing quality assessment techniques for Epimedium sagittatum primarily focus on optimizing cultivation methods, post-harvest component analysis, or static quality grading. These methods typically employ single-sampling to evaluate appearance, yield, or active ingredient content at a specific point in time, failing to reflect the dynamic process of quality changes throughout the entire growth cycle. Furthermore, current evaluation methods often focus on whole samples, rarely considering the morphological characteristics and medicinal contributions of different parts such as leaves, petioles, and stems. They also lack systematic evaluation methods that combine the suitability of the planting environment, the medicinal contribution of different plant parts, and harvest window prediction, thus hindering accurate guidance for quality assessment and timely harvesting of Epimedium sagittatum.

[0004] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0005] To address the problems in related technologies, this invention proposes a method and system for evaluating the growth quality of Epimedium sagittatum based on big data analysis, in order to overcome the aforementioned technical problems existing in the current related technologies.

[0006] Therefore, the specific technical solution adopted by the present invention is as follows: According to a first aspect of the present invention, a method for evaluating the growth quality of Epimedium sagittatum based on big data analysis is provided, comprising: S1. Obtain growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. S2. Based on morphological data, analyze the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and obtain medicinal contribution evaluation indicators based on the medicinal contribution data. S3. A dynamic evaluation model was constructed using suitability indicators and medicinal contribution evaluation indicators, and the growth quality parameters of Epimedium sagittatum were obtained by analyzing the dynamic evaluation model. S4. Establish a quality change curve based on growth quality parameters, use the quality change curve to predict the harvest window, and obtain the quality evaluation results of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

[0007] Preferably, the step of acquiring growth and morphological data of Epimedium sagittatum in the current planting area, constructing a growth database using the growth data, and analyzing the growth database to obtain environmental suitability indicators includes: S11. Collect light environment data and land environment data of the current planting area as growth data through a preset sensor array. The light environment data includes at least shading degree, light intensity and light duration, and the land environment data includes at least air temperature and humidity, soil temperature and humidity and soil organic matter content. S12. Standardize and associate the growth data with the planting time, collection time and plant number of Epimedium sagittatum to construct a growth database; S13. Use correlation analysis to analyze the growth database and obtain environmental suitability indicators.

[0008] Preferably, the environmental suitability indicators obtained by analyzing the growth database using correlation analysis include: S131. Using the standardized growth data in the growth database as the independent variable and the pharmacodynamic component content data of historical Epimedium sagittatum samples corresponding to the current planting area as the dependent variable, a correlation analysis model is constructed. S132. Use a correlation analysis model to calculate the correlation coefficient between growth data and the content of active ingredients, and select growth data with a correlation coefficient greater than a preset threshold as core influencing factors. S133. Based on the ratio between the correlation coefficients of the core influencing factors and the content of the active ingredients, allocate the initial weights of the core influencing factors, and use the partial correlation coefficients between the factors to perform redundancy correction on the initial weights to obtain the target weight set. S134, based on the target weight set, the core influencing factors are weighted and summed to obtain the environmental suitability index that characterizes the environmental suitability of the current planting area.

[0009] Preferably, the step of analyzing the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle based on morphological data, and obtaining medicinal contribution evaluation indicators based on the medicinal contribution data, includes: S21. Obtain morphological data of leaves, petioles and stems of Epimedium sagittatum during its growth cycle; S22. Analyze the morphological data of each part using a preset mapping model to obtain the estimated efficacy value of each part. S23. Based on the proportion of the projected area of ​​each part in the morphological data, determine the biomass contribution weight, and calculate the efficacy estimate of each part with the corresponding biomass contribution weight to obtain the medicinal value data of each part. S24. Combining the preset efficacy proportion weights of each part of Epimedium sagittatum during its growth cycle, the medicinal value data of each part are weighted to obtain the medicinal contribution evaluation index.

[0010] Preferably, the dynamic evaluation model constructed using suitability indicators and medicinal contribution evaluation indicators, and the analysis of Epimedium sagittatum using the dynamic evaluation model to obtain the growth quality parameters of Epimedium sagittatum, include: S31. Obtain the environmental suitability index and medicinal contribution evaluation index of Epimedium sagittatum at different growth stages during its growth cycle, and construct a time-series fusion matrix. S32. Analyze the time-series fusion matrix using preset dynamic evaluation rules to obtain the corresponding growth quality parameters in the growth cycle of Epimedium sagittatum.

