Traditional Chinese medicinal material production place tracing method and device, electronic equipment and storage medium

Abstract

The invention discloses a traditional Chinese medicinal material production place tracing method and device, electronic equipment and a storage medium, and relates to the technical field of traditional Chinese medicinal material identification. The method comprises the following steps: collecting a three-dimensional fluorescence spectrum of a solution corresponding to a traditional Chinese medicinal material to be detected; performing high-order cyclic factorization on the three-dimensional fluorescence spectrum of the solution corresponding to the to-be-detected traditional Chinese medicinal material to obtain a three-dimensional fluorescence spectrum of each component in the solution corresponding to the to-be-detected traditional Chinese medicinal material; and inputting the three-dimensional fluorescence spectrum of each component in the solution corresponding to the to-be-detected traditional Chinese medicinal material into a pre-trained random forest model, and outputting the production place of the to-be-detected traditional Chinese medicinal material. By adopting the traditional Chinese medicinal material production place tracing method, the production place of the traditional Chinese medicinal material to be detected can be quickly and accurately determined, and the sensitivity is high.

Description

Technical Field

[0001] The present application relates to the technical field of Chinese medicinal material identification, and in particular to a method, device, electronic device and storage medium for tracing the origin of Chinese medicinal materials. Background Art

[0002] Authentic medicinal materials refer to genuine Chinese medicinal materials that grow in specific natural conditions and ecological environments and are selected through long-term clinical application of traditional Chinese medicine. They have the characteristics of excellent variety, stable quality and obvious regional characteristics. Their quality and efficacy are superior to similar medicinal materials from other regions.

[0003] At present, there are many fake and inferior Chinese medicinal materials in the market, which seriously affects the efficacy and safety of traditional Chinese medicine. Therefore, it is very important to trace the origin of Chinese medicinal materials. However, the relevant technology mainly relies on experienced pharmacists and experts to observe the appearance, smell and texture of medicinal materials for sensory identification, which is highly subjective and easily limited by personal experience and technical level, making it difficult to achieve rapid and accurate identification. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the relevant technology, it is desired to provide a method, device, electronic device and storage medium for tracing the origin of Chinese medicinal materials, which can accurately identify the origin of Chinese medicinal materials and improve the detection efficiency.

[0005] In a first aspect, the present application provides a method for tracing the origin of a Chinese medicinal material, the method comprising:

[0006] Collecting a three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be tested;

[0007] Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected;

[0008] The three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected is input into a pre-trained random forest model, and the origin of the Chinese medicinal material to be detected is output.

[0009] Optionally, the random forest model in some embodiments of the present application is trained by the following steps:

[0010] Collecting three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in samples from different origins, and establishing a mapping relationship between the origins and the three-dimensional fluorescence spectra of solutions corresponding to the Chinese medicinal materials in the samples;

[0011] Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample;

[0012] The random forest model is trained based on the mapping relationship and the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample.

[0013] Optionally, the three-dimensional fluorescence spectrum X(I×J×K) of the solution corresponding to the sample Chinese medicinal material in some embodiments of the present application includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E, and each element x in X(I×J×K) ijk for:

[0014]

[0015] Among them, x ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j, n), c in the relative emission spectrum matrix B(J×N) kn Represents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

[0016] Optionally, in some embodiments of the present application, when a high-order cyclic factor decomposition is performed on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample, the iterative expression of the relative excitation spectrum matrix A is:

[0017] a (i) T =((C + X i.. B). / (B T B)+(B + X i.. C). / (C T C));

[0018] The iterative expression of the relative emission spectrum matrix B is:

[0019] b (j) T =(A + X .j. C). / (C T C)+(C + X .j. A). / (A T A));

[0020] The iterative expression of the relative concentration matrix C is:

[0021] c( k) T =(B + X ..k A). / (A T A)+(A + X ..k B). / (B T B));

[0022] The three-dimensional trilinear matrix is ​​represented as:

[0023] X i.. =Bdiag(a (i) )C T +E i.. ;

[0024] X .j. =Cdiag(b (j) )A T +E .j. ;

[0025] X ..k =Adiag(c (k) )B T +E ..k ;

[0026] Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; X i.. represents the i-th horizontal plane matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X .j. represents the j-th side matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X ..k The kth positive matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C.

