Full-automatic integrated traditional Chinese medicine detection method and equipment

Abstract

The invention provides a full-automatic integrated traditional Chinese medicine detection method and equipment. Belongs to the technical field of traditional Chinese medicine detection and automation. The detection method comprises the following steps: shooting high-definition photos of traditional Chinese medicinal materials through a high-precision camera and an image processing unit which are arranged on a variety screening module, and comparing the high-definition photos with a built-in traditional Chinese medicinal material image database through a preset algorithm to automatically identify the types of the traditional Chinese medicinal materials; multi-dimensional quality detection is carried out on the traditional Chinese medicinal materials through multiple sensors integrated in the quality detection module; through the combination of the high-precision camera and the image processing unit and the application of the deep learning algorithm, the types of the traditional Chinese medicinal materials can be quickly and accurately identified, the detection efficiency is improved, and the possibility of human errors is also reduced.

Description

Technical Field

[0001] The invention provides a fully automatic integrated traditional Chinese medicine detection method and equipment, belonging to the technical field of traditional Chinese medicine detection and automation. Background Art

[0002] The traditional Chinese medicine testing process is cumbersome and relies on the experience and judgment of professionals. It is not only inefficient, but also easily affected by subjective factors, making it difficult to ensure the accuracy and consistency of the test results. With the advancement of science and technology, although some automated testing equipment has been launched, these devices often have single functions and cannot achieve integrated operations from variety identification to quality assessment. They are also not adaptable to the diverse shapes and textures of Chinese medicinal materials. Therefore, it is particularly important to develop a fully automatic Chinese medicine testing equipment that can comprehensively solve the above problems and integrate variety screening, quality inspection, automatic tumbling and intelligent control. Summary of the invention

[0003] The present invention provides a fully automatic integrated Chinese medicine detection method and equipment to solve the problems mentioned in the above background technology: The present invention proposes a fully automatic integrated traditional Chinese medicine detection method, the detection method comprising: S1. The high-precision camera and image processing unit equipped in the variety screening module take high-definition photos of Chinese medicinal materials, and compare them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; S2, through the multiple sensors integrated in the quality detection module, multi-dimensional quality detection of Chinese medicinal materials is carried out; S3, based on the mechanical arm and rotating platform equipped with the tumbling module, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module; S4. Receive data from each module through the control module, execute the preset algorithm logic, control the tumbling module, compare the data from the variety screening module to confirm the type of Chinese medicinal materials, and summarize the information from the quality inspection module to form a final inspection report.

[0004] The present invention provides a fully automatic integrated Chinese medicine detection device, the device comprising: Variety screening module: It uses a high-precision camera and image processing unit to take high-definition photos of Chinese medicinal materials, and compares them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; Quality detection module: Through the integration of multiple sensors, including near-infrared spectrometer, moisture meter and heavy metal detector, multi-dimensional quality detection of Chinese medicinal materials is carried out, including moisture content, active ingredient content and heavy metal residue; Tumbling module: Based on the robotic arm and rotating platform, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module to ensure that all sides can be effectively photographed and tested. It is especially suitable for Chinese medicinal materials with complex shapes that are difficult to observe directly. Control module: responsible for receiving data from each module, executing preset algorithm logic, controlling the tumbling module, comparing the data from the variety screening module to confirm the type of Chinese medicinal materials, and summarizing the information from the quality inspection module to form the final inspection report.

[0005] The beneficial effects of the present invention are as follows: through the combination of a high-precision camera and an image processing unit, and the application of a deep learning algorithm, the types of Chinese medicinal materials can be quickly and accurately identified, the detection efficiency is improved, and the possibility of human error is reduced; the quality detection module integrating multiple sensors can perform multi-dimensional quality assessment of Chinese medicinal materials, including near-infrared spectroscopy analysis, moisture content determination, heavy metal element trace analysis, etc., to ensure the quality and safety of Chinese medicinal materials; the automatic tumbling module based on a mechanical arm and a rotating platform can perform comprehensive detection without damaging the Chinese medicinal materials, thereby improving the accuracy and reliability of the detection; the control module can receive and process data from each detection module, and through The preset algorithm logic is used for data analysis, and a detailed test report is automatically generated, so that users can quickly understand the test results and quality status of Chinese medicinal materials. In the process of species identification, the uncertainty processing method is combined with other features for secondary confirmation, which improves the accuracy and robustness of identification. A virtual model is constructed through 3D modeling software or a physical simulation platform, and a tumbling simulation is performed. The tumbling strategy is optimized in combination with actual test data to ensure the safety and effectiveness of the tumbling process. The possible quality risks in Chinese medicinal materials are identified and analyzed, and a warning threshold is set. When the test results reach or exceed the warning threshold, a warning signal is issued, which helps to promptly discover and deal with potential quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 It is a step diagram of the method of the present invention; Figure 2 This is a module diagram of the device described in the present invention. DETAILED DESCRIPTION

[0007] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0008] One embodiment of the present invention, as Figure 1 As shown, a fully automatic integrated traditional Chinese medicine detection method, the detection method comprises: S1. The high-precision camera and image processing unit equipped in the variety screening module take high-definition photos of Chinese medicinal materials, and compare them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; S2. Using a variety of sensors integrated in the quality detection module, including a near-infrared spectrometer, a moisture meter, and a heavy metal detector, to perform multi-dimensional quality detection on the Chinese medicinal materials, including moisture content, active ingredient content, and heavy metal residues; S3, based on the mechanical arm and rotating platform equipped with the tumbling module, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module; S4. Receive data from each module through the control module, execute the preset algorithm logic, control the working rhythm of the tumbling module, compare the data of the variety screening module to confirm the type of Chinese medicinal materials, and summarize the information of the quality inspection module to form a final inspection report.

[0009] The working principle of the above technical solution is as follows: a high-precision camera is used to take high-definition photos of Chinese medicinal materials to ensure that the images are clear and rich in details; the image processing unit pre-processes the taken photos, such as denoising, enhancing contrast, etc., to improve the image quality; the processed images are feature extracted through a preset algorithm, and compared with the built-in Chinese medicine image database to automatically identify the type of Chinese medicinal materials; near-infrared spectroscopy technology is used to quickly and non-destructively detect the content of effective ingredients in Chinese medicinal materials; the moisture content of Chinese medicinal materials is accurately measured through specific measurement principles (such as capacitance method, resistance method, etc.); heavy metal residues in Chinese medicinal materials are detected using principles such as electrochemistry, optics or mass spectrometry to ensure that Chinese medicinal materials safety; according to the instructions of the control module, the robotic arm grabs the Chinese medicinal materials and places them on the rotating platform, and the rotating platform drives the Chinese medicinal materials to roll; the control module sends instructions to the rolling module according to the requirements of the variety screening module and the quality inspection module to ensure that all sides of the Chinese medicinal materials can be effectively photographed and inspected; the control module receives data from the variety screening module, the quality inspection module and the rolling module; executes the preset algorithm logic to process and analyze the received data; according to the processing results, the control module sends instructions to the rolling module to adjust its working rhythm; at the same time, the data of the variety screening module is compared to make a final confirmation of the type of Chinese medicinal materials, and the information of the quality inspection module is summarized to form a final inspection report.

[0010] The effects of the above technical solutions are as follows: through the integration of high-precision cameras, image processing units and multiple sensors, automatic identification and multi-dimensional quality inspection of Chinese medicinal materials are realized, greatly improving the efficiency and accuracy of inspection; the cooperation of the robotic arm and the rotating platform enables the Chinese medicinal materials to roll automatically, ensuring that all sides can be effectively photographed and inspected, reducing the tediousness and errors of manual operations; the variety screening module uses high-precision cameras and preset algorithms to quickly and accurately identify the types of Chinese medicinal materials, avoiding identification errors caused by human factors in traditional methods; the quality inspection module uses multiple sensors such as near-infrared spectrometers, moisture meters and heavy metal detectors to perform multi-dimensional quality inspections on Chinese medicinal materials, which can comprehensively reflect the quality status of Chinese medicinal materials and ensure the safety and effectiveness of Chinese medicinal materials; this method is particularly suitable for Chinese medicinal materials with complex shapes that are not easy to observe directly. Automatic rolling and all-round shooting can ensure that all sides of Chinese medicinal materials can be effectively inspected, improving the comprehensiveness and accuracy of the inspection; at the same time, the method is also applicable to Chinese medicinal materials of different types and specifications, and has strong versatility and flexibility; the control module can receive data from each module and execute preset algorithm logic to confirm the type of Chinese medicinal materials, while summarizing the information of the quality inspection module to form a final inspection report; this data integration and analysis method not only improves the accuracy and reliability of the inspection, but also provides strong data support for the quality control and traceability of Chinese medicinal materials; the application of this method can promote the modernization and standardization of the Chinese medicine industry, and improve the quality level and market competitiveness of Chinese medicinal materials; at the same time, the method can also provide scientific basis and technical support for the research and development, production, and sales of Chinese medicine, and promote the sustainable development of the Chinese medicine industry.

[0011] In one embodiment of the present invention, the S1 includes: S11. Use the high-precision camera of the variety screening module and configure different light sources to capture the subtle features of the surface of Chinese medicinal materials, such as texture, gloss, color gradient, etc.; S12, preprocessing the collected image through an image processing unit, wherein the preprocessing includes denoising, contrast enhancement, and edge detection; S13, extract features from the preprocessed images based on deep learning algorithms, identify key features of Chinese medicinal materials, and use attention mechanisms to enhance focus on key areas; S14, inputting the extracted feature vector into the trained deep learning classifier, comparing it with the known Chinese medicinal material features in the built-in Chinese medicinal material image database, and identifying the type of Chinese medicinal material by calculating the similarity between the feature vectors; S15. If there are multiple high-matching options in the identification results, a second confirmation is performed using the uncertainty processing method combined with other characteristics of the Chinese medicinal materials.