[0011] Preferably, the step of establishing a quality change curve based on growth quality parameters, predicting the harvest window using the quality change curve, and obtaining the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window includes: S41. Arrange the growth quality parameters of Epimedium sagittatum at different growth stages in the growth cycle according to the collection time order to form a quality parameter time series. S42. Perform curve fitting on the time series of quality parameters to obtain the quality change curve; S43. Based on the peak range of the quality change curve, predict the harvest window and obtain harvest recommendations; S44. Based on the growth quality parameters corresponding to the current growth stage, classify the quality grade of Epimedium sagittatum and obtain the quality evaluation results in combination with the harvesting recommendations.

[0012] Preferably, the step of classifying the quality grade of Epimedium sagittatum based on the growth quality parameters corresponding to the current growth stage, and obtaining the quality evaluation result in conjunction with harvesting recommendations, includes: S441. Quality grades include superior, good, and ordinary. S442. Harvesting recommendations include direct harvesting, delayed harvesting, and early harvesting.

[0013] According to a second aspect of the present invention, a growth quality evaluation system for Epimedium sagittatum based on big data analysis is provided, comprising: The suitability analysis module is used to obtain growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. The medicinal contribution analysis module is used to analyze the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and to obtain medicinal contribution evaluation indicators based on the medicinal contribution data. The growth quality module is used to construct a dynamic evaluation model using suitability indicators and medicinal contribution evaluation indicators, and to analyze Epimedium sagittatum using the dynamic evaluation model to obtain the growth quality parameters of Epimedium sagittatum. The quality evaluation module is used to establish a quality change curve based on growth quality parameters, predict the harvest window using the quality change curve, and obtain the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

[0014] According to a third aspect of the present invention, a computer device is provided.

[0015] Preferably, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above method.

[0016] According to a fourth aspect of the present invention, a computer-readable storage medium is provided.

[0017] Preferably, the computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the above method.

[0018] The beneficial effects of this invention are as follows: 1. By acquiring growth data of Epimedium sagittatum in the current planting area and constructing a growth database, and further combining the correlation between environmental factors and the content of medicinal components in historical samples, an environmental suitability index is obtained to characterize the environmental suitability of the current planting area. This allows for a quantitative evaluation of the growth conditions of Epimedium sagittatum at the planting area level, thereby improving the accuracy of environmental suitability judgment.

[0019] 2. By acquiring growth data of Epimedium sagittatum in the current planting area and constructing a growth database, and further combining the correlation between environmental factors and the content of medicinal components in historical samples, an environmental suitability index is obtained to characterize the environmental suitability of the current planting area. This allows for a quantitative evaluation of the growth conditions of Epimedium sagittatum at the planting area level, thereby improving the accuracy of environmental suitability judgment.

[0020] 3. By analyzing the medicinal contribution data of different parts of Epimedium sagittatum during its growth cycle, medicinal contribution evaluation indicators were obtained. Environmental suitability indicators were then integrated with medicinal contribution evaluation indicators to construct a dynamic evaluation model. This model yielded growth quality parameters of Epimedium sagittatum at different growth stages, thereby reflecting the dynamic changes in quality of Epimedium sagittatum throughout its entire growth cycle and improving the comprehensiveness of quality evaluation. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the Epimedium sagittatum growth quality evaluation system based on big data analysis according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

[0023] In the picture: 1. Suitability Analysis Module; 2. Medicinal Contribution Analysis Module; 3. Growth Quality Module; 4. Quality Evaluation Module. Detailed Implementation

[0024] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0025] According to embodiments of the present invention, a method and system for evaluating the growth quality of Epimedium sagittatum based on big data analysis are provided.