[0027] Optionally, in some embodiments of the present application, before performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the medicinal materials in the sample, the method also includes performing scattering elimination, background subtraction and smoothing denoising on the three-dimensional fluorescence spectrum of the solution corresponding to the medicinal materials in the sample.

[0028] Optionally, in some embodiments of the present application, before collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, the method further includes adding a fluorescent sensitizer compatible with the component to be detected to the solution corresponding to the Chinese medicinal material to be detected.

[0029] In a second aspect, the present application provides a Chinese medicinal material origin tracing device, the Chinese medicinal material origin tracing device comprising:

[0030] A collection module configured to collect a three-dimensional fluorescence spectrum of a solution corresponding to the Chinese medicinal material to be detected;

[0031] A factor decomposition module, configured to perform high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, so as to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected;

[0032] The origin determination module is configured to input the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected into a pre-trained random forest model, and output the origin of the Chinese medicinal material to be detected.

[0033] Optionally, the origin determination module in some embodiments of the present application is further configured to collect three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in samples of different origins, and establish a mapping relationship between the origins and the three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in the samples;

[0034] Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample;

[0035] The random forest model is trained based on the mapping relationship and the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample.

[0036] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the method for tracing the origin of Chinese medicinal materials as described in any one of the first aspects.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for tracing the origin of Chinese medicinal materials as described in any one of the first aspects.

[0038] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0039] The embodiments of the present application provide a method, device, electronic device and storage medium for tracing the origin of Chinese medicinal materials. The method completely describes all the fluorescence information of the mixed system by collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials to be detected, and performs high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials to be detected to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal materials to be detected. That is, the "mathematical separation" method is used to replace or enhance the "chemical and physical separation", and then the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal materials to be detected is input into a pre-trained random forest model, so that the origin of the Chinese medicinal materials to be detected can be output quickly and accurately with high sensitivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of a method for tracing the origin of Chinese medicinal materials provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S1 region provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S2 provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S3 provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S4 provided in an embodiment of the present application;

[0046] Figure 6 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S5 provided in an embodiment of the present application;

[0047] Figure 7A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S6 provided in an example of the present application;

[0048] Figure 8 A schematic diagram of a three-dimensional fluorescence spectrum of red peony root from S7 provided in an embodiment of the present application;

[0049] Fig. 9 A schematic diagram of a three-dimensional fluorescence spectrum before treatment provided in an embodiment of the present application;

[0050] Fig.10 A schematic diagram of a processed three-dimensional fluorescence spectrum provided in an embodiment of the present application;

[0051] Fig.11 A confusion matrix diagram of the classification results of red peony root corresponding to a random forest model provided in an embodiment of the present application;

[0052] Fig.12 A confusion matrix diagram of the classification results of peach kernel raw medicinal material corresponding to a random forest model provided in an embodiment of the present application;

[0053] Fig.13 A confusion matrix diagram of classification results of tangerine peel raw medicinal material corresponding to a random forest model provided in an embodiment of the present application;

[0054] Fig.14 This is a structural block diagram of a Chinese medicinal material origin tracing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0057] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. Figures 1 to 14 The method, device, electronic device and storage medium for tracing the origin of Chinese medicinal materials provided in the embodiments of the present application are described in detail.

[0058] Please refer to Figure 1 , which is a flow chart of a method for tracing the origin of Chinese medicinal materials provided in an embodiment of the present application, and the method for tracing the origin of Chinese medicinal materials specifically comprises the following steps:

[0059] S101, collecting a three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected.

