Method and device for detecting content of key medicinal components of traditional Chinese medicine

Abstract

The invention provides a traditional Chinese medicine key medicinal component content detection method and device, and is applied to the technical field of component detection. The method comprises the following steps: acquiring near infrared spectrum data of a plant traditional Chinese medicine sample to be detected, wherein the near infrared spectrum data is used for indicating molecular vibration information; inputting the near infrared spectrum data into a traditional Chinese medicine key effective component quantitative correction model to obtain the target component content of the plant traditional Chinese medicine sample to be detected; wherein the quantitative correction model for the key medicinal components of the traditional Chinese medicine comprises a feature extraction module and a content prediction module, the feature extraction module is used for extracting spectral features of the near infrared spectral data, and the content prediction module is used for predicting the component content of an input sample based on the spectral features. And the content prediction module comprises a nonlinear mapping relation between spectral characteristics and component contents.

Description

Technical Field

[0001] The present invention relates to the technical field of component detection, and in particular to a method and device for detecting the content of key medicinal components of traditional Chinese medicine. Background Art

[0002] As an important part of traditional Chinese medicine, the quality control of Chinese medicine is directly related to clinical efficacy and medication safety, and plays a decisive role in ensuring patients' treatment effects and medication safety.

[0003] In existing technologies, thin-layer chromatography (TLC) and high-performance liquid chromatography (HPLC) can be used to detect key active ingredients in traditional Chinese medicines. TLC involves spotting a TCM extract onto a carrier such as a silica gel plate, separating the components by utilizing the differences in their migration speeds in a developing solvent, and then visualizing and analyzing the components through chemical color development. HPLC uses a high-pressure pump to inject the mobile phase and sample into a chromatographic column containing a stationary phase. Separation is achieved based on differences in the distribution coefficients of the components between the stationary and mobile phases, and detection is performed using a detector.

[0004] However, this traditional analytical method relies on chemical color development and physical separation, and has disadvantages such as complex operation, long detection cycle, and high environmental pollution risk. It cannot meet the industrial requirements for rapid, accurate, and environmentally friendly detection of key active ingredients in traditional Chinese medicine. Summary of the Invention

[0005] The present invention provides a method and device for detecting the content of key medicinal ingredients of traditional Chinese medicine, which are used to solve the problem that the existing technology cannot meet the requirements of industrialization for rapid, accurate and environmentally friendly detection of key medicinal ingredients of traditional Chinese medicine.

[0006] The present invention provides a method for detecting the content of key medicinal components of traditional Chinese medicine, comprising: obtaining near-infrared spectral data of a plant traditional Chinese medicine sample to be tested, wherein the near-infrared spectral data is used to indicate molecular vibration information; inputting the near-infrared spectral data into a quantitative calibration model for key medicinal components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; wherein the quantitative calibration model for key medicinal components of traditional Chinese medicine comprises a feature extraction module and a content prediction module, wherein the feature extraction module is used to extract spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features, and the content prediction module comprises a nonlinear mapping relationship between spectral features and component content.

[0007] According to a method for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, the feature extraction module includes a preprocessing layer based on wavelet transform and a convolutional neural network layer, the convolutional neural network layer includes 6 3×3 convolution kernels connected in sequence; the content prediction module includes a parallel linear regression branch and a support vector machine regression branch, the linear regression branch includes a first fully connected layer and a linear regression layer connected in sequence, the number of neurons in the first fully connected layer is 32, and the linear regression layer is used to output the predicted value of the target ingredient content.

[0008] According to a method for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, obtaining near-infrared spectral data of a botanical Chinese medicine sample to be tested includes: collecting near-infrared spectral data of the botanical Chinese medicine sample to be tested; performing a preprocessing operation on the near-infrared spectral data, wherein the preprocessing operation includes at least one of the following: abnormal spectrum identification and elimination, spectrum correction, characteristic band screening, and mathematical transformation of spectral data.

[0009] According to a method for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, the mathematical transformation of spectral data includes performing first-order derivative, second-order derivative, multivariate scattering correction, vector normalization and convolution smoothing filtering on the original spectrum.