[0026] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to a first aspect of the present invention, a method for evaluating the growth quality of Epimedium sagittatum based on big data analysis is provided, comprising: S1. Obtain growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. In a preferred embodiment, the steps of obtaining growth and morphological data of Epimedium sagittatum in the current planting area, constructing a growth database using the growth data, and analyzing the growth database to obtain environmental suitability indicators include: S11. Collect light environment data and land environment data of the current planting area as growth data through a preset sensor array. The light environment data includes at least shading degree, light intensity and light duration, and the land environment data includes at least air temperature and humidity, soil temperature and humidity and soil organic matter content. S12. Standardize and associate the growth data with the planting time, collection time and plant number of Epimedium sagittatum to construct a growth database; S13. Use correlation analysis to analyze the growth database and obtain environmental suitability indicators.

[0027] In a preferred embodiment, the environmental suitability index obtained by analyzing the growth database using correlation analysis includes: S131. Using the standardized growth data in the growth database as the independent variable and the pharmacodynamic component content data of historical Epimedium sagittatum samples corresponding to the current planting area as the dependent variable, a correlation analysis model is constructed. S132. Use a correlation analysis model to calculate the correlation coefficient between growth data and the content of active ingredients, and select growth data with a correlation coefficient greater than a preset threshold as core influencing factors. S133. Based on the ratio between the correlation coefficients of the core influencing factors and the content of the active ingredients, allocate the initial weights of the core influencing factors, and use the partial correlation coefficients between the factors to perform redundancy correction on the initial weights to obtain the target weight set. S134, based on the target weight set, the core influencing factors are weighted and summed to obtain the environmental suitability index that characterizes the environmental suitability of the current planting area.

[0028] Specifically, light environment data (such as shading degree, light intensity, and duration environmental factors) and soil environment data (such as air temperature, soil temperature, soil moisture, and organic matter environmental factors) of Epimedium sagittatum are collected by a sensor array set up in the planting area as growth data. The mathematical expression is as follows: ; In the formula, For the first A set of growth data at each sampling time point. For the first The sampling time of the first sampling moment nData corresponding to each environmental factor n This represents the total number of environmental factors.

[0029] For example, For shade level, Light intensity, For duration of illumination, For air temperature, For air humidity, For soil temperature, For soil moisture, This refers to the soil organic matter content.

[0030] Since the environmental factors have different dimensions, the original values ​​of each environmental factor are mapped to a unified numerical range using min-max standardization. The mathematical expression for this is: ; In the formula, As environmental factors, The standardized dimensionless value. This represents the historical minimum value of environmental factors. This represents the historical maximum value of environmental factors.

[0031] The planting time, harvesting time, and plant number of Epimedium sagittatum are retrieved and associated with growth data for storage. The expression is as follows: ; ; In the formula, For growth database, To record the total, For growth database, Number the plants. For planting time, For the time of collection, This is growth data.

[0032] At this point, the growth data is used as the independent variable to construct the independent variable set. Construct a dependent variable set using historical pharmacodynamic component content data as the dependent variable. .

[0033] The Pearson correlation coefficient is used to measure the significance of the contribution of each environmental factor to the efficacy of the drug. Its calculation expression is as follows: ; In the formula, For the first i Environmental factors and pharmacological components Y The correlation coefficient between them for j The sample at the th iStandardized observations under each environmental factor For the first i The sample mean of each environmental factor For the first j The measured efficacy content of each sample This represents the sample mean of the drug efficacy content.

[0034] The correlation coefficients are then filtered using a preset threshold, and the filtering expression is as follows: ; In the formula, For the preset threshold, for i The absolute values ​​of the correlation coefficients between environmental factors and pharmacologically active ingredients.

[0035] For example, when If the absolute value of the correlation coefficient corresponding to the shading degree is greater than or equal to 0.6 when the shading degree is 0.6, then the shading degree is determined as the core influencing factor.

[0036] After identifying the core influencing factors, initial weights are assigned to each factor based on its degree of influence. To avoid redundant weight calculations due to high correlation between factors (e.g., "light intensity" and "shading degree" essentially describe the same latitude information), a partial correlation coefficient is used for redundancy correction. Finally, based on the corrected target weight set, a comprehensive calculation is performed on each core influencing factor corresponding to the current planting area to obtain an environmental suitability index characterizing the environmental suitability of the current planting area. The expression for this index is: ; In the formula, As an environmental suitability indicator, k The total number of core impact factors For the first i The target weights of the core influencing factors For the first i A standardized dimensionless value.