[0012] The working principle of the above technical solution is as follows: as the core component of the variety screening module, the camera is responsible for capturing the subtle features of the surface of Chinese medicinal materials. In order to obtain the information of Chinese medicinal materials more comprehensively and accurately, the system is equipped with different light sources, such as natural light, ultraviolet light and infrared light. These light sources can reveal the characteristics of Chinese medicinal materials such as texture, gloss and color gradient under different lighting conditions; Gaussian filtering, median filtering and other algorithms are used to denoise the collected images to reduce noise interference in the image and improve image quality; the contrast of the image is enhanced by histogram equalization, adaptive contrast adjustment and other methods to make the characteristics of Chinese medicinal materials more distinct and facilitate subsequent feature extraction; the edge detection of the image is performed using algorithms such as Canny edge detection and Sobel operator to extract the edge features of Chinese medicinal materials, providing a basis for subsequent feature extraction and recognition; the pre-processed images are feature extracted based on pre-trained models such as ResNet and VGG. These pre-trained models have been trained on large-scale image datasets and can learn rich image feature representations. Through transfer learning, these models are applied to feature extraction of Chinese herbal medicine images, which can efficiently extract the key features of Chinese herbal medicines; in order to enhance the focus on key areas, the system introduces an attention mechanism. Through the attention mechanism, the system can automatically identify the key areas in the Chinese herbal medicine images and give these areas higher weights, thereby improving the accuracy and efficiency of feature extraction; the extracted feature vectors are input into the trained deep learning classifier and compared with the known Chinese herbal medicine features in the built-in Chinese herbal medicine image database. The classifier can use models such as support vector machine SVM, random forest RF, or fully connected layers in deep learning. By calculating the similarity between feature vectors (such as cosine similarity and Euclidean distance), the system can identify the types of Chinese herbal medicines; if there are multiple high-matching options in the recognition results, the system uses uncertainty processing methods for secondary confirmation. These methods include Bayesian classifiers or ensemble learning methods (such as Adaboost, Bagging), etc. By combining other characteristics of Chinese medicinal materials (such as smell, touch, etc.), the system can further improve the accuracy and reliability of recognition; in some cases, due to the wide variety and complex characteristics of Chinese medicinal materials, the system may not be able to accurately identify them directly through image features. At this time, the system can introduce other sensory information (such as smell, touch, etc.) for secondary confirmation. This information can be obtained through additional sensors or manual input, and combined with uncertainty processing methods for comprehensive analysis to improve recognition accuracy.

[0013] The effects of the above technical solutions are as follows: by configuring high-precision cameras with different light sources, it is possible to capture subtle features on the surface of Chinese medicinal materials, such as texture, gloss and color gradient, etc., providing a rich and accurate information basis for subsequent feature extraction and recognition; the introduction of deep learning algorithms and attention mechanisms enables the system to efficiently extract the key features of Chinese medicinal materials and enhance attention to key areas, thereby improving the accuracy and robustness of recognition; the image preprocessing steps include denoising, contrast enhancement and edge detection, etc. These processes can significantly improve image quality, reduce noise interference, and enhance feature recognizability, providing strong support for subsequent feature extraction and recognition; the system uses a deep learning classifier to identify the types of Chinese medicinal materials, and provides a variety of classifier options (such as SVM, RF or fully connected layers in deep learning), and can select the most suitable classifier for recognition according to actual conditions; when there are multiple high-matching options in the recognition results The system can use uncertainty processing methods for secondary confirmation, and make comprehensive judgments based on other characteristics of Chinese medicinal materials (such as smell and touch), which further improves the accuracy and reliability of recognition. The technical solution has good scalability, and can continuously improve the accuracy and generalization of recognition by increasing the number of samples in the Chinese medicinal materials image database and improving the training quality of the deep learning model. At the same time, the system can adapt to the recognition needs of Chinese medicinal materials of different types and specifications, and has strong versatility and flexibility. The technical solution realizes the automation and intelligence of Chinese medicinal materials identification, reduces the influence of human intervention and subjective judgment, and improves detection efficiency and accuracy. By improving the accuracy and efficiency of Chinese medicinal materials identification, the technical solution helps to reduce the costs and risks in the production and sales of Chinese medicines. At the same time, it can also provide scientific basis and technical support for the research and development, quality control and market supervision of Chinese medicines, and promote the sustainable development of the Chinese medicine industry.

[0014] In one embodiment of the present invention, the S13 includes: According to the types of Chinese medicinal materials and image characteristics, a deep learning model is selected, and feature extraction is performed to optimize the selected deep learning model; Using a deep learning model to extract features from the preprocessed Chinese medicinal material images and identify key features of the Chinese medicinal materials, including shape, color, texture, and surface microstructure; Combined with near-infrared spectroscopy analysis technology, the spectral features of Chinese medicinal materials are extracted, and the spectral features include absorption peaks and reflectivity; the image features and spectral features are fused through a multimodal feature fusion method; Introducing the attention mechanism into the deep learning model to enhance the extracted features; The principal component analysis was used to reduce the dimension of the extracted features, and the feature selection algorithm was used to select the feature subset that contributed most to the identification of Chinese herbal medicine species; The feature vectors after dimension reduction and selection are concatenated or combined to generate feature vectors for identifying the types of Chinese medicinal materials.

[0015] The working principle of the above technical solution is as follows: according to the types and image characteristics of Chinese medicinal materials, select suitable deep learning models (such as ResNet, VGG, Inception, etc.), which have been pre-trained on large-scale image data sets and have good feature extraction capabilities; optimize the selected deep learning model, including adjusting hyperparameters such as network structure, learning rate, batch size, and using data enhancement techniques (such as rotation, scaling, cropping, etc.) to expand the training data set and improve the generalization ability of the model; use the optimized deep learning model to extract features from the pre-processed Chinese medicinal material images. Through network structures such as convolutional layers and pooling layers, key features such as the shape, color, texture, and surface microstructure of Chinese medicinal materials are gradually extracted; these features are represented in the form of high-dimensional vectors and contain rich information in the Chinese medicinal material images; combine near-infrared spectral analysis technology to perform spectral scanning on Chinese medicinal materials and extract their spectral features. Spectral features include absorption peaks, reflectivity, etc., which can reflect the chemical composition and structural information of Chinese medicinal materials; image features and spectral features are fused through multimodal feature fusion methods (such as feature splicing, feature weighted fusion, etc.). In this way, the system can make comprehensive use of the image and spectral information of Chinese medicinal materials to improve the accuracy and robustness of recognition; introduce attention mechanisms such as channel attention, spatial attention or self-attention in deep learning models. These mechanisms can automatically identify the key areas and features in the images of Chinese medicinal materials and give higher weights to these areas and features; through the attention mechanism, the system can more accurately capture the subtle features and key information of Chinese medicinal materials, further improving the accuracy of recognition; use dimensionality reduction techniques such as principal component analysis (PCA) to reduce the dimensionality of the extracted high-dimensional features. Dimensionality reduction can reduce the redundancy and noise between features and improve the expressiveness of features; use feature selection algorithms (such as feature selection based on mutual information, feature selection based on models, etc.) to select the feature subsets that contribute most to the identification of Chinese medicinal materials from the reduced dimensionality features. These feature subsets can more accurately reflect the type information of Chinese medicinal materials; concatenate or combine the feature vectors after dimensionality reduction and selection to generate feature vectors for Chinese medicinal materials type identification. This feature vector contains the key information and subtle features of Chinese medicinal materials and is the basis for subsequent classification and identification.

[0016] The effects of the above technical solution are: extracting features from Chinese herbal medicine images through a deep learning model, and extracting spectral features by combining near-infrared spectroscopy analysis technology, thus realizing the fusion of multimodal features. This method can comprehensively utilize the image and spectral information of Chinese herbal medicines, thereby improving the accuracy and robustness of recognition; introducing an attention mechanism to enhance features, so that the model can more accurately capture the subtle features and key information of Chinese herbal medicines, further improving the accuracy of recognition; selecting a suitable deep learning model according to the type and image characteristics of Chinese herbal medicines, and optimizing it, improving the generalization ability and feature extraction ability of the model; by adjusting the model structure and hyperparameters, and using data enhancement technology, the adaptability and stability of the model are enhanced. The principal component analysis (PCA) is used to reduce the dimensionality of the extracted high-dimensional features, which reduces the redundancy and noise between features and improves the expressiveness of the features; the feature selection algorithm is used to select the feature subset that contributes most to the identification of Chinese medicinal materials, which reduces the computational complexity and improves the recognition efficiency; this technical solution can adapt to the identification needs of Chinese medicinal materials of different types and specifications, and has strong versatility and flexibility; by increasing the number of samples in the Chinese medicinal materials image database and improving the training quality of the deep learning model, the recognition accuracy and generalization ability can be continuously improved, and the scalability of the system is enhanced; this technical solution provides the Chinese medicine industry with an efficient and accurate method for identifying Chinese medicinal materials, which helps to promote the modernization and standardization of the Chinese medicine industry; by improving the accuracy and efficiency of Chinese medicinal materials identification, the cost and risk in the production and sales of Chinese medicines are reduced, and the sustainable development of the Chinese medicine industry is promoted.