[0060] It should be noted that Chinese herbal medicines contain a variety of endogenous fluorescent components such as flavonoids, coumarins, alkaloids, terpenoid quinones and organic acids, which can provide a basis for three-dimensional fluorescence identification of origin. However, the fluorescence of some endogenous substances in Chinese herbal medicines is weak, making it impossible to directly use three-dimensional fluorescence technology for detection. Therefore, before collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese herbal medicine to be detected, the embodiment of the present application can also add a fluorescent sensitizer compatible with the component to be detected to the solution corresponding to the Chinese herbal medicine to be detected, that is, after the fluorescent molecules are complexed or reacted with the target analytical substance, the corresponding fluorescent signal changes, thereby achieving the purpose of enhancing fluorescence. For example, an amphiphilic surfactant is added, and when the concentration of the surfactant reaches the critical micelle concentration, it will dynamically associate to form micelles, and the luminescent molecules are bound inside the micelles. This binding reduces the free collision between the luminescent molecules and molecules such as solvent molecules and other solute molecules, thereby reducing the possibility of collision quenching, thereby achieving enhanced stability and sensitization.

[0061] In addition, the viscosity of micellar solutions is usually higher than that of ordinary solutions, and high viscosity means that the movement between molecules becomes more difficult, which makes it more difficult for oxygen molecules (one of the factors that may cause luminescence quenching) to approach the luminescent molecules, reducing the quenching effect of oxygen on the luminescent molecules. For example, cyclodextrin, as a type of cyclic oligosaccharide, has a unique cavity structure and a hydrophilic outer surface. Therefore, it can interact with molecules with fluorescent groups to form a host-guest inclusion complex, thereby increasing the emission rate constant, reducing the freedom of molecular movement, avoiding deactivation collisions, maintaining a suitable microenvironment, and protecting the excited state from contact with large-volume water molecules and quenchers.

[0062] S102, performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected.

[0063] S103, inputting the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected into the pre-trained random forest model, and outputting the origin of the Chinese medicinal material to be detected.

[0064] Exemplarily, when training the random forest model, the embodiment of the present application first collects the three-dimensional fluorescence spectra of the solutions corresponding to the Chinese medicinal materials in the samples of different origins, and establishes the mapping relationship between the three-dimensional fluorescence spectra of the solutions corresponding to the Chinese medicinal materials in the origin and the sample, for example, a certain amount of sample Chinese medicinal materials is weighed and placed in a 25mL volumetric flask, methanol (or pure water) is added, and the volume is constant and ultrasonic centrifuged as a mother liquor, and then a certain amount of mother liquor is transferred to dilute the solution into different concentrations, and the most suitable detection concentration of the sample is selected according to the actual detection spectrum for detection, and each sample is measured twice to ensure the quality and stability of the data, and then the appropriate excitation wavelength range, emission wavelength range and bandwidth are selected according to the sample to be measured, reducing the sample measurement and data processing overhead. Among them, for the sample Chinese medicinal materials with weak fluorescence, gold nanoclusters (AuNCs) fluorescent probes can be used to enhance fluorescence. It should be noted that the process of collecting the three-dimensional fluorescence spectra of the solution corresponding to the Chinese medicinal materials to be detected and factoring the three-dimensional fluorescence spectrum data in the embodiment of the present application is similar to the process of collecting the three-dimensional fluorescence spectra of the solution corresponding to the sample Chinese medicinal materials and factoring the three-dimensional fluorescence spectrum data.

[0065] Secondly, ②, perform high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal materials in the sample. Optionally, before performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials in the sample, the embodiment of the present application can also perform scattering elimination, background subtraction and smoothing denoising on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials in the sample, for example, importing the three-dimensional fluorescence spectrum data into the ModelLab Specman 3D software for background subtraction, and using the segmented Spline spline interpolation method to eliminate Rayleigh scattering and Raman scattering, and constructing a smooth curve to fit the data points, thereby effectively eliminating the influence of the scattering signal on the fluorescence spectrum. Furthermore, the three-dimensional fluorescence spectrum X(I×J×K) of the solution corresponding to the Chinese medicinal materials in the sample includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E, and each element x in X(I×J×K) ijk for:

[0066]

[0067] In formula (1), x ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j, n), c in the relative emission spectrum matrix B(J×N)kn Represents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K); N represents the number of components, and its value can be determined according to the approximate number of fluorescent components in the Chinese medicinal materials, or by entering different numbers of components to view the component analysis results and determine the specific number of components based on the results.