[0037] S2. Based on morphological data, analyze the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and obtain medicinal contribution evaluation indicators based on the medicinal contribution data. As a preferred embodiment, the step of analyzing the medicinal contribution data of various parts of Epimedium sagittatum during its growth cycle based on morphological data, and obtaining medicinal contribution evaluation indicators based on the medicinal contribution data, includes: S21. Obtain morphological data of leaves, petioles and stems of Epimedium sagittatum during its growth cycle; S22. Analyze the morphological data of each part using a preset mapping model to obtain the estimated efficacy value of each part. S23. Based on the proportion of the projected area of ​​each part in the morphological data, determine the biomass contribution weight, and calculate the efficacy estimate of each part with the corresponding biomass contribution weight to obtain the medicinal value data of each part. S24. Combining the preset efficacy proportion weights of each part of Epimedium sagittatum during its growth cycle, the medicinal value data of each part are weighted to obtain the medicinal contribution evaluation index.

[0038] Because different parts of Epimedium sagittatum, such as leaves, petioles, and stems, exhibit variations in morphology, area distribution, biomass proportion, and medicinal value throughout its growth cycle, it is necessary to analyze the entire plant in multiple parts separately. The results from each part are then combined to obtain a medicinal contribution evaluation index that reflects the current medicinal value level of the plant.

[0039] Specifically, morphological data of the leaves, petioles, and stems of Epimedium sagittatum are obtained through image acquisition equipment, 3D scanning equipment, or manual measurement. The morphological data includes the projected area, outline, color characteristics, thickness characteristics, length characteristics, and integrity information of each part. The leaf data mainly reflects the area, fullness, and integrity of the leaf blade; the stem data mainly reflects the thickness, uprightness, and growth status of the stem.

[0040] Morphological data analysis is performed using a pre-defined mapping model to obtain a predicted efficacy value.

[0041] It should be noted that the mapping model adopts a hierarchical prediction model based on image feature extraction and machine learning regression analysis. First, the original images of each part of Epimedium sagittatum are input into the input layer; in the preprocessing layer, the images of each part are denoised, segmented, and scaled; in the feature extraction layer, the geometric, color, and texture features of each part of Epimedium sagittatum are extracted; then, in the regression prediction layer, the features are input into a random forest regression algorithm or a support vector regression algorithm to establish a mapping relationship between the morphological features of each part and the content of pharmacodynamic components, and output the estimated content of icariin, hyoscyamine A, hyoscyamine B, and hyoscyamine C in each part.

[0042] In addition, during the training process, samples of Epimedium sagittatum covering the entire growth cycle and different planting areas were collected. The samples were subjected to high-precision imaging to extract morphological feature data of each part, and the true contents of icariin, cyproterone A, cyproterone B and cyproterone C in each sample were determined by high performance liquid chromatography. These were used as supervisory labels to train and correct the mapping model.

[0043] Furthermore, based on the proportion of the projected area of ​​leaves, petioles, and stems within the whole plant, the corresponding biomass contribution weights are determined. A larger proportion of the projected area indicates a higher spatial and potential biomass proportion for that part within the whole plant. After determining the biomass contribution weights for each part, the estimated efficacy value of each part is combined with its corresponding biomass contribution weight to obtain the medicinal value data for each part. The calculation expression is as follows: ; In the formula, For the first i Data on the medicinal value of each part For the first i Estimated efficacy values ​​for each part For the first i The biomass contribution weight of each part.

[0044] It should be noted that, based on the preset part weight table, leaves, petioles, and stems are each assigned a corresponding preset efficacy weight. The medicinal value data of each part is then multiplied by its corresponding weight to obtain the medicinal contribution evaluation index, the expression of which is: ; In the formula, Evaluation indicators for contribution to medicinal use The total number of parts. For part i The weighting of drug efficacy proportion, For the first i Data on the medicinal value of each part.