[0017] In one embodiment of the present invention, the S14 includes: Before the extracted feature vector is input into the deep learning classifier, it is normalized and each feature in the feature vector is weighted according to the importance of the key features of the Chinese medicinal materials; Map the feature vector to a high-dimensional or low-dimensional feature space through a deep learning algorithm; In the feature space, the cosine similarity is used to calculate the similarity between the feature vector of the Chinese herbal medicine to be identified and the feature vector of the known Chinese herbal medicine in the Chinese herbal medicine image database; According to the similarity calculation results, several Chinese medicinal materials with the highest similarity are selected as candidates for preliminary identification; According to the types and characteristics of Chinese medicinal materials, deep learning classifiers are selected and trained using known Chinese medicinal material features in the Chinese medicinal material image database; Input the feature vectors of the initially identified candidate objects into the trained deep learning classifier for classification and identification to obtain the type information of the Chinese medicinal materials; The working principle of the above technical solution is as follows: before the extracted feature vector is input into the deep learning classifier, it is first normalized. Normalization is to scale the feature values ​​to a common scale, which helps to eliminate the dimensional differences between different features and improve the performance of the classifier; according to the importance of the key features of Chinese medicinal materials (such as shape, color, texture, surface microstructure), each feature in the feature vector is weighted. Weighted processing can emphasize those features that are more critical to the identification of Chinese medicinal materials, thereby improving the accuracy of identification; the feature vector is mapped to a high-dimensional or low-dimensional feature space through deep learning algorithms (such as PCA, t-SNE, etc.). These algorithms can capture the intrinsic relationship between feature vectors and map them to a more compact and easy-to-classify space; PCA (Principal Component Analysis) is a commonly used dimensionality reduction technique that reduces the dimension of the data and retains as much information as possible by projecting the feature vectors onto the principal component directions; t-SNE (t-distributed Stochastic Neighbor Embedding) is a nonlinear dimensionality reduction technique that can map high-dimensional data into a low-dimensional space while retaining the local and global structure of the data; In the feature space, cosine similarity is used to calculate the similarity between the feature vectors of the Chinese herbal medicine to be identified and the feature vectors of known Chinese herbal medicines in the Chinese herbal medicine image database. Cosine similarity measures the directional similarity between two vectors, regardless of their size; Based on the similarity calculation results, several Chinese herbal medicines with the highest similarity are selected as candidates for preliminary identification. This step helps to narrow the recognition range and improve the efficiency of subsequent classifiers; According to the types and characteristics of Chinese herbal medicines, select appropriate deep learning classifiers (such as support vector machines SVM, random forest RF, fully connected layers in deep learning, etc.). These classifiers have different characteristics and advantages, and are suitable for different types of TCM identification tasks. The classifiers are trained using known TCM features in the TCM image database. During the training process, the classifiers will learn the mapping relationship between the features and types of TCMs, so that they have the ability to classify and identify new samples. The feature vectors of the initially identified candidate objects are input into the trained deep learning classifier for classification and identification. The classifier will output the type information of the TCM based on the input feature vectors. The output result can be the name, number or other identification information of the TCM, which can be used for the subsequent processing and management of the TCMs.

[0018] The effects of the above technical solution are as follows: normalization processing eliminates the dimensional differences between different features, so that the feature vector has a uniform scale when input into the classifier, which helps to improve the recognition accuracy of the classifier; feature weighting processing weights the feature vector according to the importance of the key features of the Chinese medicinal materials, emphasizes the role of the key features in the recognition process, and further improves the recognition accuracy; mapping the feature vector to a high-dimensional or low-dimensional feature space through a deep learning algorithm (such as PCA, t-SNE, etc.) helps to capture the intrinsic relationship between the feature vectors and improve the separability of the features; the optimization of the feature space makes the similarity calculation between the feature vector of the Chinese medicinal material to be identified and the feature vector of the known Chinese medicinal material in the Chinese medicinal material image database more accurate, thereby improving the accuracy of the candidate objects for preliminary identification; the cosine similarity calculation is simple and efficient, and can quickly calculate the similarity between feature vectors, reducing the calculation complexity; by selecting several Chinese medicinal materials with the highest similarity as the candidate objects, narrowing the recognition scope and improving the recognition efficiency of subsequent classifiers; selecting appropriate deep learning classifiers according to the types and characteristics of Chinese medicinal materials, and using known Chinese medicinal material features in the Chinese medicine image database for training, so that the classifier can better adapt to the needs of Chinese medicinal material identification; the trained deep learning classifier has high recognition accuracy and generalization ability, and can accurately identify the type information of Chinese medicinal materials; this technical solution can adapt to the identification needs of Chinese medicinal materials of different types and specifications, and has strong versatility and flexibility; with the continuous expansion and updating of the Chinese medicine image database, this technical solution can continue to learn and optimize, and continuously improve the accuracy and efficiency of Chinese medicinal material identification; this technical solution provides the Chinese medicine industry with an efficient and accurate method for identifying Chinese medicinal materials, which is helpful to promote the intelligent development of the Chinese medicine industry; by improving the accuracy and efficiency of Chinese medicinal material identification, it reduces the costs and risks in the production and sales of Chinese medicine, and promotes the sustainable development of the Chinese medicine industry.

[0019] In one embodiment of the present invention, the S15 includes: According to the output results of the deep learning classifier, the recognition results of Chinese medicinal materials are sorted by matching degree, and the top N options with the highest matching degree are selected as candidates; Perform differential analysis on the feature vectors of candidate objects to identify subtle differences in shape, color, texture, and surface microstructure. Use odor sensors or gas chromatography-mass spectrometry (GC-MS) to collect and analyze the odor of Chinese medicinal materials and extract characteristic odor components. Use touch sensors or robotic arms to simulate human hands touching Chinese medicinal materials to collect their tactile characteristics such as hardness, elasticity, and roughness; use Bayesian classifiers to fuse visual features (shape, color, texture, surface microstructure) with sensory features (smell, touch) to calculate the posterior probability that each candidate object belongs to each type of Chinese medicinal material; The output results of multiple classifiers are integrated by using ensemble learning methods, and the uncertainty of the recognition results is evaluated based on the output results of the Bayesian classifier or ensemble learning method; If the uncertainty is high, further verification or adjustment is required; based on the output of the uncertainty processing method, the most likely type of Chinese medicinal material is selected as the final identification result; among them, the indicators with high uncertainty are as follows: Low classifier confidence: When a deep learning classifier or Bayesian classifier gives a low confidence level (for example, a value of 0-100 and a score of 30) to the recognition result of a candidate object, that is, the probability distribution of the recognition result is relatively scattered and has no significant peak, it indicates that there is great uncertainty in the classifier's recognition of the Chinese medicinal material.

[0020] High feature vector discreteness: The feature vectors of candidate objects (including shape, color, texture, surface microstructure, etc.) are relatively discrete in the feature space, with no obvious clustering trend, indicating that these candidate objects have a high visual similarity (for example, a value of 0-100 and a score of 75) and are difficult to distinguish effectively through visual features.

[0021] Inconsistent sensory characteristics: There is an obvious inconsistency between the characteristic odor components extracted by the odor sensor or GC-MS and the tactile characteristics collected by the tactile sensor. For example, the types of Chinese medicinal materials indicated by the odor and tactile characteristics are inconsistent, which increases the uncertainty of identification.

[0022] The output results of ensemble learning are scattered: After integrating the output results of multiple classifiers using the ensemble learning method, the recognition results obtained still have a high degree of dispersion, that is, there are large differences between the recognition results of different classifiers, which shows that the ensemble learning method cannot effectively reduce the uncertainty of recognition.

[0023] Compare the final recognition results with the actual situation and collect feedback data.

[0024] The working principle of the above technical solution is as follows: according to the output results of the deep learning classifier, the recognition results of Chinese medicinal materials are ranked by matching degree. The matching degree usually indicates the similarity between the recognition results and the known characteristics of Chinese medicinal materials; the top N options with the highest matching degree are selected as candidates. These candidates are closest to the Chinese medicinal materials to be identified in terms of visual features; the feature vectors of the candidates are differentially analyzed to identify the subtle differences between them in terms of shape, color, texture, and surface microstructure. These subtle differences help to further distinguish the candidates and improve the accuracy of recognition; the smell of Chinese medicinal materials is collected and analyzed using odor sensors or gas chromatography-mass spectrometry (GC-MS) to extract characteristic odor components. As one of the important sensory characteristics of Chinese medicinal materials, odor characteristics help to enhance the reliability of recognition; touch sensors or robotic arms are used to simulate human hands touching Chinese medicinal materials to collect their tactile characteristics such as hardness, elasticity, and roughness. Tactile features provide an additional information dimension for the identification of Chinese herbal medicines, which helps to improve the comprehensiveness of identification. The Bayesian classifier is used to integrate visual features (shape, color, texture, surface microstructure) with sensory features (smell, touch). The Bayesian classifier can calculate the posterior probability that each candidate object belongs to each type of Chinese herbal medicine based on known features; the posterior probability represents the probability that the candidate object belongs to a certain type of Chinese herbal medicine under the condition of given observation data (i.e., visual and sensory features). By comparing the posterior probabilities, the recognition range can be further narrowed and the accuracy of recognition can be improved. The output results of multiple classifiers are integrated using ensemble learning methods (such as Adaboost, Bagging, random forest, etc.). The ensemble learning method can combine the advantages of multiple classifiers and improve the stability and accuracy of recognition. According to the output results of the Bayesian classifier or ensemble learning method, the uncertainty of the recognition result is evaluated. Uncertainty assessment helps to identify those candidates that may have recognition errors, so as to conduct further verification or adjustment; if the uncertainty is high, further verification or adjustment is required. Verification can be performed by adding additional observation data (such as more visual and sensory features) or using expert knowledge; based on the output of the uncertainty handling method, the most likely type of Chinese medicinal materials is selected as the final recognition result. The final recognition result should have a high degree of confidence and accuracy; the final recognition result is compared with the actual situation, and feedback data is collected. The feedback data includes information on the accuracy of the recognition results, the effectiveness of the uncertainty assessment, and the performance of the system; the feedback data is used to optimize the deep learning model, training data set, and uncertainty handling method. The optimization process includes adjusting model parameters, increasing training samples, improving uncertainty assessment algorithms, etc., to improve the overall performance and accuracy of the system.

[0025] The effects of the above technical solution are as follows: through the preliminary identification of the deep learning classifier, combined with the matching degree ranking, the candidate objects closest to the Chinese medicinal materials to be identified can be screened out, providing a basis for subsequent feature analysis and fusion; the feature vectors of the candidate objects are differentially analyzed to identify the subtle differences between them, further improving the accuracy of recognition; the introduction of sensory features such as smell and touch, combined with visual features, the use of Bayesian classifiers for feature fusion, and the calculation of posterior probabilities can more comprehensively reflect the characteristics of Chinese medicinal materials, thereby improving the reliability of recognition; the use of ensemble learning methods to integrate the output results of multiple classifiers can combine the advantages of multiple classifiers and improve the stability and robustness of recognition; based on the output results of the Bayesian classifier or the ensemble learning method, the uncertainty of the recognition results is evaluated, and it is possible to identify Candidate objects with recognition errors can provide a basis for subsequent verification or adjustment; the final recognition result is compared with the actual situation, and feedback data is collected to timely discover and correct recognition errors, providing data support for system optimization; using feedback data to optimize deep learning models, training data sets, and uncertainty processing methods can continuously improve the overall performance and accuracy of the system, making it more adaptable to the needs of actual application scenarios; this technical solution combines a variety of advanced technologies such as deep learning, feature fusion, integrated learning, and uncertainty assessment to achieve intelligent and automated identification of Chinese medicinal materials, reducing the cost and difficulty of manual identification; through continuous optimization and improvement, this technical solution is expected to provide more efficient and accurate identification methods for the planting, processing, quality control and other links of Chinese medicinal materials, and promote the intelligent upgrading and development of the Chinese medicinal materials industry.