[0068] When performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the sample Chinese medicinal material, the iterative expression of the relative excitation spectrum matrix A is:

[0069] a (i) T =((C + X i.. B). / (B T B)+(B + X i.. C). / (C T C)) (2)

[0070] The iterative expression of the relative emission spectrum matrix B is:

[0071] b (j) T =(A + X .j. C). / (C T C)+(C + X .j. A). / (A T A)) (3)

[0072] The iterative expression of the relative concentration matrix C is:

[0073] c (k) T =(B + X ..k A). / (A T A)+(A + X ..k B). / (B T B)) (4)

[0074] The three-dimensional trilinear matrix is ​​represented as:

[0075] X i.. =Bdiag(a (i) )C T +E i..

[0076] X .j. =Cdiag(b (j) )A T +E .j.

[0077] X ..k =Adiag(c (k) )B T +E ..k (5)

[0078] In formula (2) to formula (5), a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; X i.. represents the i-th horizontal plane matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X .j. represents the j-th side matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X ..k The kth positive matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C. It should be noted that, compared with the parallel factorization method (PARAFAC), the high-order cyclic factorization method of the embodiment of the present application introduces tensor singular value decomposition (tensor SVD) to perform high-order cyclic decomposition on trilinear data, so that a (i) 、b (j) and c (k) It can be obtained by cyclically minimizing the loss function. Generally, after a finite number of cycles (usually less than 10 times), the matrix decomposition result with residuals satisfying the conditions can be obtained. At the same time, it also avoids the emergence of imaginary solutions and sensitivity to the number of factors.

[0079] Finally, ③, based on the mapping relationship and the three-dimensional fluorescence spectrum of each component in the solution corresponding to the sample Chinese medicinal materials, the random forest model is trained. It should be noted that the random forest model in the embodiment of the present application has a high prediction accuracy and can handle complex nonlinear relationships; it can run effectively on large data sets and perform well when processing large-scale data; by introducing randomness, it can effectively prevent overfitting and improve the generalization ability of the model; it has good robustness to noisy data and can maintain good performance when the data noise is large; and it can handle high-dimensional data without dimensionality reduction processing.

[0080] First, by calculating the Gini index of each feature, we determine which feature works best in segmenting the data, and thus select the optimal root node. The lower the Gini index, the purer the data set and the better the classification effect.

[0081] Furthermore, the mathematical representation of the Gini index is:

[0082]

[0083] In formula (6), G inl represents the Gini index, m represents the number of samples, and p represents the feature state probability.

[0084] Then, the total Gini index after node segmentation is calculated by weighted Gini index, namely:

[0085]

[0086] In formula (7), G inl总 represents the total Gini index, m1 and m2 represent the states after separation, G inl1 represents the Gini index corresponding to m1, G inl2 Represents the Gini index corresponding to m2.

[0087] Using the same method, try to calculate the Gini index of all possible splits and select the feature with the lowest Gini index as the root node. The lowest Gini index means the lowest impurity.

[0088] The specific steps are as follows: 1) L represents the number of training cases (samples), Q represents the number of features; 2) Input the number of features q, which is used to determine the decision result of a node on the decision tree, where q should be much smaller than Q; 3) Sample L times from the L training cases (samples) in a way of replacement sampling to form a training set (i.e. bootstrap sampling), and use the unsampled cases (samples) for prediction and evaluate its error; 4) For each node, randomly select q features, and the decision of each node on the decision tree is determined based on these features, and calculate the best splitting method based on these q features; 5) Each tree will grow completely without pruning, which may be adopted after building a normal tree classifier. The above steps will achieve the best classification effect.