[0045] In this embodiment, The weight is 3, corresponding to the leaf, petiole, and stem, and the weight of the leaf is preferably 0.7-0.9, while the weights of the petiole and stem are preferably 0.1-0.3.

[0046] S3. A dynamic evaluation model was constructed using suitability indicators and medicinal contribution evaluation indicators, and the growth quality parameters of Epimedium sagittatum were obtained by analyzing the dynamic evaluation model. In a preferred embodiment, the dynamic evaluation model constructed using suitability indicators and medicinal contribution evaluation indicators, and the analysis of Epimedium sagittatum using the dynamic evaluation model, yields the following growth quality parameters: S31. Obtain the environmental suitability index and medicinal contribution evaluation index of Epimedium sagittatum at different growth stages during its growth cycle, and construct a time-series fusion matrix. S32. Analyze the time-series fusion matrix using preset dynamic evaluation rules to obtain the corresponding growth quality parameters in the growth cycle of Epimedium sagittatum.

[0047] Specifically, by arranging the environmental suitability indicators and medicinal contribution evaluation indicators at different growth stages within the growth cycle in a chronological order, a [structure / construction] is constructed. The time-series fusion matrix is ​​expressed as follows: ; In the formula, For time-series fusion matrix, This is the growth stage. These are environmental suitability indicators corresponding to the growth stage. The evaluation index is the medicinal contribution of the corresponding growth stage.

[0048] Analysis of the time-series fusion matrix yields the growth quality parameters, the calculation expressions of which are as follows: ; In the formula, For growth quality parameters, for The dynamic weighting coefficients, for The dynamic weighting coefficients, These are environmental suitability indicators corresponding to the growth stage. The evaluation index is the medicinal contribution of the corresponding growth stage.

[0049] The dynamic evaluation rule specifically states that in the early growth stage of Epimedium sagittatum, before the plant has accumulated significant medicinal components, a weight is set as follows: (For example: =0.8, =0.2); During the mid-growth stage, environmental factors and plant morphology change rapidly, and weights are set accordingly. (For example: , =0.2); In the later stages of growth, Epimedium sagittatum approaches maturity, and a weight is set. (For example: =0.1, =0.9).

[0050] S4. Establish a quality change curve based on growth quality parameters, use the quality change curve to predict the harvest window, and obtain the quality evaluation results of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

[0051] In a preferred embodiment, the step of establishing a quality change curve based on growth quality parameters, predicting the harvest window using the quality change curve, and obtaining the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window includes: S41. Arrange the growth quality parameters of Epimedium sagittatum at different growth stages in the growth cycle according to the collection time order to form a quality parameter time series. S42. Perform curve fitting on the time series of quality parameters to obtain the quality change curve; S43. Based on the peak range of the quality change curve, predict the harvest window and obtain harvest recommendations; S44. Based on the growth quality parameters corresponding to the current growth stage, classify the quality grade of Epimedium sagittatum and obtain the quality evaluation results in combination with the harvesting recommendations.

[0052] In a preferred embodiment, the step of classifying the quality grade of Epimedium sagittatum based on the growth quality parameters corresponding to the current growth stage, and obtaining the quality evaluation result in conjunction with harvesting recommendations, includes: S441. Quality grades include superior, good, and ordinary. S442. Harvesting recommendations include direct harvesting, delayed harvesting, and early harvesting.

[0053] Specifically, the growth quality parameters are sorted in ascending order according to the corresponding sampling dates to construct a time series of quality parameters. A warning polynomial fitting algorithm is then used to fit the time series of quality parameters to construct a quality change curve, and the slope of the quality change curve is calculated. K (i.e., the rate of quality growth), when the slope K When the value starts to fall back and approaches zero, and the quality change curve reaches the peak range of the plateau period, it is determined to be the best stage for drug efficacy accumulation. When the slope becomes gentle and the growth quality parameters are at a high level, the time period is regarded as the harvest window, and harvesting suggestions are output.

[0054] The level of growth quality parameters is determined by combining a preset quality threshold range, for example: Superior: .

[0055] Good grade: .

[0056] Standard Level: .