[0026] In one embodiment of the present invention, the S2 includes: S21, activating the near-infrared spectrometer in the quality inspection module, performing non-destructive scanning on the Chinese medicinal materials, obtaining near-infrared spectrum data thereof, and covering a wavelength range from 780 nm to 2526 nm; S22, preprocessing the collected spectral data, wherein the preprocessing includes smoothing, baseline correction and normalization to eliminate the influence of instrument noise and baseline drift on the analysis results; S23, using chemometric methods to analyze the pre-processed spectral data and establish a quantitative determination model for the active ingredients in Chinese medicinal materials; S24, drying the Chinese medicinal materials in a constant temperature drying oven, and calculating the moisture content by measuring the mass difference before and after drying; S25, using a capacitive sensor to measure the change in the dielectric constant of the Chinese medicinal material, and determining the moisture content according to the relationship between the moisture content and the dielectric constant; S26. Crush the Chinese medicinal materials to an appropriate particle size, and use acid digestion (such as nitric acid, hydrochloric acid, hydrofluoric acid, etc.) or microwave digestion to convert the heavy metal elements in the Chinese medicinal materials into soluble forms; S27, introducing the digested sample solution into the ICP-MS instrument, using high-energy plasma to atomize the sample and excite it to a high-energy state, and using a mass spectrometer to detect the characteristic mass number of each element to perform trace analysis of heavy metal elements (such as lead, mercury, arsenic, cadmium, etc.); S28. Process the data obtained from ICP-MS detection accordingly and evaluate the safety of heavy metal residues in Chinese medicinal materials according to relevant standards.

[0027] The working principle of the above technical solution is: activate the near-infrared spectrometer in the quality inspection module, and use near-infrared spectroscopy technology to perform non-destructive scanning of Chinese medicinal materials. Near-infrared spectroscopy technology is based on the principle of frequency doubling and sum frequency absorption in molecular vibration. By measuring the near-infrared spectral data of Chinese medicinal materials in the wavelength range of 780nm to 2526nm, it reflects the information of the internal chemical components of Chinese medicinal materials; the collected spectral data is smoothed (such as Savitzky-Golay filtering), baseline corrected and normalized. Smoothing can eliminate high-frequency noise in spectral data; baseline correction can eliminate the influence of baseline drift on the analysis results; normalization can make the spectral data of different samples have a unified scale; chemometric methods (such as partial least squares PLS, principal component regression PCR) are used to analyze the pre-processed spectral data. These methods extract characteristic information from spectral data to establish a mathematical model between the effective ingredients (such as flavonoids, alkaloids, polysaccharides, etc.) in Chinese medicinal materials and spectral data; dry the Chinese medicinal materials in a constant temperature drying oven, measure the mass difference before and after drying, and calculate the moisture content of the Chinese medicinal materials based on the mass difference; use a capacitive sensor to measure the change in the dielectric constant of the Chinese medicinal materials. There is a certain relationship between moisture content and dielectric constant. The moisture content of Chinese medicinal materials can be indirectly determined by measuring the change in dielectric constant; crush the Chinese medicinal materials to an appropriate particle size, and use acid digestion (such as nitric acid, hydrochloric acid, hydrofluoric acid, etc.) or microwave digestion to convert the heavy metal elements in the Chinese medicinal materials into a soluble state. This helps with subsequent heavy metal element detection; introduce the digested sample solution into the ICP-MS instrument. The ICP-MS instrument uses high-energy plasma to atomize and excite the sample to a high-energy state, and detects the characteristic mass number of each element through a mass spectrometer. Since different elements have different characteristic mass numbers, it is possible to perform trace analysis of heavy metal elements (such as lead, mercury, arsenic, cadmium, etc.); perform baseline correction, peak identification, and quantitative calculation on the data obtained by ICP-MS detection. Evaluate the safety of heavy metal residues in traditional Chinese medicines according to relevant standards (such as national standards or industry standards).

[0028] The effects of the above technical scheme are as follows: non-destructive scanning of Chinese medicinal materials by near-infrared spectrometer avoids sample damage that may be caused by traditional detection methods, which is beneficial to the subsequent use of samples; the rapid scanning characteristics of near-infrared spectroscopy technology make the detection process efficient and fast, and can greatly improve the efficiency of Chinese medicinal materials quality detection; smoothing, baseline correction and normalization in the pretreatment step effectively eliminate the influence of instrument noise and baseline drift on the analysis results, and improve the accuracy of spectral data; chemometric methods (such as PLS, PCR) are used to analyze spectral data, and a quantitative determination model for effective ingredients in Chinese medicinal materials is established, which realizes the rapid and accurate determination of the content of effective ingredients in Chinese medicinal materials; a constant temperature drying oven is used to measure the mass difference before and after drying to calculate the moisture content, which is a classic and accurate moisture determination method; at the same time, a capacitive sensor is introduced to measure the change in the dielectric constant of Chinese medicinal materials to determine the moisture content, providing another rapid and non-destructive moisture detection method, which increases the diversity and flexibility of detection; acid digestion or microwave digestion The method converts heavy metal elements in Chinese medicinal materials into soluble states, providing good sample pretreatment for subsequent ICP-MS detection; ICP-MS instruments have the characteristics of high sensitivity, high resolution and low detection limit, and can accurately detect trace heavy metal elements in Chinese medicinal materials, providing strong support for the safety assessment of Chinese medicinal materials; the data obtained by ICP-MS detection are processed by baseline correction, peak identification and quantitative calculation to ensure the accuracy and reliability of the test results; the safety of heavy metal residues in Chinese medicinal materials is evaluated according to relevant standards (such as national standards or industry standards), so that the test results have legal effect and authority, providing a scientific basis for the quality control of Chinese medicinal materials; the technical solution combines multiple advanced technologies such as near-infrared spectroscopy technology and ICP-MS technology to achieve comprehensive quality inspection of Chinese medicinal materials and promote the innovation and development of Chinese medicinal materials quality inspection technology; at the same time, the technical solution also provides strong technical support for the planting, processing, quality control and other links of Chinese medicinal materials, which is helpful to improve the overall quality and market competitiveness of Chinese medicinal materials.

[0029] In one embodiment of the present invention, the S23 includes: Before using chemometric methods, statistical methods are used to detect outliers in spectral data and process them accordingly; The spectral data is featured by continuous projection algorithm to extract the characteristic wavelength that has the greatest influence on the determination of the effective ingredient content of traditional Chinese medicine. The pre-processed spectral data were used as independent variables, and the content of active ingredients in Chinese medicinal materials was used as dependent variables. The partial least squares method was used to establish a multivariate linear regression model for quantitative determination of the ingredients. The principal component analysis was performed on the spectral data, the principal components were extracted as new independent variables, and the model between the principal components and the content of effective ingredients in Chinese medicinal materials was established using regression methods; The regression version of support vector machine, namely support vector regression, is used to perform nonlinear mapping on spectral data and establish a nonlinear relationship model between the content of active ingredients in Chinese medicinal materials and spectral data. K-fold cross validation is used to verify the established model and evaluate the prediction performance of the model; and optimization algorithms such as grid search and random search are used to tune the parameters of the model; According to the cross-validation results and model performance indicators (such as mean square error MSE, determination coefficient R², etc.), the advantages and disadvantages of different chemometric methods are compared, and the optimal model is selected for subsequent application.

[0030] The working principle of the above technical solution is as follows: before using the chemometric method, the outliers in the spectral data are first detected using statistical methods (such as box plots, Grubbs test, etc.). These methods identify outliers by comparing the statistical characteristics of the data points with the data set (such as the median, quartiles, mean, etc.); once the outliers are detected, they are processed accordingly according to the specific situation, such as deleting the outliers, correcting the outliers (if the correct value of the outliers is known), or estimating the outliers using interpolation methods; feature selection is performed on the spectral data by the continuous projection algorithm (SPA). The SPA algorithm extracts the characteristic wavelengths that have the greatest influence on the determination of the content of the active ingredients of Chinese medicinal materials from the spectral data by iterative projection; the pre-processed spectral data is used as the independent variable, the content of the active ingredients in the Chinese medicinal materials is used as the dependent variable, and the partial least squares method (PLS) is used to establish a multivariate linear regression model. PLS extracts the most effective components (i.e., latent variables) for prediction by considering the information of the independent variables and the dependent variables at the same time, thereby establishing a model; principal component analysis (PCA) is performed on the spectral data to extract the principal components as new independent variables. PCA projects high-dimensional data into low-dimensional space through linear transformation while retaining the main information of the data; uses regression methods (such as linear regression, ridge regression, etc.) to establish a model between the principal component and the content of the active ingredients of Chinese medicinal materials; uses the regression version of the support vector machine (SVM), namely support vector regression (SVR), to perform nonlinear mapping on the spectral data. SVR maps the input data into a high-dimensional feature space by introducing a kernel function, and establishes a linear regression model in this space; K-fold cross validation is used to verify the established model. K-fold cross validation divides the data set into K subsets, and takes one of the subsets as the test set and the remaining subsets as the training set in turn, so as to obtain the performance evaluation results of K models; uses optimization algorithms such as grid search and random search to tune the parameters of the model. These algorithms systematically search the parameter space to find the optimal parameter combination to improve the prediction performance of the model; compares the advantages and disadvantages of different chemometric methods based on cross validation results and model performance indicators (such as mean square error MSE, coefficient of determination R², etc.). MSE measures the average difference between the model's predicted values ​​and the true values, and R² measures how well the model fits the data; the optimal model is selected for subsequent applications. The optimal model usually has a lower MSE and a higher R² value, taking into account the complexity and generalization ability of the model.

