A method, system, device, medium and product for identifying the origin of Huangshan Maofeng tea
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA NAT INST OF STANDARDIZATION
- Filing Date
- 2026-03-18
- Publication Date
- 2026-06-05
AI Technical Summary
Existing technologies are insufficient to accurately distinguish Huangshan Maofeng tea from other green teas from different regions, leading to serious problems with counterfeit and substandard teas. Current traceability technologies have high false positive rates and limited detection dimensions, failing to meet the standardized protection requirements for geographical indication teas.
By combining metabolomics detection and near-infrared spectroscopy, core differential metabolites and characteristic spectral bands were screened out by collecting full-spectrum metabolomics data and near-infrared spectral data of tea samples, and an origin discrimination model was constructed to achieve accurate identification of Huangshan Maofeng tea.
It improves the accuracy and reliability of identification, has a high degree of mechanistic interpretability and industrial application potential, and is suitable for precise traceability in laboratories and rapid screening in the industry, meeting the standardized protection needs of geographical indication tea.
Smart Images
Figure CN122150178A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of tea quality testing and geographical origin tracing, and in particular to a method, system, equipment, medium and product for identifying the origin of Huangshan Maofeng tea. Background Technology
[0002] Huangshan Maofeng belongs to the category of baked green tea. Its unique flavor and quality have given it significant market competitiveness and high economic value. However, due to the common processing techniques of baked green tea, Huangshan Maofeng differs only slightly in appearance from baked green teas from other regions, making it difficult to accurately distinguish using conventional sensory methods. Furthermore, some baked green teas from non-core production areas are illegally sold as Huangshan Maofeng. This not only directly infringes upon consumers' legitimate rights but also severely damages the geographical indication brand reputation of Huangshan Maofeng, disrupting the normal market order and healthy development ecosystem of the tea industry.
[0003] Currently, existing single traceability technologies generally suffer from high false positive rates and limited detection dimensions, making it difficult to balance identification accuracy, mechanism interpretability, and industrial application adaptability, thus failing to meet the actual needs of standardized protection of geographical indication tea. Summary of the Invention
[0004] The purpose of this application is to provide a method, system, equipment, medium, and product for identifying the origin of Huangshan Maofeng tea. This method can accurately distinguish Huangshan Maofeng tea from green tea from non-core production areas, thereby curbing counterfeiting and substandard products from a technical perspective. Furthermore, it provides reliable technical support and theoretical basis for the protection of the Huangshan Maofeng geographical indication brand, source control of tea, precise quality control, and the healthy and sustainable development of the industry. To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for identifying the origin of Huangshan Maofeng tea, including: Samples of Huangshan Maofeng tea from known production areas were collected, and extract samples and tablet samples were prepared respectively. The extract sample was subjected to metabolomics analysis to obtain full-spectrum metabolomics data of the sample; Near-infrared spectral data of the compressed sample were collected, and the characteristic spectral bands of the sample were screened out after preprocessing the near-infrared spectral data. The full spectrum data of the sample metabolomics and the characteristic spectral bands of the sample are fused to obtain fused data. A country of origin discrimination model is constructed based on the fused data; Obtain the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands of the sample to be tested; The full spectrum data of the metabolomics to be tested and the characteristic spectral bands to be tested are input into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
[0005] Secondly, this application provides a system for identifying the origin of Huangshan Maofeng tea, comprising: The sample preparation module is used to collect Huangshan Maofeng tea samples from known origins and prepare extract samples and tablet samples respectively. The sample metabolomics full-spectrum data acquisition module is used to perform metabolomics detection on the extract sample to obtain sample metabolomics full-spectrum data; The sample characteristic spectral band screening module is used to collect the near-infrared spectral data of the tablet sample, and screen out the sample characteristic spectral bands after preprocessing the near-infrared spectral data. The data fusion module is used to fuse the full spectrum data of the sample metabolomics with the characteristic spectral bands of the sample to obtain fused data; The model building module is used to build an origin discrimination model based on the fused data; The test information acquisition module is used to acquire the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands to be tested. The Zen-based discrimination module is used to input the full spectrum data of the metabolomics to be tested and the spectral bands of the characteristic to be tested into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
[0006] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for identifying the origin of Huangshan Maofeng tea.
[0007] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for identifying the origin of Huangshan Maofeng tea.
[0008] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for identifying the origin of Huangshan Maofeng tea.
[0009] According to the specific embodiments provided in this application, this application has the following technical effects: 1. High accuracy and reliability in identification: By collecting full-spectrum metabolomics data and near-infrared spectral data of samples, core differential metabolites and characteristic spectral bands are screened out respectively, and the two are fused into multi-source data. This complementary strategy of combining "internal molecular fingerprint (metabolites)" and "external macroscopic spectrum (near-infrared spectrum)" breaks through the information limitations of single technical means. It can comprehensively characterize the origin characteristics of Huangshan Maofeng from two dimensions: microscopic chemical composition and macroscopic physical properties, thereby greatly improving the discrimination model's ability to distinguish similar-looking roasted green teas and ensuring the accuracy of the identification results.