[0057] It should be added that when the level is excellent, and the rate... K If the yield stabilizes, it is determined to be ready for direct harvesting, provided the grade is good or average, but the rate of harvesting is high. K If the rate is greater than zero, it indicates that there is still room for improvement in the efficacy of the herb, and it is recommended to delay harvesting. K If the plant is pointing downwards, it indicates that the medicinal components may be degraded due to environmental stress or over-maturation, and early harvesting is recommended.

[0058] According to a second aspect of the invention, such as Figure 2As shown, a big data analysis-based evaluation system for the growth quality of Epimedium sagittatum is provided, including: The suitability analysis module 1 is used to obtain the growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. Module 2, which analyzes the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and obtains the medicinal contribution evaluation index based on the medicinal contribution data. Module 3 for growth quality is used to construct a dynamic evaluation model using suitability indicators and medicinal contribution evaluation indicators, and to analyze Epimedium sagittatum using the dynamic evaluation model to obtain the growth quality parameters of Epimedium sagittatum. The quality evaluation module 4 is used to establish a quality change curve based on growth quality parameters, predict the harvest window using the quality change curve, and obtain the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

[0059] In summary, by acquiring growth data of *Epimedium sagittatum* in the current planting area and constructing a growth database, and further combining the correlation between environmental factors and the content of medicinal components in historical samples, environmental suitability indicators characterizing the environmental suitability of the current planting area are obtained. This allows for a quantitative evaluation of the growth conditions of *Epimedium sagittatum* at the planting area level, improving the accuracy of environmental suitability assessment. Furthermore, by analyzing the medicinal contribution data of different parts of *Epimedium sagittatum* during its growth cycle, medicinal contribution evaluation indicators are obtained. These environmental suitability indicators are then integrated with the medicinal contribution evaluation indicators to construct a dynamic evaluation model. This model yields growth quality parameters corresponding to different growth stages of *Epimedium sagittatum*, reflecting the dynamic changes in quality throughout the entire growth cycle and improving the comprehensiveness of quality evaluation.

[0060] According to a third aspect of the present invention, a computer device is provided.

[0061] Preferably, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above method.

[0062] This computer device can be a server, and its internal structure diagram can be as follows: Figure 3As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores static and dynamic information data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0063] According to a fourth aspect of the present invention, a computer-readable storage medium is provided.

[0064] Preferably, the computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the above method.

[0065] Any references to memory, storage, database, or other media used in the embodiments provided in this invention may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM may take many forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for evaluating the growth quality of Epimedium sagittatum based on big data analysis, characterized in that, include: S1. Obtain growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. S2. Based on morphological data, analyze the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and obtain medicinal contribution evaluation indicators based on the medicinal contribution data. S3. A dynamic evaluation model was constructed using suitability indicators and medicinal contribution evaluation indicators, and the growth quality parameters of Epimedium sagittatum were obtained by analyzing the dynamic evaluation model. S4. Establish a quality change curve based on growth quality parameters, use the quality change curve to predict the harvest window, and obtain the quality evaluation results of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

2. The big data analysis-based growth quality evaluation method of Epimedium sagittatum according to claim 1, characterized in that, The process involves acquiring growth and morphological data of Epimedium sagittatum in the current planting area, constructing a growth database using the growth data, and analyzing the growth database to obtain environmental suitability indicators, including: S11. Collect light environment data and land environment data of the current planting area as growth data through a preset sensor array. The light environment data includes at least shading degree, light intensity and light duration, and the land environment data includes at least air temperature and humidity, soil temperature and humidity and soil organic matter content. S12. Standardize and associate the growth data with the planting time, collection time and plant number of Epimedium sagittatum to construct a growth database; S13. Use correlation analysis to analyze the growth database and obtain environmental suitability indicators.

3. The method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to claim 2, characterized in that, The environmental suitability indicators obtained by analyzing the growth database using correlation analysis include: S131. Using the standardized growth data in the growth database as the independent variable and the pharmacodynamic component content data of historical Epimedium sagittatum samples corresponding to the current planting area as the dependent variable, a correlation analysis model is constructed. S132. Use a correlation analysis model to calculate the correlation coefficient between growth data and the content of active ingredients, and select growth data with a correlation coefficient greater than a preset threshold as core influencing factors. S133. Based on the ratio between the correlation coefficients of the core influencing factors and the content of the active ingredients, allocate the initial weights of the core influencing factors, and use the partial correlation coefficients between the factors to perform redundancy correction on the initial weights to obtain the target weight set. S134, based on the target weight set, the core influencing factors are weighted and summed to obtain the environmental suitability index that characterizes the environmental suitability of the current planting area.