[0010] According to a method for detecting the content of key effective components of traditional Chinese medicine provided by the present invention, before inputting the near-infrared spectral data into a quantitative correction model for key effective components of traditional Chinese medicine, the method further includes: obtaining near-infrared spectral data and target component content of plant traditional Chinese medicine samples from different origins and different batches; constructing a training set and a test set based on the near-infrared spectral data and target component content of plant traditional Chinese medicine samples from different origins and different batches; using the training set and the test set to train candidate neural network models, so that each trained candidate neural network model establishes a mapping relationship between the spectral characteristics corresponding to the plant traditional Chinese medicine sample and the target component content; and determining a quantitative correction model for key effective components of traditional Chinese medicine from the candidate neural network models based on preset evaluation indicators.

[0011] According to a method for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, the preset evaluation indicators include a training set correlation coefficient, a test set correlation coefficient, a training set root mean square error, and a test set root mean square error.

[0012] The present invention also provides a device for detecting the content of key effective components of traditional Chinese medicine, comprising the following modules: an acquisition module and a processing module; the acquisition module is used to acquire near-infrared spectral data of a plant traditional Chinese medicine sample to be tested, and the near-infrared spectral data is used to indicate molecular vibration information; the processing module is used to input the near-infrared spectral data into a quantitative calibration model for key effective components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; wherein the quantitative calibration model for key effective components of traditional Chinese medicine comprises a feature extraction module and a content prediction module, the feature extraction module is used to extract spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features, and the content prediction module includes a nonlinear mapping relationship between spectral features and component content.

[0013] According to a device for detecting the content of key medicinal ingredients in traditional Chinese medicine provided by the present invention, the feature extraction module includes a preprocessing layer based on wavelet transform and a convolutional neural network layer, the convolutional neural network layer includes 6 3×3 convolution kernels connected in sequence; the content prediction module includes a parallel linear regression branch and a support vector machine regression branch, the linear regression branch includes a first fully connected layer and a linear regression layer connected in sequence, the number of neurons in the first fully connected layer is 32, and the linear regression layer is used to output the predicted value of the target ingredient content.

[0014] According to a device for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, the acquisition module is used to collect near-infrared spectral data of a botanical traditional Chinese medicine sample to be tested; and preprocess the near-infrared spectral data, wherein the preprocessing operation includes at least one of the following: abnormal spectrum identification and elimination, spectrum correction, characteristic band screening, and mathematical transformation of spectral data.

[0015] According to a device for detecting the content of key medicinal ingredients in traditional Chinese medicine provided by the present invention, the mathematical transformation of spectral data includes first-order derivative, second-order derivative, multivariate scattering correction, vector normalization and convolution smoothing filtering using the original spectrum.

[0016] According to a device for detecting the content of key effective components of traditional Chinese medicine provided by the present invention, the acquisition module is used to obtain near-infrared spectral data and target component content of plant traditional Chinese medicine samples from different origins and different batches; the processing module is used to construct a training set and a test set based on the near-infrared spectral data and target component content of plant traditional Chinese medicine samples from different origins and different batches; the training set and the test set are used to train candidate neural network models, so that each trained candidate neural network model establishes a mapping relationship between the spectral characteristics corresponding to the plant traditional Chinese medicine samples and the target component content; and a quantitative correction model for key effective components of traditional Chinese medicine is determined from the candidate neural network models based on preset evaluation indicators.

[0017] According to a device for detecting the content of key effective ingredients in traditional Chinese medicine provided by the present invention, the preset evaluation indicators include a training set correlation coefficient, a test set correlation coefficient, a training set root mean square error, and a test set root mean square error.

[0018] The present invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for detecting the content of key active ingredients in traditional Chinese medicine as described above is implemented.

[0019] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for detecting the content of key active ingredients in traditional Chinese medicine.

[0020] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for detecting the content of key active ingredients in traditional Chinese medicine.

[0021] The method and device for detecting the content of key medicinal ingredients in traditional Chinese medicine provided by the present invention can combine near-infrared spectral data with a prediction network to quantitatively analyze the content of target ingredients in botanical traditional Chinese medicines. Since near-infrared spectral data is used to indicate molecular vibration information, and molecular vibration information can reflect the presence and content of ingredients, rapid, non-destructive, and high-precision detection of key medicinal ingredients in traditional Chinese medicines is achieved, solving the problems of low efficiency, dependence on chemical reagents, and complex operation of traditional methods, and having significant industrial application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is one of the flow charts of the method for detecting the content of key active ingredients in traditional Chinese medicine provided by the present invention; Figure 2 This is the second flow chart of the method for detecting the content of key medicinal ingredients of traditional Chinese medicine provided by the present invention; Figure 3 This is a schematic diagram of the structure of the device for detecting the content of key medicinal ingredients in traditional Chinese medicine provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0025] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0026] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0027] In order to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order.