[0031] The effects of the above technical solution are as follows: by detecting outliers in spectral data through statistical methods (such as box plots and Grubbs tests) and performing corresponding processing, the data quality is effectively improved and the impact of noise and errors on subsequent modeling is reduced; by using the continuous projection algorithm (SPA) to perform feature selection on spectral data, the characteristic wavelengths that have the greatest influence on the determination of the content of effective ingredients in Chinese medicinal materials can be extracted, thereby simplifying the model structure and improving the prediction accuracy and efficiency of the model; by establishing a multivariate linear regression model through the partial least squares method, the relationship between multiple characteristic wavelengths of spectral data and the content of effective ingredients in Chinese medicinal materials can be comprehensively considered, and the determination of the content of effective ingredients in Chinese medicinal materials can be realized. Rapid and accurate quantitative determination of active ingredients in medicinal materials; principal component analysis (PCA) of spectral data, and the extracted principal components as new independent variables, not only reduce the dimension of the data, but also help to understand the main structure and source of variation in the data, and enhance the explanatory power of the model; support vector regression (SVR) is used to perform nonlinear mapping of spectral data, which can establish a nonlinear relationship model between the content of active ingredients in Chinese medicinal materials and spectral data, which is suitable for complex data scenarios with strong nonlinear relationships; K-fold cross validation is used to verify the established model, which can comprehensively evaluate the prediction performance of the model and avoid overfitting or underfitting. At the same time, the parameters of the model are tuned using optimization algorithms such as grid search and random search, which further improves the prediction accuracy and generalization ability of the model; the advantages and disadvantages of different chemometric methods are compared based on cross-validation results and model performance indicators (such as mean square error MSE, determination coefficient R², etc.), and the optimal model can be scientifically and objectively selected for subsequent application, ensuring the accuracy and reliability of the quality detection results of Chinese medicinal materials.

[0032] In one embodiment of the present invention, S3 includes: S31, tumbling the Chinese medicinal materials according to relevant characteristics of the Chinese medicinal materials, including type, shape and density, based on a preset tumbling strategy, including tumbling speed, angle, number of times and tumbling path; S32. Evaluate and optimize the rollover strategy and adjust the rollover parameters through simulation experiments and actual test data feedback; S33. The robotic arm accurately grasps and stably places the Chinese medicinal materials based on visual servo technology or laser navigation technology. The rotating platform rolls according to the instructions of the control module, while the robotic arm maintains a stable grip on the Chinese medicinal materials. S34. During the tumbling process, the variety screening module and the quality inspection module continue to work, collect images and spectral data of Chinese medicinal materials in real time, and feed them back to the control module for processing and analysis in real time; S35, the control module fuses and processes the collected data, and the fusion and processing include image stitching, spectral data correction, and feature extraction to obtain comprehensive detection information of Chinese medicinal materials.

[0033] The working principle of the above technical solution is as follows: according to the relevant characteristics of Chinese medicinal materials (type, shape, density, etc.), the system presets a set of rolling strategies, including rolling speed, angle, number of times and rolling path. These strategies are formulated to ensure that the Chinese medicinal materials can fully expose their various surfaces during the rolling process, which is convenient for subsequent detection and analysis; the robotic arm or rotating platform performs rolling operations on the Chinese medicinal materials according to the preset rolling strategy. During the rolling process, the system will dynamically adjust the rolling strategy according to the actual characteristics of the Chinese medicinal materials to ensure the rolling effect and safety; the system evaluates the rolling strategy through simulation experiments and actual detection data feedback. The evaluation indicators may include rolling effect, detection accuracy, degree of damage to medicinal materials, etc.; according to the evaluation results, the system adjusts and optimizes the rolling strategy, including the adjustment of rolling speed, angle, number of times and path, to improve the rolling effect and detection accuracy; the robotic arm accurately grasps the Chinese medicinal materials based on visual servo technology or laser navigation technology. During the grasping process, the robotic arm will maintain a stable grip on the Chinese medicinal materials to avoid damage to the medicinal materials or detection errors during the rolling process; the rotating platform will perform rolling operations according to the instructions of the control module, while the robotic arm will maintain a stable grip on the Chinese medicinal materials. During the rolling process, the robotic arm and the rotating platform must maintain a high degree of coordination to avoid collisions and interference, and ensure the stability and safety of the Chinese medicinal materials; during the rolling process, the variety screening module and the quality inspection module continue to work. The variety screening module may use image recognition technology to identify the type and form of Chinese medicinal materials; the quality inspection module uses spectral analysis and other technologies to detect the quality of Chinese medicinal materials; the image and spectral data of Chinese medicinal materials are collected in real time, and these data are fed back to the control module for processing and analysis. The control module will adjust the rolling strategy and optimize the detection parameters based on these data; the control module fuses and processes the collected image and spectral data. The fusion processing may include steps such as image stitching, spectral data correction, and feature extraction; through data fusion and processing, the system can obtain comprehensive detection information of Chinese medicinal materials, including information on types, forms, and quality. This information provides an important basis for subsequent analysis and decision-making.

[0034] The effect of the above technical solution is: according to the characteristics of Chinese medicinal materials such as type, shape and density, the preset rolling strategy (including rolling speed, angle, number and path) can be used to roll the Chinese medicinal materials in a targeted manner to ensure that all surfaces of the medicinal materials can be fully detected and analyzed. This personalized rolling strategy not only improves the detection efficiency, but also reduces the number of unnecessary rolling times and reduces the risk of damage to the medicinal materials; through simulation experiments and feedback from actual detection data, the system can continuously evaluate and optimize the rolling strategy and make fine adjustments to the rolling parameters. This dynamic optimization mechanism ensures that the rolling strategy always matches the actual characteristics of the Chinese medicinal materials, further improving the accuracy and reliability of the detection; the robotic arm uses visual servo technology or laser navigation technology to achieve accurate grasping and stable placement of Chinese medicinal materials. During the rolling process, the robotic arm maintains a stable grip on the medicinal materials to avoid damage to the medicinal materials and detection errors. At the same time, the coordinated work of the rotating platform and the control module ensures the stability and safety of the tumbling process; the variety screening module and the quality inspection module work continuously during the tumbling process, collect the image and spectral data of Chinese medicinal materials in real time, and feed back these data to the control module in real time for processing and analysis. This real-time data collection and feedback mechanism can timely discover and handle abnormal situations, improving the precision and accuracy of detection; the control module fuses and processes the collected image and spectral data, including steps such as image stitching, spectral data correction and feature extraction. This data fusion and processing technology can obtain comprehensive detection information of Chinese medicinal materials, including detailed data on types, morphology, quality, etc., providing strong support for the quality control and traceability of Chinese medicinal materials; the entire technical solution realizes the automation and intelligence of Chinese medicinal materials tumbling detection. Through the technical means of preset tumbling strategies, dynamic optimization parameters, precise grabbing and placement, real-time data collection and feedback, and data fusion and processing, the system can efficiently and accurately complete the detection task of Chinese medicinal materials, reducing the cost and risk of manual intervention.

[0035] In one embodiment of the present invention, the S32 includes: Using 3D modeling software or physical simulation platform, construct a virtual model of Chinese herbal medicines according to their types, shapes, density and other characteristics; at the same time, simulate the movements and interactions of the robotic arm, rotating platform and control module; In the simulation environment, the Chinese medicinal materials are tumbling simulated according to the preset tumbling speed, angle, number of times, tumbling path and other strategies; and the robot arm movements, the movement trajectory of the Chinese medicinal materials and possible collisions during the tumbling process are recorded; Analyze the results of the simulation experiment to evaluate the effectiveness and safety of the rolling strategy; identify potential collision points, rolling instability areas, and risk points of damage to Chinese medicinal materials; During the actual testing process, the Chinese medicinal materials are tumbled according to the preset tumbling strategy, and sensors and testing equipment are used to collect images, spectra, and status data of the mechanical arm and rotating platform of the Chinese medicinal materials in real time; Preprocess the collected data, compare the actual test data with the simulation experiment results, analyze the performance of the rollover strategy in actual application, and identify differences and potential problems; Extract key features of the rolling strategy from simulation experiments and actual test data, such as rolling speed, angle, number, path length, number of collisions, etc.; use feature selection algorithms to select the features that have the greatest impact on the rolling effect; Based on the machine learning algorithm, a prediction model between the rolling strategy and the rolling effect of Chinese medicinal materials is established; according to the output results of the prediction model, the rolling strategy is adjusted and optimized; Use multi-objective optimization algorithms to find the optimal solution among multiple objectives.

