Traditional Chinese medicinal material active component traceability detection system
By combining IoT sensors and high-resolution Raman spectrometers with XGBoost and support vector machines for multi-dimensional detection, the problem of adulteration of parts in traditional Chinese medicine traceability testing has been solved, enabling precise traceability of the origin and parts of Chinese medicinal materials, and improving detection accuracy and safety.
Patent Information
- Application Number
- CN202511112699.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-09
- Publication Date
- 2025-11-14
AI Technical Summary
Traditional methods for tracing and testing Chinese medicinal materials cannot identify adulteration patterns where the materials actually originate from the labeled production area but the main active ingredients come from the same low-value parts, leading to economic losses of high-value medicinal materials and risks in clinical medication.
The system uses IoT sensors to collect environmental parameters throughout the entire cultivation cycle of Chinese medicinal herbs, and combines this with a high-resolution Raman spectrometer for point-by-point scanning. It then uses a pre-trained XGBoost model and support vector machine for multi-dimensional verification. By analyzing the correlation between environmental parameters and component distribution, the system determines the authenticity of the place of origin and part of the plant, thus forming a closed-loop detection mechanism.
It significantly improves the accuracy of matching origin and part of origin, reduces the risk of misjudgment, ensures the quality control of Chinese medicinal materials and the safety of clinical medication, and reduces economic losses and health risks caused by adulteration.
Smart Images
Figure FT_1 
Figure FT_2 
Figure FT_3
Abstract
Description
Technical Field
[0001] This invention relates to the field of traditional Chinese medicine testing technology, specifically a traceability testing system for active ingredients in traditional Chinese medicine. Background Technology
[0002] As the core raw material of the traditional Chinese medicine industry, the quality traceability of Chinese medicinal materials is crucial to ensuring medication safety and market fairness. Traditional traceability testing often relies on single-dimensional environmental parameters and component thresholds to determine the authenticity of the place of origin, or to verify the part of the medicinal material through morphological observation and simple component detection. However, with the upgrading of adulteration methods, a new counterfeiting model of "authentic place of origin but adulterated parts" has emerged in the market. That is, the medicinal material is actually produced in the marked production area, but the main active ingredients come from the same low-value parts, such as using the rootlets of Panax notoginseng to impersonate the main root. This kind of adulteration can pass the environmental and component matching verification of traditional place of origin traceability, and is difficult to detect through conventional part detection due to morphological similarity. Current technology lacks the ability to verify both the authenticity of the place of origin and the authenticity of the part, resulting in economic losses of high-value medicinal materials and risks to clinical medication. Summary of the Invention
[0003] This application provides a traceability and detection system for active ingredients in Chinese medicinal materials, which solves the problem that traditional traceability and detection methods for Chinese medicinal materials often focus on a single dimension and cannot identify new adulteration patterns where the origin is real but the parts are adulterated. That is, the medicinal materials are actually produced in the marked production area, but the main active ingredients come from the same low-value parts, resulting in economic losses of high-value medicinal materials and risks to clinical use. This system effectively solves the hidden adulteration problem that traditional methods cannot cover.
[0004] To achieve the above objectives, the embodiments of this application disclose the following technical solutions:
[0005] On the one hand, this solution discloses a method for tracing and detecting the active ingredients of traditional Chinese medicine, including the following steps: Step S1: Collect environmental parameters of the target traditional Chinese medicine throughout its entire planting cycle using IoT sensors, and scan multiple parts of the traditional Chinese medicine point by point using a high-resolution Raman spectrometer to obtain the spatial distribution map of the components in each part; Step S2: Input the environmental parameters into a pre-trained origin verification model and output the theoretical origin matching probability; the origin verification model is trained based on historical planting data and is used to characterize the correlation between environmental parameters and the authenticity of the origin; Step S3: Input the spatial distribution map of the components in each part into a pre-trained part verification model and output the standard component intensity threshold matching degree of each part; the part verification model is trained based on historical genuine part data and is used to characterize the correlation between part and component distribution; Step S4: Determine the authenticity of the origin and part of the traditional Chinese medicine based on the theoretical origin matching probability and the component distribution matching degree of each part.