[0028] The embodiments of the present application describe some exemplary embodiments for the purpose of explanation. It should be understood that the present application can be implemented in other ways that are not specifically shown in the drawings.

[0029] like Figure 1As shown, the embodiment of the present application provides a method for detecting the content of key medicinal ingredients in traditional Chinese medicine, which can be applied to a device for detecting the content of key medicinal ingredients in traditional Chinese medicine. The method for detecting the content of key medicinal ingredients in traditional Chinese medicine may include S101-S104: S101. The device for detecting the content of key medicinal ingredients in traditional Chinese medicine obtains the near-infrared spectral data and target ingredient content of plant traditional Chinese medicine samples from different origins and batches.

[0030] First, to fully reflect the characteristics of botanical Chinese medicines under different growth environments and production conditions, botanical Chinese medicine samples from different production areas and batches are collected to ensure sample diversity. After collection, the herbs are pulverized and then sieved to obtain a uniform coarse powder. Next, take the coarse powder prepared above, add an appropriate amount of petroleum ether, and perform degreasing operation twice. After degreasing, evaporate the solvent to obtain a defatted sample. Subsequently, use 1.0 mol / L hydrochloric acid solution to hydrolyze the defatted sample, and heat the mixed solution under reflux for 5 hours. After the reaction is completed, cool it slightly, and then transfer the residue and residual liquid to a volumetric flask. Add chloroform to the cooled solution for liquid-liquid extraction, shake it thoroughly to transfer the target substance in the sample to the chloroform layer, let it stand for stratification, carefully recover the chloroform layer, and dilute the extract to the specified volume for standby use. After completing the above operations, start preparing the reference solution. The reference solution can provide a known concentration of the active substance. By analyzing the spectral characteristics of the reference solution at different concentrations, a standard curve can be drawn for the botanical Chinese medicine sample, thus providing reliable reference content information for model establishment and verification.

[0031] The specific operation is to accurately weigh the target component reference substance, add chloroform to dissolve it, and dilute to the required concentration. After the preparation is completed, the stability, precision and sample recovery of the reference solution are verified. Only if it meets the detection requirements can it be used for subsequent experiments. Then the thin layer chromatography conditions are set, and a homemade silica gel plate is used. After spotting, the thin layer plate is placed in a developing cylinder for saturation. Cyclohexane-ethyl acetate is used as the developing agent. After the development is completed, sulfuric acid ethanol solution is sprayed for color development. The measurement wavelength of the near-infrared spectrometer can be set to 530nm, the reference wavelength can be set to 680nm, and the scanning parameters can be matched and adjusted according to the near-infrared spectrometer used. A standard curve is drawn by preparing reference solution of different concentrations to ensure that its linear range meets the detection requirements. Finally, the test and reference solutions were precisely pipetted and developed according to the TLC conditions described above. The target component content in the sample was calculated using the two-point external standard method. To ensure the reliability and accuracy of the results, each sample was assayed in triplicate, with the results calculated on a dry basis, and the average value was calculated.

[0032] It should be noted that the target component can be the key pharmacological substance and / or soluble solid in the botanical Chinese medicine sample.

[0033] S102. The device for detecting the content of key medicinal ingredients in traditional Chinese medicine constructs a training set and a test set based on the near-infrared spectral data and target ingredient content of plant traditional Chinese medicine samples from different origins and different batches.

[0034] Optionally, the device for detecting the content of key medicinal ingredients in traditional Chinese medicine can divide all sample data into a training set and a test set in a ratio of 8:2.

[0035] Optionally, before constructing the training and test sets, the apparatus for detecting the content of key active ingredients in traditional Chinese medicines can preprocess the collected near-infrared spectral data. Specifically, this includes identifying and removing abnormal near-infrared spectra, correcting the spectra after removing the abnormal near-infrared spectra, and screening the characteristic bands of the corrected near-infrared spectra.