[0089] The traceability effect of the random forest model of the embodiment of the present application is verified below. For example (I) weigh 1.0g of red peony root powder from different origins, add 10mL of 50% ethanol solution by volume, let it stand after shaking, repeat the operation several times, extract for 2.5h, ultrasonically extract for 20min, temperature 30°C, ultrasonic power 300W, take 100μL of solution and dilute to 10mL volumetric flask with water, the sample extract concentration is 1mg / mL, and store in a sealed container at 4°C for later use. According to the actual detection spectrum, select the most suitable detection concentration for the sample for detection, place the solution in a cuvette, and measure it using a fluorescence spectrometer. Among them, the excitation wavelength λ ex 200nm-375nm, bandwidth is 5nm; emission wavelength λ em The wavelength is 270nm-550nm, and the bandwidth is 5nm. The red peony samples were collected in May 2021. A total of 42 red peony samples were collected, 6 samples from each province. The detailed information of the red peony samples is shown in Table 1. In order to eliminate the differences caused by the harvesting time, the harvesting interval is strictly controlled to no more than 5 days. The three-dimensional fluorescence spectra of red peony from each origin are shown in Figures 2 to 8 shown.

[0090] Table 1 Detailed information of red peony root samples

[0091] Origin Medicinal Plants longitude latitude Sample No. S1 Peony 131.12 44.06 hlj1-hlj6 S2 Peony 124.18 51.98 sl1-sl6 S3 Peony 124.63 49.75 NMG1-NMG6 S4 Peony 119.83 40.82 ln1-ln6 S5 Peony 116.71 39.52 hb1-hb6 S6 Paeonia lactiflora 104.46 34.84 gs1-gs6 S7 Paeonia lactiflora 101.12 30.98 sc1-sc6

[0092] Furthermore, the three-dimensional fluorescence spectrum of red peony root from each origin was subjected to scattering elimination and background subtraction, wherein the Rayleigh scattering bandwidth was 35nm, the Raman scattering bandwidth was 5nm, and the secondary Rayleigh scattering bandwidth was 5nm. Rayleigh scattering was eliminated by the segmented Spline interpolation method. The three-dimensional fluorescence spectrum before processing is as follows: Fig. 9 As shown, the processed three-dimensional fluorescence spectrum is as follows Fig.10 As shown in the figure, we can see that the spectrum result with extremely clean background is obtained. The random forest model is used to predict different groups of red peony root raw materials. The results are as follows Fig.11 The model shown has a classification accuracy of 97.62%.

[0093] For example (II), weigh 0.5g of peach kernel samples from different origins, dissolve them in methanol and place them in a 25mL volumetric flask, add 50uL of fluorescent molecular probe and dilute to volume with methanol solution (chromatographic grade), sonicate and centrifuge an appropriate amount as the mother liquor, and then dilute the mother liquor with methanol to a 10mg / mL solution for testing. Select the most suitable detection concentration for the sample according to the actual detection spectrum, place the solution in a cuvette, and measure it using a fluorescence spectrometer. Among them, the excitation wavelength λ ex 200nm-400nm, bandwidth is 5nm; emission wavelength λ emThe wavelength is 250nm-730nm, the bandwidth is 5nm; the photomultiplier diode voltage is 600V, and the sample details are shown in Table 2. The random forest model is used to predict the different groups of peach kernel raw materials. The results are as follows Fig.12 The model shown has 100% classification accuracy.

[0094] Table 2 Detailed information of peach kernel samples

[0095] Origin Sample No. S8 hbt1-hbt54 S9 gst55-gst57 S10 sdt58-sdt69

[0096] For example (III), 0.25 g of dried tangerine peel samples from different origins were weighed, dissolved in methanol and placed in a 25 mL volumetric flask, and methanol solution (chromatographically pure) was added to the fixed volume, ultrasonicated and centrifuged as a mother liquor, and then the mother liquor was diluted with methanol to a 1 mg / mL solution for testing. The most suitable detection concentration of the sample was selected according to the actual detection spectrum, the solution was placed in a cuvette, and measured using a fluorescence spectrometer. Among them, the excitation wavelength λ ex 200nm-550nm, bandwidth is 5nm; emission wavelength λ em The wavelength is 200nm-600nm, the bandwidth is 5nm; the photomultiplier diode voltage is 600V, and the sample details are shown in Table 3. The random forest model is used to predict the different groups of tangerine peel raw materials. The results are as follows Fig.13 The model shown has 100% classification accuracy.