[0006] On the other hand, this solution discloses a traceability and detection system for active ingredients in traditional Chinese medicine, including:
[0007] The data acquisition module is used to collect environmental parameters throughout the entire cultivation cycle of the target Chinese medicinal herb using IoT sensors, and to obtain spatial distribution maps of components in each part using a high-resolution Raman spectrometer. The model validation module is used to input the environmental parameters into a pre-trained machine learning model and output the theoretical origin matching probability; and to input the component spatial distribution maps into a pre-trained part validation model and output the component intensity threshold matching degree for each part. The result output module is used to determine the authenticity of the origin and part of the Chinese medicinal herb based on the theoretical origin matching probability and the component intensity threshold matching degree.
[0008] This invention presents a traceability and detection system for active ingredients in traditional Chinese medicine (TCM) materials. By innovatively integrating origin verification and part verification, it effectively solves the novel adulteration problem of "authentic origin but adulterated parts," which traditional methods cannot identify. Based on the correlation between environmental parameters and component distribution, the system utilizes a pre-trained XGBoost model and fusion formula to optimize the origin verification probability. Simultaneously, it uses a support vector machine combined with a weighted component matching degree formula to accurately determine the authenticity of the part, forming a multi-dimensional verification closed loop of "environment-component-part." Compared to traditional single-dimensional detection, this system not only improves the matching accuracy between origin and part but also uses a dynamic correction formula to inversely optimize the origin probability based on the part verification results, strengthening the intrinsic correlation between the two and significantly reducing the risk of misjudgment. In practical applications, this system can accurately identify the behavior of low-value parts being passed off as high-value parts, providing more reliable technical support for the quality control, market circulation, and clinical medication safety of TCM materials. It effectively reduces economic losses and health risks caused by adulteration, promoting the development of TCM material traceability and detection towards a more comprehensive and accurate direction. Attached Figure Description
[0009] Figure 1 This is a flowchart of the method according to Embodiment 1 of the present invention; Figure 2 This is an overall block diagram of the system according to Embodiment 2 of the present invention; Figure 3 This is an interaction diagram of the system in Embodiment 2 of the present invention. Detailed Implementation
[0010] Specific embodiments of the invention will now be described in detail. Although the invention is described in conjunction with these specific embodiments, it should be understood that the invention is not intended to be limited to these specific embodiments. Rather, these embodiments are intended to cover alternative, modified, or equivalent embodiments that may be included within the spirit and scope of the invention as defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. The invention may be practiced without some or all of these specific details. In other instances, well-known processes have not been described in detail so as not to unnecessarily obscure the invention.
[0011] When used in conjunction with the terms "comprising," "method comprising," or similar language in this specification and appended claims, the singular forms "a," "some," and "the" include plural references unless the context clearly indicates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0012] Application Overview: In existing technologies, the traceability and testing of Chinese medicinal materials mainly rely on single-dimensional environmental parameters and component thresholds to determine the authenticity of the origin, or to verify the part of the medicinal material through morphological observation and simple component detection. For example, traditional methods determine the origin by detecting environmental parameters, such as soil trace elements, temperature, and humidity, and their correlation with medicinal material components, such as saponin content, or by verifying the part of the medicinal material through chemical staining and morphological comparison. However, such methods have significant technical defects. When the medicinal material actually comes from the labeled production area, but the main active ingredients come from the same low-value part, such as using the fibrous roots of Panax notoginseng to impersonate the main root, traditional testing cannot find the contradiction in the authenticity of the origin through the correlation between environmental parameters and components, and the morphological similarity makes it difficult to identify the differences in parts through conventional testing. This leads to high-value medicinal materials being adulterated with low-value parts but still being judged as qualified products.
[0013] To address the aforementioned issues, this solution utilizes a pre-trained XGBoost model and a fusion formula to optimize the origin verification probability. Simultaneously, it employs a support vector machine combined with a weighted component matching degree formula to accurately determine the authenticity of the part, forming a multi-dimensional verification loop encompassing environment, component, and part. Compared to traditional single-dimensional detection, this system not only improves the matching accuracy between origin and part but also uses a dynamic correction formula to inversely optimize the origin probability based on the part verification results, strengthening the intrinsic correlation between the two and significantly reducing the risk of misjudgment.