[0036] Optionally, the method for identifying abnormal near-infrared spectra collected can be principal component analysis-Mahalanobis distance method, the method for spectrum correction can be convolution smoothing method and linear function normalization method, and the method for screening bands can be competitive adaptive reweighting algorithm.

[0037] S103. The device for detecting the content of key medicinal ingredients of traditional Chinese medicine uses the training set and the test set to train the candidate neural network model, so that each trained candidate neural network model establishes a mapping relationship between the spectral characteristics corresponding to the plant traditional Chinese medicine sample and the target ingredient content.

[0038] Specifically, a candidate neural network model was first constructed, comprising a feature extraction module and a content prediction module. The feature extraction module included a wavelet transform-based preprocessing layer and a convolutional neural network layer, with the convolutional neural network layer comprising six sequentially connected 3×3 convolution kernels. The content prediction module comprised a parallel linear regression branch and a support vector machine regression branch, with the linear regression branch comprising a first fully connected layer and a linear regression layer, each connected in sequence. The first fully connected layer had 32 neurons, and the linear regression layer was used to output the predicted value of the target component content.

[0039] In the feature extraction module, the input near-infrared spectral data is first preprocessed using a wavelet transform. This step is necessary because near-infrared spectral data may contain high-frequency noise, which can interfere with subsequent analysis. Wavelet transform preprocessing effectively removes this high-frequency noise, making the data purer. After wavelet transform preprocessing, the data enters the convolutional neural network layer. In this layer, six 3×3 convolution kernels sequentially convolve the data. Each convolution kernel acts as a "feature detector." During the convolution operation, it extracts features from different angles and levels, providing rich information for subsequent analysis.

[0040] In the content prediction module, the features output by the convolutional neural network layer are respectively input into the linear regression branch and the support vector machine regression branch. The linear regression branch includes a first fully connected layer and a linear regression layer connected in sequence. The number of neurons in the first fully connected layer is 32. The linear regression layer is used to output the predicted value of the target component content.

[0041] Throughout the model training process, the Adagrad optimizer is used to optimize model training. The Adagrad optimizer adaptively adjusts the learning rate based on the gradient of each parameter during training, making model training more efficient. Here, the learning rate is set to 0.003, and the gradient of the mean squared error loss function with L1 regularization (regularization coefficient of 0.0001) is calculated. L1 regularization prevents model overfitting. By adding L1 regularization to the loss function, the model is more generalizable and avoids over-reliance on certain features in the training data. Based on the calculated gradients, the model weights are updated. This iterative training continues through multiple rounds, continuously adjusting the model parameters until the loss function converges on the training set.

[0042] S104. The device for detecting the content of key medicinal ingredients of traditional Chinese medicine determines a quantitative correction model for the content of key medicinal substances of traditional Chinese medicine from the candidate neural network models based on preset evaluation indicators.

[0043] Optionally, the preset evaluation indicators include a training set correlation coefficient, a test set correlation coefficient, a training set root mean square error, and a test set root mean square error.

[0044] like Figure 2 As shown, the embodiment of the present application provides a method for detecting the content of key medicinal ingredients of traditional Chinese medicine, which may also include S201-S202: S201. A device for detecting the content of key medicinal ingredients of traditional Chinese medicine obtains near-infrared spectrum data of a plant traditional Chinese medicine sample to be tested.

[0045] The above-mentioned near-infrared spectrum data is used to indicate molecular vibration information.

[0046] It's important to note that when infrared light shines on a botanical herbal sample, the molecules within it absorb specific frequencies of infrared light. This is because the atoms within the molecule, connected by chemical bonds, vibrate at different energy states. When the frequency of these vibrations matches certain frequencies of infrared light, absorption occurs. In other words, infrared spectral data is actually an outward reflection of molecular vibrations, recording their characteristics. Different components have unique molecular structures and, consequently, specific molecular vibration patterns. By analyzing infrared spectral data, characteristic absorption peaks associated with the target component can be identified. Based on the intensities of these absorption peaks, the content of the target component in the botanical herbal sample can be inferred.