[0036] The working principle of the above technical solution is as follows: First, a virtual model of Chinese medicinal materials is constructed based on the characteristics of Chinese medicinal materials such as type, shape and density using 3D modeling software or physical simulation platform. At the same time, the actions and interactions of the robotic arm, rotating platform and control module are simulated to create a simulation environment similar to the actual detection environment; in the simulation environment, the virtual model of Chinese medicinal materials and the models of equipment such as the robotic arm and rotating platform are imported. According to the preset strategies such as rolling speed, angle, number of times and rolling path, the Chinese medicinal materials are simulated for rolling. The actions of the robotic arm, the movement trajectory of the Chinese medicinal materials and possible collisions during the rolling process are recorded; the results of the simulation experiment are analyzed to evaluate the effectiveness and safety of the rolling strategy. The feasibility of the rolling strategy in practical application is evaluated by identifying potential collision points, rolling instability areas and risk points of damage to Chinese medicinal materials; the movement trajectory of the Chinese medicinal materials, the actions of the robotic arm and the collisions in the simulation experiment are analyzed. According to the analysis results, the effectiveness of the rolling strategy is evaluated, and potential collision points, rolling unstable areas, and risk points of damage to Chinese medicinal materials are identified; in the actual detection process, the Chinese medicinal materials are rolled according to the preset rolling strategy, and the images, spectra, and status data of the robotic arm and rotating platform of the Chinese medicinal materials are collected in real time using sensors and detection equipment; in the actual detection environment, sensors and detection equipment, such as cameras and spectrometers, are set up. The Chinese medicinal materials are rolled according to the preset rolling strategy, and data is collected in real time. The collected data is preprocessed, such as denoising and filtering; the actual detection data is compared with the simulation experiment results, and the performance of the rolling strategy in actual application is analyzed to identify differences and potential problems; the actual detection data after preprocessing is compared with the simulation experiment results to analyze the differences and potential problems of the rolling strategy in actual application. By comparing the data such as the robot arm action, the movement trajectory of the Chinese medicinal materials, and the collision situation, the shortcomings of the rolling strategy in actual application are identified; the key features of the rolling strategy are extracted from the simulation experiment and actual detection data, such as rolling speed, angle, number, path length, number of collisions, etc. Use feature selection algorithms to screen out the features that have the greatest impact on the rolling effect; extract the key features of the rolling strategy, and use feature selection algorithms (such as recursive feature elimination RFE, model-based feature selection MBFS, etc.) to screen the features. Through feature selection, determine the features that have the greatest impact on the rolling effect; establish a prediction model between the rolling strategy and the rolling effect of Chinese medicinal materials based on machine learning algorithms. According to the output results of the prediction model, adjust and optimize the rolling strategy; select appropriate machine learning algorithms (such as support vector machines SVM, random forest RF, etc.) to establish a prediction model between the rolling strategy and the rolling effect of Chinese medicinal materials.Use the collected data to train the model, and adjust and optimize the rolling strategy based on the prediction results; use multi-objective optimization algorithms (such as genetic algorithm GA, particle swarm optimization PSO, etc.) to find the optimal solution between multiple objectives (such as rolling efficiency, safety, and risk of damage to Chinese medicinal materials); determine the optimization objectives, such as rolling efficiency, safety, and risk of damage to Chinese medicinal materials. Select a suitable multi-objective optimization algorithm and set the algorithm parameters. Use the rolling strategy as the optimization variable and use the multi-objective optimization algorithm to find the optimal solution between multiple objectives.

[0037] The effect of the above technical solution is: by constructing a virtual model of Chinese medicinal materials through three-dimensional modeling software and physical simulation platform, and simulating the actions of the robotic arm, rotating platform and control module, the rolling strategy can be preliminarily evaluated and tested without actually touching the Chinese medicinal materials. This greatly reduces the experimental cost and reduces the risk of damage to Chinese medicinal materials due to improper operation; the simulation environment can simulate the motion trajectory and collision of Chinese medicinal materials under different rolling strategies, thereby helping researchers to accurately evaluate the effectiveness and safety of the rolling strategy. By continuously optimizing the rolling strategy, it can ensure that the Chinese medicinal materials remain intact during the rolling process, while improving the detection efficiency and accuracy; in the actual detection process, sensors and detection equipment are used to collect images, spectra of Chinese medicinal materials, and status data of the robotic arm and rotating platform in real time, providing rich data support for the evaluation and optimization of the rolling strategy. By preprocessing and comparing and analyzing these data, the differences and potential problems of the rolling strategy in actual applications can be identified, providing a basis for further optimization; the key features of the rolling strategy are extracted from the simulation experiment and actual detection data, and the features that have the greatest impact on the rolling effect are screened out using feature selection algorithms, which can significantly improve the accuracy of the prediction model. This helps to more accurately predict the impact of different tumbling strategies on the tumbling effect of Chinese medicinal materials, and provides a scientific basis for the adjustment and optimization of tumbling strategies; using multi-objective optimization algorithms to find the optimal solution between multiple objectives such as tumbling efficiency, safety, and risk of damage to Chinese medicinal materials can ensure that the tumbling strategy achieves the overall optimal effect while meeting multiple constraints. This helps to improve the overall performance and reliability of Chinese medicinal materials tumbling detection; through the close combination of simulation experiments and actual detection, as well as the application of data-driven prediction models and optimization algorithms, the research and development process of Chinese medicinal materials tumbling detection technology can be significantly accelerated. This helps to promote the innovation and development of Chinese medicinal materials quality inspection technology and enhance the overall competitiveness of the Chinese medicinal materials industry.

[0038] In one embodiment of the present invention, the S34 includes: Use high-resolution cameras or visual sensors to capture the image data of Chinese medicinal materials in real time during the tumbling process; use spectral detection equipment such as near-infrared spectrometers or Raman spectrometers to collect spectral data of Chinese medicinal materials in real time; Preprocess the collected image data, perform smoothing, baseline correction, normalization and other preprocessing steps on the spectral data to eliminate the influence of instrument noise and baseline drift on the analysis results; Image processing algorithms are used to extract image features of Chinese medicinal materials; chemometric methods are used to extract features from spectral data. Spectral features that are closely related to the content of active ingredients in Chinese medicinal materials are extracted; The extracted image features and spectral features are matched and identified with the preset Chinese medicinal materials database; the Chinese medicinal materials are screened and their quality is tested by comparing their morphology, color, texture, spectral features and other information; Use machine learning algorithms to establish an anomaly detection model for Chinese medicinal materials; perform anomaly detection on real-time collected images and spectral data to identify abnormal data that does not match the characteristics of normal Chinese medicinal materials; When abnormal data is detected, the early warning mechanism is immediately triggered and a warning signal is sent to the control module; at the same time, the abnormal data and related information are fed back to the operator or the quality inspection module.

[0039] The working principle of the above technical solution is as follows: during the tumbling process of Chinese medicinal materials, high-resolution cameras or visual sensors are used to capture the image data of Chinese medicinal materials in real time. At the same time, spectral data of Chinese medicinal materials are collected in real time through spectral detection equipment such as near-infrared spectrometers or Raman spectrometers; the camera or sensor is fixed on a mechanical arm or a rotating platform, and moves with the tumbling of Chinese medicinal materials to ensure that images of Chinese medicinal materials at all angles can be captured. The spectral detection equipment collects spectral data by contacting or contactless with Chinese medicinal materials through optical fibers or probes; the collected image data is subjected to preprocessing steps such as denoising, contrast enhancement, and image segmentation to remove irrelevant information in the image and improve image quality. The spectral data is subjected to preprocessing steps such as smoothing, baseline correction, and normalization to eliminate the influence of instrument noise and baseline drift on the analysis results; the image features of Chinese medicinal materials, such as edges, textures, shapes, etc., are extracted using image processing algorithms. At the same time, chemometric methods are used to extract features from spectral data to extract spectral features that are closely related to the content of active ingredients in Chinese medicinal materials; the extracted image features and spectral features are matched and identified with the preset Chinese medicinal materials database. By comparing the morphology, color, texture, and spectral characteristics of Chinese medicinal materials, we can screen the varieties and inspect the quality of Chinese medicinal materials. We can also use machine learning algorithms to establish an abnormality detection model for Chinese medicinal materials. We can perform abnormality detection on the real-time collected images and spectral data to identify abnormal data that does not match the characteristics of normal Chinese medicinal materials. When abnormal data is detected, the early warning mechanism is immediately triggered, sending an early warning signal to the control module, and feeding back the abnormal data and related information to the operator or the quality inspection module.

[0040] The effects of the above technical solution are: through high-resolution cameras and spectral detection equipment, images and spectral data are captured in real time during the tumbling process of Chinese medicinal materials, ensuring the immediacy and comprehensiveness of the data. This helps to timely discover the changes of Chinese medicinal materials during the tumbling process and improve the accuracy of detection; pre-processing of image and spectral data, such as denoising, contrast enhancement, image segmentation, smoothing, baseline correction, normalization, etc., effectively eliminates irrelevant information and instrument noise, and improves the reliability and analysis accuracy of data; image processing algorithms and chemometric methods are used to extract image features and spectral features of Chinese medicinal materials, and match and identify them with the preset Chinese medicinal materials database. This method can quickly and accurately identify the variety and quality of Chinese medicinal materials and improve the detection efficiency; an abnormal detection model for Chinese medicinal materials is established through machine learning algorithms to perform abnormal detection on real-time collected data. When abnormal data is detected, the early warning mechanism is immediately triggered, a warning signal is sent to the control module, and the abnormal data is fed back to the operator or the quality detection module. This helps to timely discover and deal with problems in Chinese medicinal materials, ensuring the quality and safety of Chinese medicinal materials; the entire technical solution combines a variety of technical means such as high-resolution cameras, spectral detection equipment, image processing algorithms, chemometric methods and machine learning algorithms to achieve intelligent and automated detection during the tumbling process of Chinese medicinal materials. This reduces the cost and risk of manual intervention and improves the stability and reliability of detection.

[0041] In one embodiment of the present invention, the S4 includes: S41, the control module receives all data from the variety screening module, the quality inspection module, the mechanical arm and the rotating platform, and performs data verification and format conversion; cleans and standardizes the received data; S42. According to the types and testing standards of Chinese medicinal materials, conduct quality grade assessment on various quality testing indicators of Chinese medicinal materials to determine whether they meet the quality standards; S43. Identify and analyze the possible quality risks in Chinese herbal medicines and set warning thresholds. When the test results reach or exceed the warning thresholds, a warning signal is issued; S44. Automatically generate a detailed test report based on the data analysis results and the report template, and output it to the user in the form of an electronic document through a user interface or a network interface.

[0042] The working principle of the above technical solution is as follows: First, the control module verifies the data to ensure the integrity, accuracy and timeliness of the data. Then, the received data is cleaned to remove duplicate, erroneous or irrelevant data. Finally, the data format is converted and standardized so that data from different sources and formats can be uniformly processed and analyzed; the cleaned and standardized data are compared with the preset quality standards to determine whether the Chinese medicinal materials meet the quality standards. According to the comparison results, the quality grades of the Chinese medicinal materials are divided, such as qualified, unqualified or requiring further testing; an early warning threshold is set, and when one or more quality inspection indicators reach or exceed the early warning threshold, the control module immediately issues an early warning signal. The early warning signal can be transmitted to the operator or the quality inspection module through sound, light, text prompts, etc., so that timely measures can be taken to deal with it; relevant data and results are extracted from the database. Then, according to the preset report template, these data and results are filled in the report. Finally, it is output to the user in the form of an electronic document through a user interface or a network interface. The user can view or download the test report through a terminal device such as a computer or a mobile phone.