[0097] Table 3 Detailed information of dried tangerine peel samples

[0098] Origin Sample No. S11 gdc1-gdc22 S12 zjc1-zjc28 S13 gxc1-gxc4 S14 hbc1-hbc4

[0099] The method for tracing the origin of Chinese medicinal materials provided in the embodiment of the present application completely describes all the fluorescence information of the mixed system by collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, and performs high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected, that is, using "mathematical separation" to replace or enhance "chemical and physical separation", and then inputting the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected into a pre-trained random forest model, so as to quickly and accurately output the origin of the Chinese medicinal material to be detected with high sensitivity.

[0100] Based on the above embodiments, the present application provides a Chinese herbal medicine origin tracing device. The Chinese herbal medicine origin tracing device 100 can be applied to Figures 1 to 13 In the method for tracing the origin of Chinese medicinal materials in the corresponding embodiment. Please refer to Fig.14 The Chinese herbal medicine origin tracing device 100 comprises:

[0101] The acquisition module 101 is configured to acquire a three-dimensional fluorescence spectrum of a solution corresponding to the Chinese medicinal material to be detected;

[0102] The factor decomposition module 102 is configured to perform high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, so as to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected;

[0103] The origin determination module 103 is configured to input the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected into a pre-trained random forest model, and output the origin of the Chinese medicinal material to be detected.

[0104] Optionally, in some embodiments of the present application, the origin determination module 103 is further configured to collect three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in samples of different origins, and establish a mapping relationship between the origin and the three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in the samples;

[0105] Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample;

[0106] Based on the mapping relationship and the three-dimensional fluorescence spectra of each component in the solution corresponding to the Chinese medicinal materials in the sample, a random forest model was trained.

[0107] Optionally, in some embodiments of the present application, the three-dimensional fluorescence spectrum X(I×J×K) of the solution corresponding to the sample Chinese medicinal material includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E, and each element x in X(I×J×K) ijk for:

[0108]

[0109] Among them, x ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j, n), c in the relative emission spectrum matrix B(J×N) kn Represents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

[0110] Optionally, in some embodiments of the present application, when the factor decomposition module 102 performs high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the sample Chinese medicinal material, the iterative expression of the relative excitation spectrum matrix A is:

[0111] a (i) T =((C + X i.. B). / (B T B)+(B + X i.. C). / (C T C));

[0112] The iterative expression of the relative emission spectrum matrix B is:

[0113] b (j) T =(A + X .j. C). / (C T C)+(C + X .j. A). / (A T A));

[0114] The iterative expression of the relative concentration matrix C is:

[0115] c (k) T =(B + X ..k A). / (A T A)+(A + X ..k B). / (B T B));

[0116] The three-dimensional trilinear matrix is ​​represented as:

[0117] X i.. =Bdiag(a (i) )C T +E i.. ;

[0118] X .j. =Cdiag(b (j) )A T +E .j. ;

[0119] X ..k =Adiag(c (k) )B T +E ..k ;

[0120] Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b(j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; X i.. represents the i-th horizontal plane matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X .j. represents the j-th side matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X ..k The kth positive matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C.

[0121] Optionally, in some embodiments of the present application, the factor decomposition module 102 is further configured to perform scattering elimination, background subtraction and smoothing denoising on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials in the sample before performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal materials in the sample.

[0122] Optionally, in some embodiments of the present application, before collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, the acquisition module 101 is also configured to add a fluorescent sensitizer compatible with the component to be detected to the solution corresponding to the Chinese medicinal material to be detected.

[0123] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0124] The Chinese medicinal material origin tracing device provided in the embodiment of the present application completely describes all the fluorescence information of the mixed system by collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, and performs high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, so as to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected, that is, the "mathematical separation" method is used to replace or enhance the "chemical and physical separation", and then the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected is input into a pre-trained random forest model, so as to quickly and accurately output the origin of the Chinese medicinal material to be detected, with high sensitivity.

[0125] Based on the above embodiments, the embodiments of the present application provide an electronic device. The electronic device may include a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, program, code set or instruction set is loaded and executed by the processor to implement Figures 1 to 13 The steps of the method for tracing the origin of Chinese medicinal materials in the corresponding embodiment.