[0047] Optionally, the device for detecting the content of key effective ingredients in traditional Chinese medicine obtains near-infrared spectral data of plant-based traditional Chinese medicine samples, including: collecting near-infrared spectral data of the plant-based traditional Chinese medicine samples to be tested; performing preprocessing operations on the near-infrared spectral data, and the preprocessing operations include at least one of the following: abnormal spectrum identification and elimination, spectrum correction, characteristic band screening, and mathematical transformation of spectral data.

[0048] Specifically, abnormal spectrum identification and removal refers to the use of specific algorithms and techniques to identify abnormal spectral data caused by sample contamination, instrument failure, or other reasons, and remove them from the data set to prevent these abnormal data from adversely affecting subsequent analysis. Spectral correction is to eliminate spectral deviations caused by instrument errors, environmental factors, etc., so that the spectral data can more accurately reflect the true characteristics of the sample. Feature band screening is to select specific spectral bands that are closely related to the content of key medicinal substances in botanical Chinese medicines from the entire spectral range. These spectral bands contain more valuable information, which can simplify the training and analysis process of the subsequent regression deep learning model, improve analysis efficiency, and improve model accuracy.

[0049] Optionally, the mathematical transformation of the spectral data includes performing first-order derivative, second-order derivative, multivariate scattering correction, vector normalization and convolution smoothing filtering on the original spectrum.

[0050] Specifically, first-order and second-order derivatives can highlight spectral trends and subtle features, helping to uncover information hidden in the original spectrum; multivariate scattering correction can correct for spectral baseline drift and deformation caused by factors such as sample particle size and scattering; vector normalization normalizes spectral data to make data from different samples comparable; and convolution smoothing filtering can effectively remove noise from the spectrum, making the spectral curve smoother and improving data stability. Through these spectral data mathematical transformation methods, the original spectral data can be optimized and processed from different perspectives, providing strong support for the subsequent accurate analysis of the content of key active ingredients in botanical traditional Chinese medicines.

[0051] S202. The device for detecting the content of key medicinal components of traditional Chinese medicine inputs the near-infrared spectrum data into a quantitative calibration model for key medicinal components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested.

[0052] Optionally, the quantitative correction model of key effective ingredients of traditional Chinese medicine includes a feature extraction module and a content prediction module, wherein the feature extraction module is used to extract the spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features, and the content prediction module includes a nonlinear mapping relationship between the spectral features and the component content.

[0053] The processed near-infrared spectral data is input into the trained quantitative calibration model for key effective components of traditional Chinese medicine. After feature extraction and content prediction, the quantitative calibration model for key effective components of traditional Chinese medicine can finally output the target component content of the plant traditional Chinese medicine sample to be tested.

[0054] In the embodiments of the present application, near-infrared spectral data can be combined with a prediction network to perform quantitative analysis on the content of target components in botanical Chinese medicines. Since near-infrared spectral data is used to indicate molecular vibration information, and molecular vibration information can reflect the presence and content of components, rapid, non-destructive, and high-precision detection of key effective components of Chinese medicines is achieved, solving the problems of low efficiency, dependence on chemical reagents, and complex operation of traditional methods, and having significant industrial application value.

[0055] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] The method for detecting the content of key pharmacological ingredients in traditional Chinese medicines provided in the embodiments of the present application can be performed by a device for detecting the content of key pharmacological ingredients in traditional Chinese medicines, or by a control module for detecting the content of key pharmacological ingredients in traditional Chinese medicines in the device. In the embodiments of the present application, the device for detecting the content of key pharmacological ingredients in traditional Chinese medicines is used as an example to illustrate the device for detecting the content of key pharmacological ingredients in traditional Chinese medicines provided in the embodiments of the present application.

[0057] It should be noted that, in the embodiment of the present application, the functional modules of the detection device for the content of key medicinal ingredients of traditional Chinese medicine can be divided according to the above-mentioned method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there can be another division method.

[0058] like Figure 3 As shown, an embodiment of the present application provides a device 300 for detecting the content of key effective components of traditional Chinese medicine. The device 300 for detecting the content of key effective components of traditional Chinese medicine includes: an acquisition module 301 and a processing module 302. The acquisition module 301 is used to acquire the near-infrared spectral data of the plant traditional Chinese medicine sample to be tested, and the near-infrared spectral data is used to indicate molecular vibration information; the processing module 302 is used to input the near-infrared spectral data into a quantitative calibration model for key effective components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; wherein the quantitative calibration model for key effective components of traditional Chinese medicine includes a feature extraction module and a content prediction module, the feature extraction module is used to extract the spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features, and the content prediction module includes a nonlinear mapping relationship between spectral features and component content.