[0043] The effect of the above technical solution is that the control module can centrally receive data from multiple modules and devices, and perform data verification, format conversion, cleaning and standardization. This process ensures the accuracy, consistency and availability of the data, and provides a solid foundation for subsequent quality assessment and risk analysis; according to the types of Chinese medicinal materials and the preset test standards, the quality grade of each quality test indicator of Chinese medicinal materials is evaluated. This data-based evaluation method is more objective and accurate than traditional manual evaluation, and can timely discover quality problems in Chinese medicinal materials; by identifying and analyzing the possible quality risks in Chinese medicinal materials and setting early warning thresholds, when the test results reach or exceed the early warning threshold, an early warning signal can be immediately issued. This timely early warning mechanism helps to quickly respond to and deal with potential quality problems and avoid the occurrence of adverse consequences; according to the data analysis results and the preset report template, a detailed test report is automatically generated and output to the user in the form of an electronic document through the user interface or network interface. This automated report generation method not only improves work efficiency, but also enables users to easily obtain test results and related information; the entire technical solution combines multiple links such as data integration, quality assessment, risk warning and report generation, and through intelligent processing methods, it realizes comprehensive, accurate and efficient testing of the quality of Chinese herbal medicines. This helps to improve the overall quality and safety of the production, processing and use of Chinese herbal medicines.

[0044] In one embodiment of the present invention, the S43 includes: Based on the types and testing standards of Chinese medicinal materials, determine the key quality risk indicators, compare and analyze the data provided by the quality testing module with the preset quality standards, and identify possible quality risk points; Use machine learning algorithms to build a quality risk assessment model for Chinese herbal medicines; conduct quantitative assessment of the quality risks of Chinese herbal medicines; According to the output of the risk assessment model, the quality risks of Chinese medicinal materials are divided into different levels, such as low risk, medium risk and high risk; Set warning thresholds for each quality risk indicator based on quality risk assessment results and industry standards; Dynamically adjust the warning threshold according to the real-time changes in the quality inspection data of Chinese medicinal materials; and use adaptive learning algorithms or online update mechanisms to continuously optimize the warning threshold; When the quality inspection data reaches or exceeds the warning threshold, the warning mechanism is immediately triggered to send a warning signal to the control module and operators; Formulate corresponding risk response measures based on early warning signals and risk levels; the measures include but are not limited to isolation, re-inspection, return, and destruction of Chinese medicinal materials.

[0045] The working principle of the above technical solution is as follows: according to the types and testing standards of Chinese medicinal materials, first determine the key risk indicators that affect the quality of Chinese medicinal materials, such as heavy metal content, pesticide residues, insufficient content of active ingredients, etc. These indicators are the basis for subsequent risk assessment and early warning; compare and analyze the data provided by the quality inspection module with the preset quality standards to identify possible quality risk points. This step aims to preliminarily screen out batches of Chinese medicinal materials with quality problems through data comparison; use machine learning algorithms (such as logistic regression, decision trees, random forests, etc.) to build a Chinese medicinal material quality risk assessment model. This model can quantitatively evaluate the quality risk of Chinese medicinal materials based on quality inspection data and output the assessment results; according to the output results of the risk assessment model, the quality risk of Chinese medicinal materials is divided into different levels, such as low risk, medium risk and high risk. This step helps to take different countermeasures for Chinese medicinal materials with different risk levels; set early warning thresholds for each quality risk indicator based on quality risk assessment results and industry standards. These thresholds are key parameters for triggering the early warning mechanism. When the quality inspection data reaches or exceeds these thresholds, an early warning will be triggered; according to the real-time changes in the quality inspection data of Chinese medicinal materials, the early warning thresholds are dynamically adjusted. This step aims to ensure the accuracy and flexibility of the early warning mechanism, and to be able to adjust the early warning threshold in time according to the actual situation to avoid false alarms or missed alarms; and to continuously optimize the early warning threshold using adaptive learning algorithms or online update mechanisms. This step aims to continuously improve the accuracy and stability of the early warning mechanism through the learning ability of machine learning algorithms; when the quality inspection data reaches or exceeds the early warning threshold, the early warning mechanism is immediately triggered to send an early warning signal to the control module and operators. The early warning signal should contain key information such as risk level, risk indicators, and batches of Chinese medicinal materials, so that operators can take timely measures to deal with risks; formulate corresponding risk response measures based on the early warning signal and risk level. These measures may include isolation, re-inspection, return, and destruction of Chinese medicinal materials, etc., aiming to eliminate quality risks and ensure the safety and compliance of Chinese medicinal materials.

[0046] The effect of the above technical solution is: by determining key quality risk indicators based on the types and testing standards of Chinese medicinal materials, and using machine learning algorithms to build a quality risk assessment model, the quality risk of Chinese medicinal materials can be quantified more accurately. This data-driven method is more objective and accurate than traditional manual evaluation; real-time monitoring of Chinese medicinal materials quality test data, and triggering the early warning mechanism according to the preset early warning threshold, can detect potential quality problems at the first time. This timely early warning helps operators to take measures quickly to prevent the problem from expanding and reduce losses; by dynamically adjusting the early warning threshold and optimizing it using an adaptive learning algorithm or an online update mechanism, the early warning mechanism can be adjusted according to the real-time changes in the quality test data of Chinese medicinal materials, thereby improving the accuracy and flexibility of the early warning; the early warning signal contains key information such as risk level, risk indicator, and batch of Chinese medicinal materials, which helps operators quickly understand the risk situation and formulate targeted risk response measures; according to the early warning signal and risk level, corresponding risk response measures can be formulated, such as isolation, re-inspection, return, and destruction of Chinese medicinal materials. These measures help eliminate quality risks and ensure the safety and compliance of Chinese medicinal materials. They combine advanced technologies such as machine learning algorithms, adaptive learning algorithms, and online update mechanisms to improve the intelligence level of the quality inspection process for Chinese medicinal materials. This intelligent inspection process helps improve inspection efficiency and reduce the cost of manual intervention. By promptly discovering and handling quality problems in Chinese medicinal materials, the S43 technical solution helps ensure the stability and healthy development of the Chinese medicinal materials market. This helps to enhance consumers' trust in Chinese medicinal materials and promote the sustainable development of the Chinese medicinal materials industry.

[0047] One embodiment of the present invention, as Figure 2 As shown, a fully automatic integrated traditional Chinese medicine testing device, the device comprises: Variety screening module: It uses a high-precision camera and image processing unit to take high-definition photos of Chinese medicinal materials, and compares them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; Quality detection module: Through the integration of multiple sensors, including near-infrared spectrometer, moisture meter and heavy metal detector, multi-dimensional quality detection of Chinese medicinal materials is carried out, including moisture content, active ingredient content and heavy metal residue; Tumbling module: Based on the robotic arm and rotating platform, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module to ensure that all sides can be effectively photographed and tested. It is especially suitable for Chinese medicinal materials with complex shapes that are difficult to observe directly. Control module: responsible for receiving data from each module, executing preset algorithm logic, controlling the working rhythm of the tumbling module, comparing the data from the variety screening module to confirm the type of Chinese medicinal materials, and summarizing the information from the quality inspection module to form the final inspection report.

[0048] The working principle of the above technical solution is as follows: a high-precision camera is used to take high-definition photos of Chinese medicinal materials to ensure that the images are clear and rich in details; the image processing unit pre-processes the taken photos, such as denoising, enhancing contrast, etc., to improve the image quality; the processed images are feature extracted through a preset algorithm, and compared with the built-in Chinese medicine image database to automatically identify the type of Chinese medicinal materials; near-infrared spectroscopy technology is used to quickly and non-destructively detect the content of effective ingredients in Chinese medicinal materials; the moisture content of Chinese medicinal materials is accurately measured through specific measurement principles (such as capacitance method, resistance method, etc.); heavy metal residues in Chinese medicinal materials are detected using principles such as electrochemistry, optics or mass spectrometry to ensure that Chinese medicinal materials safety; according to the instructions of the control module, the robotic arm grabs the Chinese medicinal materials and places them on the rotating platform, and the rotating platform drives the Chinese medicinal materials to roll; the control module sends instructions to the rolling module according to the requirements of the variety screening module and the quality inspection module to ensure that all sides of the Chinese medicinal materials can be effectively photographed and inspected; the control module receives data from the variety screening module, the quality inspection module and the rolling module; executes the preset algorithm logic to process and analyze the received data; according to the processing results, the control module sends instructions to the rolling module to adjust its working rhythm; at the same time, the data of the variety screening module is compared to make a final confirmation of the type of Chinese medicinal materials, and the information of the quality inspection module is summarized to form a final inspection report.

[0049] The effects of the above technical solutions are as follows: through the integration of high-precision cameras, image processing units and multiple sensors, automatic identification and multi-dimensional quality inspection of Chinese medicinal materials are realized, greatly improving the efficiency and accuracy of inspection; the cooperation of the robotic arm and the rotating platform enables the Chinese medicinal materials to roll automatically, ensuring that all sides can be effectively photographed and inspected, reducing the tediousness and errors of manual operations; the variety screening module uses high-precision cameras and preset algorithms to quickly and accurately identify the types of Chinese medicinal materials, avoiding identification errors caused by human factors in traditional methods; the quality inspection module uses multiple sensors such as near-infrared spectrometers, moisture meters and heavy metal detectors to perform multi-dimensional quality inspections on Chinese medicinal materials, which can comprehensively reflect the quality status of Chinese medicinal materials and ensure the safety and effectiveness of Chinese medicinal materials; this method is particularly suitable for Chinese medicinal materials with complex shapes that are not easy to observe directly. Automatic rolling and all-round shooting can ensure that all sides of Chinese medicinal materials can be effectively inspected, improving the comprehensiveness and accuracy of the inspection; at the same time, the method is also applicable to Chinese medicinal materials of different types and specifications, and has strong versatility and flexibility; the control module can receive data from each module and execute preset algorithm logic to confirm the type of Chinese medicinal materials, while summarizing the information of the quality inspection module to form a final inspection report; this data integration and analysis method not only improves the accuracy and reliability of the inspection, but also provides strong data support for the quality control and traceability of Chinese medicinal materials; the application of this method can promote the modernization and standardization of the Chinese medicine industry, and improve the quality level and market competitiveness of Chinese medicinal materials; at the same time, the method can also provide scientific basis and technical support for the research and development, production, and sales of Chinese medicine, and promote the sustainable development of the Chinese medicine industry.