[0014] Example 1
[0015] A method for tracing and detecting the active ingredients of traditional Chinese medicinal materials includes the following steps: Step S1: Collect environmental parameters throughout the entire planting cycle of the target traditional Chinese medicinal material using IoT sensors, and scan multiple parts of the material point-by-point using a high-resolution Raman spectrometer to obtain the spatial distribution map of the components in each part; Step S2: Input the environmental parameters into a pre-trained origin verification model and output the theoretical origin matching probability; the origin verification model is trained based on historical planting data and is used to characterize the correlation between environmental parameters and the authenticity of the origin; Step S3: Input the spatial distribution map of the components in each part into a pre-trained part verification model and output the standard component intensity threshold matching degree of each part; the part verification model is trained based on historical genuine part data and is used to characterize the correlation between part and component distribution; Step S4: Determine the authenticity of the origin and part of the traditional Chinese medicinal material based on the theoretical origin matching probability and the component distribution matching degree of each part.
[0016] In step S1, the environmental parameters are collected by IoT sensors deployed in the planting area at a frequency of at least once a day; the spectral imaging technology is achieved by a high-resolution Raman spectrometer.
[0017] Specifically, the system collects environmental parameters such as annual average temperature, humidity difference, soil trace elements, and diurnal temperature difference through an IoT sensor network of field weather stations. The collection frequency is once daily, with an IoT sensor deployment density of ≥50 sensors / square kilometer. Intensified collection is initiated when the daily temperature difference is ≥10℃, and the diurnal temperature difference error range is ±2℃. This is combined with a high-resolution Raman spectrometer for micron-level scanning of the medicinal herb cross-section at a scanning speed ≤1mm / s, obtaining a spatial distribution map of components covering the cortex, pith, and phloem with a resolution of 5μm×5μm×5μm. This scheme further proposes that in step S2, the origin verification model is a classification model constructed using the XGBoost algorithm, with input features being the time-series statistical values of the environmental parameters and output being the theoretical origin matching probability.
[0018] This embodiment further proposes that, unlike traditional origin verification models which only output fixed probability values, this solution can dynamically adjust the origin probability by combining the part verification results, thus avoiding misjudgments where the origin is genuine but the part is adulterated.
[0019] At the data processing level, the system employs the XGBoost algorithm to construct a provenance verification model. Through SHAP value analysis, key features such as annual average temperature (weighted at 0.32) and soil copper content (weighted at 0.21) are selected. This is combined with a dynamic correction formula to dynamically calibrate the provenance probability. This correction formula introduces location matching degree as a feedback factor and uses the β_j coefficient, determined through cross-validation, with primary root β=0.3 and fibrous root β=0.1, to nonlinearly correct the original provenance probability.
[0020] The corrected formula is: ;
[0021] in, : The original output probability of the origin validation model;
[0022] : No. The degree of matching of component distribution in each part;
[0023] Weighting coefficients for the influence of part of the plant on the place of origin;
[0024] The above formula uses part matching degree to inversely correct the origin probability, strengthening the correlation between origin and part. Based on the principle of conditional probability in probability theory, this formula uses a term-by-term product to implement weighted constraints on the origin probability of each part. The value of β_j is determined through grid search and K-fold cross-validation to ensure the model's sensitivity adapts to different part features. The part validation model uses a support vector machine with radial basis function kernel, solving a convex quadratic programming problem using the Lagrange multiplier method.
[0025] This embodiment further proposes to use the weighted component matching degree formula as one of the input features of the XGBoost model, replacing the single intensity value, so that the origin validation model can simultaneously consider the correlation between environmental parameters and the distribution of site components. The formula is modified as follows:
[0026] ;
[0027] The above formula allows origin verification to not only rely on environmental parameters, but also incorporate the verification results of component distribution, further addressing the issue of authentic origin but adulterated parts.
[0028] This solution further proposes that, in step S3, the part verification model is a classification model constructed by support vector machine. In the embodiment, the convex quadratic programming objective function of support vector machine is used, the input feature is the peak intensity of the component spatial distribution map of each part, and the output is the component distribution matching degree.