[0059] Optionally, the feature extraction module includes a preprocessing layer based on wavelet transform and a convolutional neural network layer, the convolutional neural network layer includes 6 3×3 convolution kernels connected in sequence; the content prediction module includes a parallel linear regression branch and a support vector machine regression branch, the linear regression branch includes a first fully connected layer and a linear regression layer connected in sequence, the number of neurons in the first fully connected layer is 32, and the linear regression layer is used to output the predicted value of the target component content.

[0060] Optionally, the acquisition module 301 is used to collect near-infrared spectral data of the botanical Chinese medicine sample to be tested; and perform preprocessing operations on the near-infrared spectral data, wherein the preprocessing operations include at least one of the following: abnormal spectrum identification and elimination, spectrum correction, characteristic band screening, and spectral data mathematical transformation.

[0061] Optionally, the mathematical transformation of the spectral data includes performing first-order derivative, second-order derivative, multivariate scattering correction, vector normalization and convolution smoothing filtering on the original spectrum.

[0062] Optionally, the acquisition module 301 is used to obtain near-infrared spectral data and target component content of plant-based Chinese medicine samples from different origins and different batches; the processing module 302 is used to construct a training set and a test set based on the near-infrared spectral data and target component content of plant-based Chinese medicine samples from different origins and different batches; the training set and the test set are used to train the candidate neural network model, so that each trained candidate neural network model establishes a mapping relationship between the spectral characteristics corresponding to the plant-based Chinese medicine samples and the target component content; and a quantitative correction model for key effective components of Chinese medicine is determined from the candidate neural network model based on preset evaluation indicators.

[0063] Optionally, the preset evaluation indicators include a training set correlation coefficient, a test set correlation coefficient, a training set root mean square error, and a test set root mean square error.

[0064] In the embodiments of the present application, near-infrared spectral data can be combined with a prediction network to perform quantitative analysis on the content of target components in botanical Chinese medicines. Since near-infrared spectral data is used to indicate molecular vibration information, and molecular vibration information can reflect the presence and content of components, rapid, non-destructive, and high-precision detection of key effective components of Chinese medicines is achieved, solving the problems of low efficiency, dependence on chemical reagents, and complex operation of traditional methods, and having significant industrial application value.

[0065] Figure 4 An example of a physical structure diagram of an electronic device is shown below. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to execute a method for detecting the content of key medicinal components in traditional Chinese medicine. The method includes: obtaining near-infrared spectral data of a botanical Chinese medicine sample to be tested, wherein the near-infrared spectral data is used to indicate molecular vibration information; inputting the near-infrared spectral data into a quantitative calibration model for key medicinal components in traditional Chinese medicine to obtain the target component content of the botanical Chinese medicine sample to be tested; wherein the quantitative calibration model for key medicinal components in traditional Chinese medicine includes a feature extraction module and a content prediction module, wherein the feature extraction module is used to extract spectral features of the near-infrared spectral data; and the content prediction module is used to predict the component content of the input sample based on the spectral features. The content prediction module includes a nonlinear mapping relationship between spectral features and component content.

[0066] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0067] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for detecting the content of key effective components of traditional Chinese medicine provided by the above-mentioned methods, the method including: obtaining near-infrared spectral data of the plant traditional Chinese medicine sample to be tested, the near-infrared spectral data being used to indicate molecular vibration information; inputting the near-infrared spectral data into a quantitative calibration model for key effective components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; wherein the quantitative calibration model for key effective components of traditional Chinese medicine includes a feature extraction module and a content prediction module, the feature extraction module is used to extract the spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features, and the content prediction module includes a nonlinear mapping relationship between spectral features and component content.

[0068] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for detecting the content of key effective components of traditional Chinese medicine provided by the above-mentioned methods, the method comprising: obtaining near-infrared spectral data of the plant traditional Chinese medicine sample to be tested, the near-infrared spectral data being used to indicate molecular vibration information; inputting the near-infrared spectral data into a quantitative calibration model for key effective components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; wherein the quantitative calibration model for key effective components of traditional Chinese medicine comprises a feature extraction module and a content prediction module, the feature extraction module being used to extract spectral features of the near-infrared spectral data, the content prediction module being used to predict the component content of the input sample based on the spectral features, and the content prediction module comprising a nonlinear mapping relationship between spectral features and component content.