[0050] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A fully automatic integrated traditional Chinese medicine detection method, characterized in that: The detection method comprises: S1. The high-precision camera and image processing unit equipped in the variety screening module take high-definition photos of Chinese medicinal materials, and compare them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; S2, through the multiple sensors integrated in the quality detection module, multi-dimensional quality detection of Chinese medicinal materials is carried out; S3, based on the mechanical arm and rotating platform equipped with the tumbling module, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module; S4. Receive data from each module through the control module, execute the preset algorithm logic, control the tumbling module, compare the data from the variety screening module to confirm the type of Chinese medicinal materials, and summarize the information from the quality inspection module to form a final inspection report.

2. A fully automatic integrated traditional Chinese medicine detection method according to claim 1, characterized in that: Said S1 comprises: S11. Use the high-precision camera of the variety screening module and configure different light sources to capture the subtle features on the surface of Chinese medicinal materials; S12, preprocessing the collected image through an image processing unit, wherein the preprocessing includes denoising, contrast enhancement, and edge detection; S13, extract features from the preprocessed images based on deep learning algorithms, identify key features of Chinese medicinal materials, and use attention mechanisms to enhance focus on key areas; S14, inputting the extracted feature vector into the trained deep learning classifier, comparing it with the known Chinese medicinal material features in the built-in Chinese medicinal material image database, and identifying the type of Chinese medicinal material by calculating the similarity between the feature vectors; S15. If there are multiple high-matching options in the identification results, a second confirmation is performed using the uncertainty processing method combined with other characteristics of the Chinese medicinal materials.

3. A fully automatic integrated traditional Chinese medicine detection method according to claim 2, characterized in that: The S13 comprises: According to the types of Chinese medicinal materials and image characteristics, a deep learning model is selected, and feature extraction is performed to optimize the selected deep learning model; Use deep learning models to extract features from preprocessed Chinese medicinal materials images and identify key features of Chinese medicinal materials; Combined with near-infrared spectroscopy analysis technology, the spectral features of Chinese medicinal materials are extracted, and the image features and spectral features are fused through multimodal feature fusion methods; Introducing the attention mechanism into the deep learning model to enhance the extracted features; The principal component analysis was used to reduce the dimension of the extracted features, and the feature selection algorithm was used to select the feature subset that contributed to the identification of Chinese herbal medicine species; The feature vectors after dimension reduction and selection are concatenated or combined to generate feature vectors for identifying the types of Chinese medicinal materials.

4. A fully automatic integrated traditional Chinese medicine detection method according to claim 2, characterized in that: The S15 comprises: According to the output results of the deep learning classifier, the recognition results of Chinese medicinal materials are sorted by matching degree, and the top N options with the highest matching degree are selected as candidates; Perform differential analysis on the feature vectors of candidate objects to identify subtle differences; use odor sensors or gas chromatography-mass spectrometry to collect and analyze the odor of Chinese medicinal materials and extract characteristic odor components; The touch sensor or robotic arm is used to simulate the human hand touching the Chinese medicinal materials to collect the touch characteristics; the Bayesian classifier is used to fuse the visual features with the sensory features to calculate the posterior probability that each candidate object belongs to each type of Chinese medicinal material; The output results of multiple classifiers are integrated by using ensemble learning methods, and the uncertainty of the recognition results is evaluated based on the output results of the Bayesian classifier or ensemble learning method; If the uncertainty is high, verification or adjustment is performed; based on the output of the uncertainty processing method, the most likely type of Chinese medicinal material is selected as the final identification result; Compare the final recognition results with the actual situation and collect feedback data.

5. A fully automatic integrated traditional Chinese medicine detection method according to claim 1, characterized in that: The S2 comprises: S21, activating the near-infrared spectrometer in the quality inspection module, performing non-destructive scanning on the Chinese medicinal materials, obtaining near-infrared spectrum data thereof, and covering a wavelength range from 780 nm to 2526 nm; S22, preprocessing the collected spectral data, wherein the preprocessing includes smoothing, baseline correction and normalization to eliminate the influence of instrument noise and baseline drift on the analysis results; S23, using chemometric methods to analyze the pre-processed spectral data and establish a quantitative determination model for the active ingredients in Chinese medicinal materials; S24, drying the Chinese medicinal materials in a constant temperature drying oven, and calculating the moisture content by measuring the mass difference before and after drying; S25, using a capacitive sensor to measure the change in the dielectric constant of the Chinese medicinal material, and determining the moisture content according to the relationship between the moisture content and the dielectric constant; S26, crushing the Chinese medicinal materials, and converting the heavy metal elements in the Chinese medicinal materials into soluble forms by acid digestion or microwave digestion; S27, introducing the digested sample solution into an ICP-MS instrument, atomizing the sample and exciting it to a high energy state using high energy plasma, detecting the characteristic mass number of each element by a mass spectrometer, and performing trace analysis of heavy metal elements; S28. Process the data obtained from ICP-MS detection accordingly and evaluate the safety of heavy metal residues in Chinese medicinal materials according to relevant standards.

6. A fully automatic integrated traditional Chinese medicine detection method according to claim 5, characterized in that: The S23 comprises: Before using chemometric methods, statistical methods are used to detect outliers in spectral data and process them accordingly; The spectral data is featured by continuous projection algorithm to extract the characteristic wavelength that has the greatest influence on the determination of the effective ingredient content of traditional Chinese medicine. The pre-processed spectral data were used as independent variables, and the content of active ingredients in Chinese medicinal materials was used as dependent variables. The partial least squares method was used to establish a multivariate linear regression model for quantitative determination of the ingredients. The principal component analysis was performed on the spectral data, the principal components were extracted as new independent variables, and the model between the principal components and the content of effective ingredients in Chinese medicinal materials was established using regression methods; The regression version of support vector machine is used to perform nonlinear mapping on spectral data and establish a nonlinear relationship model between the content of active ingredients in Chinese medicinal materials and spectral data. K-fold cross validation was used to validate the established model and evaluate the model's predictive performance; and the optimization algorithm was used to tune the model's parameters; Based on the cross-validation results and model performance indicators, the advantages and disadvantages of different chemometric methods were compared, and the optimal model was selected for subsequent application.

7. A fully automatic integrated traditional Chinese medicine detection method according to claim 1, characterized in that: The S3 includes: S31, tumbling the Chinese medicinal materials according to the relevant characteristics of the Chinese medicinal materials and based on a preset tumbling strategy; S32. Evaluate and optimize the rollover strategy and adjust the rollover parameters through simulation experiments and actual test data feedback; S33. The robotic arm accurately grasps and stably places the Chinese medicinal materials based on visual servo technology or laser navigation technology. The rotating platform rolls according to the instructions of the control module, while the robotic arm maintains a stable grip on the Chinese medicinal materials. S34. During the tumbling process, the variety screening module and the quality inspection module continue to work, collect images and spectral data of Chinese medicinal materials in real time, and feed them back to the control module for processing and analysis in real time; S35. The control module integrates and processes the collected data to obtain comprehensive detection information of Chinese medicinal materials.

8. A fully automatic integrated traditional Chinese medicine detection method according to claim 7, characterized in that: The S32 includes: Using 3D modeling software or physical simulation platform, build a virtual model of Chinese herbal medicine according to its characteristics; at the same time, simulate the actions and interactions of the robotic arm, rotating platform and control module; In the simulation environment, according to the preset strategy, the Chinese medicinal materials are rolled over and recorded. The robot arm movements, the movement trajectory of the Chinese medicinal materials and possible collisions during the rolling process are recorded. Analyze the results of the simulation experiment to evaluate the effectiveness and safety of the rolling strategy; identify potential collision points, rolling instability areas, and risk points of damage to Chinese medicinal materials; During the actual testing process, the Chinese medicinal materials are tumbled according to the preset tumbling strategy, and sensors and testing equipment are used to collect images, spectra, and status data of the mechanical arm and rotating platform of the Chinese medicinal materials in real time; Preprocess the collected data, compare the actual test data with the simulation experiment results, analyze the performance of the rollover strategy in actual application, and identify differences and potential problems; Extract the key features of the rolling strategy from simulation experiments and actual test data, and use feature selection algorithms to select the features that have the greatest impact on the rolling effect; Based on the machine learning algorithm, a prediction model between the rolling strategy and the rolling effect of Chinese medicinal materials is established; according to the output results of the prediction model, the rolling strategy is adjusted and optimized; Use multi-objective optimization algorithms to find the optimal solution among multiple objectives.

9. A fully automatic integrated traditional Chinese medicine detection method according to claim 1, characterized in that: The S4 comprises: S41, the control module receives all data from the variety screening module, the quality inspection module, the mechanical arm and the rotating platform, and performs data verification and format conversion; cleans and standardizes the received data; S42. According to the types and testing standards of Chinese medicinal materials, conduct quality grade assessment on various quality testing indicators of Chinese medicinal materials to determine whether they meet the quality standards; S43. Identify and analyze the possible quality risks in Chinese herbal medicines and set warning thresholds. When the test results reach or exceed the warning thresholds, a warning signal is issued; S44. Automatically generate a detailed test report based on the data analysis results and the report template, and output it to the user in the form of an electronic document through a user interface or a network interface.

10. A fully automatic integrated Chinese medicine testing device, characterized in that: The device comprises: Variety screening module: It uses a high-precision camera and image processing unit to take high-definition photos of Chinese medicinal materials, and compares them with the built-in Chinese medicinal material image database through a preset algorithm to automatically identify the types of Chinese medicinal materials; Quality detection module: Through the integration of multiple sensors, including near-infrared spectrometer, moisture meter and heavy metal detector, multi-dimensional quality detection of Chinese medicinal materials is carried out, including moisture content, active ingredient content and heavy metal residue; Tumbling module: Based on the robotic arm and rotating platform, the Chinese medicinal materials are automatically tumbled according to the instructions of the control module; Control module: responsible for receiving data from each module, executing preset algorithm logic, controlling the tumbling module, comparing the data from the variety screening module to confirm the type of Chinese medicinal materials, and summarizing the information from the quality inspection module to form the final inspection report.

Images