[0029] In traditional methods, the matching degree of component distribution may be calculated solely through comparison of single peak intensities. However, this scheme needs to consider the different sensitivity of different parts to component distribution, therefore a weighted fusion formula is designed:
[0030] ;
[0031] in, : No. Measured component intensities at each location;
[0032] : No. Standard component intensity thresholds for each part;
[0033] : No. Deviation of environmental parameters in the production area of each part; deviation of environmental parameters in the production area can be the deviation of diurnal temperature difference;
[0034] : Average environmental parameters of standard production areas;
[0035] , : The super-parameters adjusted according to the medicinal herb varieties.
[0036] The above formula, through the dual calculation of intensity ratio and environmental deviation penalty, better reflects the actual scenario of the influence of the production environment on the distribution of components. Considering that a single intensity comparison cannot reflect the impact of the environment on the components of the part, the formula combines the proportional weight α of the measured and standard intensities with the weight 1−α of the exponential penalty term for environmental parameter deviation, where σ is the deviation tolerance parameter determined according to the medicinal herb variety, making the matching degree calculation more consistent with the actual planting scenario.
[0037] This solution further proposes that, in step S4, if the theoretical origin matching probability is greater than the preset origin threshold and the component distribution matching degree of all parts is greater than the preset part threshold, then it is determined to be a genuine product with both the origin and the part being genuine; if the theoretical origin matching probability is greater than the preset origin threshold but the component distribution matching degree of some parts is less than the preset part threshold, then it is determined to be a counterfeit product with a genuine origin but adulterated parts.
[0038] The preset origin threshold is 90%, and the preset part threshold is 85%. If the theoretical origin matching probability is greater than 90% but the part component distribution matching degree is less than 85%, it is determined as "the origin is real but the part is adulterated".
[0039] This solution further proposes that, in step S4, the preset origin threshold and preset part threshold are set according to the pharmacopoeia standards of the medicinal material varieties.
[0040] Based on the statistical characteristics of environmental parameters for major medicinal herb producing areas as defined in the Chinese Pharmacopoeia, cluster analysis of historical planting data was used to map environmental parameters from producing areas meeting Pharmacopoeia standards into a probability space, with the probability value corresponding to the top 90% confidence interval taken as the threshold. Referring to the minimum limits for component content in medicinal herb parts as specified in the Chinese Pharmacopoeia, Raman spectral intensity calibration was used to map the spectral characteristics of parts meeting these standards into a probability space, with the matching degree corresponding to the top 85% confidence interval taken as the threshold.
[0041] This solution further proposes that, in step S2, before calculating the theoretical origin matching probability, the origin verification model standardizes the environmental parameters to eliminate dimensional differences. In this embodiment, the standardization process of the origin verification model employs Z-score standardization or Min-Max normalization.
[0042] Example 2
[0043] The traceability and detection system for active ingredients in traditional Chinese medicinal materials includes:
[0044] The data acquisition module is used to collect environmental parameters throughout the entire planting cycle of the target Chinese medicinal materials using IoT sensors, and to obtain the spatial distribution maps of components in each part using a high-resolution Raman spectrometer; the model verification module is used to input the environmental parameters into a pre-trained machine learning model and output the theoretical origin matching probability; and to input the component spatial distribution maps into a pre-trained part verification model and output the component intensity threshold matching degree for each part; the result output module is used to determine the authenticity of the origin and part of the Chinese medicinal materials based on the theoretical origin matching probability and the component intensity threshold matching degree.
[0045] The data acquisition module acquires environmental parameters and spectral data in real time, which are then standardized and fed into the model validation module. The origin validation submodule outputs the original probability and dynamically corrects it by combining the matching degree of the part validation submodule. The result output module determines the result based on the 90% origin threshold and the 85% part threshold. The data storage module saves the data synchronously for model iteration.
[0046] This solution further proposes that the data acquisition module includes: an IoT planting environment sensor group, deployed at a field weather station, used to collect annual average temperature, humidity difference, soil trace elements and diurnal temperature difference; and a high-resolution Raman spectrometer, set up in the medicinal material processing workshop, used to scan medicinal material slices point by point, with a scanning resolution of 5μm.