[0069] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0070] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for detecting the content of key active ingredients in traditional Chinese medicine, characterized in that: include: Acquiring near-infrared spectral data of a plant-based Chinese medicine sample to be tested, wherein the near-infrared spectral data is used to indicate molecular vibration information; Inputting the near-infrared spectral data into a quantitative calibration model for key effective components of traditional Chinese medicine to obtain the target component content of the plant traditional Chinese medicine sample to be tested; Among them, the quantitative correction model of key effective ingredients of traditional Chinese medicine includes a feature extraction module and a content prediction module. The feature extraction module is used to extract the spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features. The content prediction module includes a nonlinear mapping relationship between spectral features and component content.

2. The method for detecting the content of key active ingredients in traditional Chinese medicine according to claim 1, wherein: The feature extraction module includes a preprocessing layer based on wavelet transform and a convolutional neural network layer, the convolutional neural network layer includes 6 3×3 convolution kernels connected in sequence; the content prediction module includes a parallel linear regression branch and a support vector machine regression branch, the linear regression branch includes a first fully connected layer and a linear regression layer connected in sequence, the number of neurons in the first fully connected layer is 32, and the linear regression layer is used to output the predicted value of the target component content.

3. The method for detecting the content of key active ingredients in traditional Chinese medicine according to claim 1, wherein: The method of obtaining near infrared spectroscopy data of the plant Chinese medicine sample to be tested includes: Collect near-infrared spectral data of the plant Chinese medicine samples to be tested; The near-infrared spectral data is preprocessed, wherein the preprocessing operation includes at least one of the following: abnormal spectrum identification and elimination, spectrum correction, characteristic band screening, and spectral data mathematical transformation.

4. The method for detecting the content of key active ingredients in traditional Chinese medicine according to claim 3, wherein: The mathematical transformation of the spectral data includes first-order derivative, second-order derivative, multivariate scattering correction, vector normalization and convolution smoothing filtering using the original spectrum.

5. The method for detecting the content of key active ingredients in traditional Chinese medicine according to any one of claims 1 to 4, wherein: Before inputting the near-infrared spectral data into the quantitative calibration model for key effective components of traditional Chinese medicine, the method further comprises: Obtain near-infrared spectral data and target component content of botanical Chinese medicine samples from different origins and batches; The training set and test set were constructed based on the near-infrared spectral data and target component content of herbal Chinese medicine samples from different origins and batches; The candidate neural network models are trained using the training set and the test set, so that each trained candidate neural network model establishes a mapping relationship between the spectral characteristics corresponding to the botanical Chinese medicine sample and the target component content; Based on preset evaluation indicators, a quantitative correction model for key effective components of traditional Chinese medicine is determined from the candidate neural network models.

6. The method for detecting the content of key active ingredients in traditional Chinese medicine according to claim 5, wherein: The preset evaluation indicators include the training set correlation coefficient, the test set correlation coefficient, the training set root mean square error and the test set root mean square error.

7. A device for detecting the content of key medicinal ingredients in traditional Chinese medicine, characterized in that: include: Acquisition module and processing module; The acquisition module is used to acquire near-infrared spectrum data of the botanical Chinese medicine sample to be tested, and the near-infrared spectrum data is used to indicate molecular vibration information; The processing module is used to input the near-infrared spectral data into a quantitative calibration model for key medicinal components of traditional Chinese medicine to obtain the target component content of the botanical traditional Chinese medicine sample to be tested; Among them, the quantitative correction model of key effective ingredients of traditional Chinese medicine includes a feature extraction module and a content prediction module. The feature extraction module is used to extract the spectral features of the near-infrared spectral data, and the content prediction module is used to predict the component content of the input sample based on the spectral features. The content prediction module includes a nonlinear mapping relationship between spectral features and component content.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for detecting the content of key effective ingredients in traditional Chinese medicine as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting the content of key active ingredients in traditional Chinese medicine as described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for detecting the content of key active ingredients in traditional Chinese medicine as claimed in any one of claims 1 to 6 is implemented.

Images