4. The method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to claim 1, characterized in that, The analysis of morphological data on the medicinal contribution of different parts of Epimedium sagittatum during its growth cycle, and the resulting medicinal contribution evaluation indicators, include: S21. Obtain morphological data of leaves, petioles and stems of Epimedium sagittatum during its growth cycle; S22. Analyze the morphological data of each part using a preset mapping model to obtain the estimated efficacy value of each part. S23. Based on the proportion of the projected area of ​​each part in the morphological data, determine the biomass contribution weight, and calculate the efficacy estimate of each part with the corresponding biomass contribution weight to obtain the medicinal value data of each part. S24. Combining the preset efficacy proportion weights of each part of Epimedium sagittatum during its growth cycle, the medicinal value data of each part are weighted to obtain the medicinal contribution evaluation index.

5. The method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to claim 1, characterized in that, The dynamic evaluation model was constructed using suitability indicators and medicinal contribution evaluation indicators, and the growth quality parameters of Epimedium sagittatum were obtained by analyzing the dynamic evaluation model using the dynamic evaluation model: S31. Obtain the environmental suitability index and medicinal contribution evaluation index of Epimedium sagittatum at different growth stages during its growth cycle, and construct a time-series fusion matrix. S32. Analyze the time-series fusion matrix using preset dynamic evaluation rules to obtain the corresponding growth quality parameters in the growth cycle of Epimedium sagittatum.

6. The method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to claim 1, characterized in that, The process of establishing a quality change curve based on growth quality parameters, predicting the harvest window using the quality change curve, and obtaining the quality evaluation results of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window includes: S41. Arrange the growth quality parameters of Epimedium sagittatum at different growth stages in the growth cycle according to the collection time order to form a quality parameter time series. S42. Perform curve fitting on the time series of quality parameters to obtain the quality change curve; S43. Based on the peak range of the quality change curve, predict the harvest window and obtain harvest recommendations; S44. Based on the growth quality parameters corresponding to the current growth stage, classify the quality grade of Epimedium sagittatum and obtain the quality evaluation results in combination with the harvesting recommendations.

7. The method for evaluating the growth quality of Epimedium sagittatum based on big data analysis according to claim 6, characterized in that, The process of classifying Epimedium sagittatum into quality grades based on the growth quality parameters corresponding to the current growth stage, and obtaining quality evaluation results by combining harvesting recommendations, includes: S441. Quality grades include superior, good, and ordinary. S442. Harvesting recommendations include direct harvesting, delayed harvesting, and early harvesting.

8. A big data analysis-based growth quality evaluation system for Epimedium sagittatum, used to implement the big data analysis-based growth quality evaluation method for Epimedium sagittatum as described in any one of claims 1-7, characterized in that, include: The suitability analysis module is used to obtain growth and morphological data of Epimedium sagittatum in the current planting area, construct a growth database using the growth data, and analyze the growth database to obtain environmental suitability indicators. The medicinal contribution analysis module is used to analyze the medicinal contribution data of each part of Epimedium sagittatum during its growth cycle, and to obtain medicinal contribution evaluation indicators based on the medicinal contribution data. The growth quality module is used to construct a dynamic evaluation model using suitability indicators and medicinal contribution evaluation indicators, and to analyze Epimedium sagittatum using the dynamic evaluation model to obtain the growth quality parameters of Epimedium sagittatum. The quality evaluation module is used to establish a quality change curve based on growth quality parameters, predict the harvest window using the quality change curve, and obtain the quality evaluation result of Epimedium sagittatum based on the growth quality parameters and the predicted harvest window.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for evaluating the growth quality of Epimedium sagittatum based on big data analysis as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for evaluating the growth quality of Epimedium sagittatum based on big data analysis as described in any one of claims 1-7.

Images