[0047] The model validation module includes: an origin validation submodule, which integrates a classification model built with the XGBoost algorithm to calculate the theoretical origin matching probability based on environmental parameters; and a part validation submodule, which integrates a classification model built with support vector machines to calculate the component intensity threshold matching degree based on the component spatial distribution map.
[0048] The result output module includes: a first judgment unit for judging whether the theoretical origin matching probability is greater than 90%; a second judgment unit for judging whether the component intensity threshold matching degree of all parts is greater than 85%; and a result output unit for outputting "genuine product" when both the first and second judgment units are true, otherwise outputting "genuine origin but adulterated parts" or "both origin and parts are adulterated". This solution further proposes that the system also includes a data storage module for storing historical planting data, historical genuine product part data, and real-time collected environmental parameters and component spatial distribution maps.
[0049] In this embodiment, system visualization can display time-series curves of environmental parameters, 3D heatmaps of component distribution, and trends in verification probability changes through a dynamic dashboard.
[0050] In an example of tracing and detecting the source of Panax notoginseng, the method and system for tracing and detecting the active ingredients of this traditional Chinese medicine are applied. First, the data acquisition module deploys 55 IoT sensors per square kilometer in the Panax notoginseng planting area in Wenshan, Yunnan, to collect environmental parameters such as annual average temperature and soil trace elements once a day. When the diurnal temperature difference reaches 10°C, encrypted data collection is initiated. At the same time, in the processing workshop, a high-resolution Raman spectrometer is used to perform micron-level scanning of the cross-section of the main root and fibrous roots of Panax notoginseng at a speed of 0.8 mm / s to obtain a spatial distribution map of the components with a resolution of 5 μm × 5 μm × 5 μm, covering the cortex, pith and phloem.
[0051] Next, the model validation module inputs the environmental parameters into the XGBoost origin validation model after Z-score standardization. This model is trained based on historical planting data in Wenshan area. Through SHAP value analysis, the annual average temperature weight is 0.32 and the soil copper content weight is 0.21, outputting a theoretical origin matching probability of 92%. Then, the spatial distribution map of each part is input into the part validation model constructed by support vector machine, and the matching degree of the main root component distribution is calculated to be 88% and that of the fibrous roots is 80%. The β coefficient of the main root is taken as 0.3 and that of the fibrous roots is taken as 0.1. The original origin probability is corrected by substituting into the correction formula.
[0052] Meanwhile, the matching degree of component distribution is calculated according to the formula. , Based on the characteristics of Panax notoginseng varieties, the final output module determines that the theoretical origin matching probability is 92%, which is greater than the preset origin threshold of 90%. However, the matching degree of the fibrous root component distribution is 80%, which is less than the preset part threshold of 85%. Therefore, the Panax notoginseng is determined to be a counterfeit product with genuine origin but adulterated fibrous roots. All data is synchronously stored in the data storage module. The entire process is displayed through the system's visual interface, showing the environmental parameter change curves, component distribution heatmaps, and verification results, realizing full-cycle traceability and detection of Panax notoginseng from planting to processing.
[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation methods of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications should be covered within the scope of the technical solutions claimed in the present invention.
Claims
1. A method for tracing and detecting the active ingredients in traditional Chinese medicinal materials, characterized in that, The process includes the following steps: Step S1: Collect environmental parameters throughout the entire cultivation cycle of the target Chinese medicinal herb using IoT sensors, and scan multiple parts of the herb point-by-point using a high-resolution Raman spectrometer to obtain the spatial distribution map of the components in each part; Step S2: Input the environmental parameters into a pre-trained origin verification model and output the theoretical origin matching probability; the origin verification model is trained based on historical planting data and is used to characterize the correlation between environmental parameters and the authenticity of the origin; Step S3: Input the spatial distribution map of the components in each part into a pre-trained part verification model and output the standard component intensity threshold matching degree for each part; the part verification model is trained based on historical genuine part data and is used to characterize the correlation between part and component distribution; Step S4: Determine the authenticity of the origin and part of the Chinese medicinal herb based on the theoretical origin matching probability and the component distribution matching degree of each part.
2. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S1, the environmental parameters include annual average temperature, humidity difference, soil trace elements, and diurnal temperature difference; the high-resolution Raman spectrometer's scanning range covers the cortex, pith, and phloem of the medicinal material slices.
3. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S2, the origin verification model is a classification model constructed using the XGBoost algorithm. The input features are the time-series statistical values of the environmental parameters, and the output is the theoretical origin matching probability. The theoretical origin matching probability is adjusted using a dynamic correction formula, which is: ； in, : The original output probability of the origin validation model; : No. The degree of matching of component distribution in each part; Weighting coefficients for the influence of part of the plant on the place of origin; The weighted component matching degree formula is used as one of the input features of the XGBoost model, replacing the single intensity value. This allows the origin validation model to consider the correlation between environmental parameters and the distribution of site components simultaneously. The formula is modified as follows: 。 4. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S3, the part verification model is a classification model constructed using support vector machines. The input features are the peak intensities of the component spatial distribution maps of each part, and the output is the component distribution matching degree. The standard component intensity threshold matching degree is calculated using a fusion formula, which is: ； in, : No. Measured component intensities at each location; : No. Standard component intensity thresholds for each part; : No. Deviations in the environmental parameters of the production area for each part; : Average environmental parameters of standard production areas; , : The super-parameters adjusted according to the medicinal herb varieties.
5. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S4, if the theoretical origin matching probability is greater than the preset origin threshold and the component distribution matching degree of all parts is greater than the preset part threshold, it is determined to be a genuine product with both genuine origin and genuine part; if the theoretical origin matching probability is greater than the preset origin threshold but the component distribution matching degree of some parts is less than the preset part threshold, it is determined to be a counterfeit product with genuine origin but adulterated parts.
6. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S2, before calculating the theoretical origin matching probability, the origin verification model standardizes the environmental parameters to eliminate dimensional differences.
7. The method for tracing and detecting active ingredients in traditional Chinese medicinal materials according to claim 1, characterized in that, In step S4, the preset origin threshold and preset part threshold are set according to the pharmacopoeia standards of the medicinal material varieties.
8. A traceability and detection system for active ingredients in traditional Chinese medicinal materials, characterized in that, include: The data acquisition module is used to collect environmental parameters throughout the entire planting cycle of the target Chinese medicinal materials through IoT sensors, and to obtain the spatial distribution map of the components of each part through a high-resolution Raman spectrometer. The model verification module is used to input the environmental parameters into a pre-trained machine learning model and output the theoretical origin matching probability; input the component spatial distribution map into a pre-trained part verification model and output the component intensity threshold matching degree of each part; the result output module is used to determine the authenticity of the origin and part of the Chinese medicinal material based on the theoretical origin matching probability and the component intensity threshold matching degree.
9. The traceability and detection system for active ingredients in traditional Chinese medicine according to claim 8, characterized in that, The data acquisition module includes: an IoT planting environment sensor group, deployed at a field weather station, used to collect annual average temperature, humidity difference, soil trace elements and diurnal temperature difference; and a high-resolution Raman spectrometer, set up in the medicinal material processing workshop, used to scan medicinal material slices point by point. The model validation module includes: an origin validation submodule, which integrates a classification model built with the XGBoost algorithm to calculate the theoretical origin matching probability based on environmental parameters; and a part validation submodule, which integrates a classification model built with support vector machines to calculate the component intensity threshold matching degree based on the component spatial distribution map. The result output module includes: The first judgment unit is used to determine whether the theoretical origin matching probability is greater than the preset origin threshold. The second judgment unit is used to determine whether the component intensity threshold matching degree of all parts is greater than the preset part threshold; the result output unit is used to output the judgment result when both the first judgment unit and the second judgment unit are true.
10. The traceability and detection system for active ingredients in traditional Chinese medicine according to claim 6, characterized in that, The system also includes a data storage module for storing historical planting data, historical data on genuine plant parts, and real-time collected environmental parameters and spatial distribution maps of components.