[0126] As another aspect, the present invention provides a computer-readable storage medium for storing program code for executing the aforementioned Figures 1 to 13 Any implementation method of the method for tracing the origin of Chinese medicinal materials in the corresponding embodiment.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0129] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0130] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method for tracing the origin of medicinal materials in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0131] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for tracing the origin of Chinese medicinal materials, characterized in that: The method for tracing the origin of Chinese medicinal materials includes: Collecting a three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be tested; Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected; The three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected is input into a pre-trained random forest model, and the origin of the Chinese medicinal material to be detected is output.

2. The method for tracing the origin of Chinese medicinal materials according to claim 1, characterized in that: The random forest model is trained by the following steps: Collecting three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in samples from different origins, and establishing a mapping relationship between the origins and the three-dimensional fluorescence spectra of solutions corresponding to the Chinese medicinal materials in the samples; Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample; The random forest model is trained based on the mapping relationship and the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample.

3. The method for tracing the origin of Chinese medicinal materials according to claim 2, characterized in that: The three-dimensional fluorescence spectrum X(I×J×K) of the solution corresponding to the Chinese medicinal material in the sample includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E. Each element x in X(I×J×K) ijk for: Among them, x ijk represents the fluorescence intensity of the kth sample at the excitation wavelength i and the emission wavelength j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i,n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j,n) in the relative emission spectrum matrix B(J×N), c kn Represents the element (k,n) in the relative concentration matrix C(K×N), e ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

4. The method for tracing the origin of Chinese medicinal materials according to claim 2, characterized in that: When performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample, the iterative expression of the relative excitation spectrum matrix A is: a (i) T =((C + X i.. B). / (B T B)+(B + X i.. C). / (C T C)); The iterative expression of the relative emission spectrum matrix B is: b (j) T =(A + X .j. C). / (C T C)+(C + X .j. A). / (A T A)); The iterative expression of the relative concentration matrix C is: c (k) T =(B + X ..k A). / (A T A)+(A + X ..k B). / (B T B)); The three-dimensional trilinear matrix is ​​represented as: X i.. =Bdiag(a (i) )C T +E i.. ; X .j. =Cdiag(b (j) )A T +E .j. ; X ..k =Adiag(c (k) )B T +E ..k ; Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; X i.. represents the i-th horizontal plane matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X .j. represents the j-th side matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample, X ..k The kth positive matrix of the three-dimensional fluorescence spectrum X of the solution corresponding to the medicinal material in the sample; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C.

5. The method for tracing the origin of Chinese medicinal materials according to claim 4, characterized in that: Before performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the medicinal material in the sample, the method also includes performing scattering elimination, background subtraction and smoothing denoising on the three-dimensional fluorescence spectrum of the solution corresponding to the medicinal material in the sample.

6. The method for tracing the origin of Chinese medicinal materials according to any one of claims 1 to 5, characterized in that: Before collecting the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, the method further includes adding a fluorescence sensitizer compatible with the component to be detected to the solution corresponding to the Chinese medicinal material to be detected.

7. A Chinese herbal medicine origin tracing device, characterized in that: The Chinese medicinal material origin tracing device comprises: A collection module configured to collect a three-dimensional fluorescence spectrum of a solution corresponding to the Chinese medicinal material to be detected; A factor decomposition module, configured to perform high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material to be detected, so as to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected; The origin determination module is configured to input the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material to be detected into a pre-trained random forest model, and output the origin of the Chinese medicinal material to be detected.

8. The Chinese herbal medicine origin tracing device according to claim 7, characterized in that: The origin determination module is also configured to collect three-dimensional fluorescence spectra of solutions corresponding to Chinese medicinal materials in samples of different origins, and establish a mapping relationship between the origins and the three-dimensional fluorescence spectra of solutions corresponding to the Chinese medicinal materials in the samples; Performing high-order cyclic factor decomposition on the three-dimensional fluorescence spectrum of the solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample; The random forest model is trained based on the mapping relationship and the three-dimensional fluorescence spectrum of each component in the solution corresponding to the Chinese medicinal material in the sample.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the method for tracing the origin of traditional Chinese medicine as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for tracing the origin of traditional Chinese medicine described in any one of claims 1 to 6.

Images