[0010] 2. Clear and traceable mechanism: On the one hand, this application clarifies the specific material basis for the differences in origin by screening "core differential metabolites", which makes the identification results have a solid biochemical theoretical support and a high degree of mechanistic interpretability. On the other hand, it introduces "near-infrared spectroscopy" technology and utilizes its rapid and non-destructive characteristics to construct a discrimination model by combining fused data. This makes the method have the potential for industrial application to adapt to large-scale and rapid screening while maintaining high accuracy, thus meeting the actual needs of standardized protection of geographical indication tea.
[0011] 3. Wide adaptability to various scenarios: This application combines the advantages of accurate qualitative analysis in metabolomics detection with the rapid and non-destructive characteristics of near-infrared spectroscopy. It is suitable for both precise source tracing analysis in laboratories and rapid on-site screening in industries, covering different detection scenarios and enabling industrial application. Attached Figure Description
[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0013] Figure 1 A flowchart illustrating a method for identifying the origin of Huangshan Maofeng tea, provided as an embodiment of this application; Figure 2 The score plot shows the orthogonal partial least squares discriminant analysis model constructed based on full-spectrum metabolomics data. Figure 3 This is a distribution map of the core differential metabolite content between Huangshan Maofeng (HSMF) samples and non-Huangshan Maofeng (Non-HSMF) samples; Figure 4 A ranking chart of the importance projection values of the core differential metabolites between Huangshan Maofeng samples and non-Huangshan Maofeng samples; Figure 5The scores are plots of the orthogonal partial least squares discriminant analysis model based on spectral data; where (a) is the score plot of the orthogonal partial least squares discriminant analysis model based on near-infrared spectroscopy, and (b) is the score plot of the orthogonal partial least squares discriminant analysis model based on Raman spectroscopy. Figure 6 The confusion matrix diagram for classifying Huangshan Maofeng and non-Huangshan Maofeng samples using an orthogonal partial least squares discriminant analysis model; Figure 7 The image shows the feature spectral bands extracted using the feature selection algorithm; where (a) is the feature spectral band image obtained by the competitive adaptive reweighted sampling method, and (b) is the feature spectral band image obtained by the random forest algorithm. Figure 8 This is a score map of the origin discrimination model built based on fused data; Figure 9 The figure shows the correlation analysis results between differential metabolites and characteristic spectral bands. Detailed Implementation
[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0015] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0016] In one exemplary embodiment, such as Figure 1 As shown, a method for identifying the origin of Huangshan Maofeng tea is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is described using a server as an example, and includes the following steps S1 to S7.
[0017] S1: Collect Huangshan Maofeng tea samples from known origins and prepare extract samples and tablet samples respectively.
[0018] S2: Perform metabolomics detection on the extracted sample to obtain full-spectrum metabolomics data of the sample.
[0019] S3: Collect the near-infrared spectral data of the tablet sample, and screen out the characteristic spectral bands of the sample after preprocessing the near-infrared spectral data.
[0020] S4: The full spectrum data of the sample metabolomics is fused with the characteristic spectral bands of the sample to obtain fused data.
[0021] S5: Construct an origin discrimination model based on the fused data.
[0022] S6: Obtain the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands to be tested.
[0023] S7: Input the full spectrum data of the metabolomics to be tested and the characteristic spectral bands to be tested into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
[0024] By implementing steps S1 to S7 above, this application combines the advantages of rapid and non-destructive near-infrared spectroscopy with the precise qualitative analysis of chemical fingerprints (full spectrum data of metabolomics), clearly identifying the core differential metabolites and characteristic spectral bands of Huangshan Maofeng. The established origin discrimination model has a high recognition rate for Huangshan Maofeng, achieving non-destructive origin screening that is accurate, rapid, and interpretable.
[0025] In a specific embodiment, step S1 specifically includes: (1) Preparation of extract sample.
[0026] Accurately weigh 0.2g of tea powder (Huangshan Maofeng) into a 15mL centrifuge tube, add 10mL of 70% methanol solution containing 0.26μg / mL theophylline (as internal standard) and 0.5mg / mL vitamin C (as antioxidant), shake well, and then extract in a 70℃ constant temperature water bath for 30min. After extraction, centrifuge at 35000r / min for 10min, take 1mL of supernatant, filter through a 0.22μm organic microporous membrane, collect the filtrate, transfer it to a brown sample bottle, seal it, and store it at 4℃ for later use.
[0027] (2) Preparation of tablet samples.
[0028] Weigh 0.1g of tea powder (Huangshan Maofeng) and place it into a special mold. Press the sample using a HY-12 infrared tablet press, apply a pressure of 25MPa, and maintain the pressure for 1 minute in each of the four directions to press it into a round tablet with uniform thickness and no cracks. Prepare 3 tablets in parallel for each sample. After pressing, seal immediately and store in a -20℃ refrigerator to avoid moisture absorption affecting the accuracy of spectral detection.
[0029] Strict control of the preparation process ensures sample consistency and stability, effectively avoids component oxidation and deterioration and detection interference, and provides a standardized sample basis for subsequent detection in each stage.
[0030] In one specific embodiment, step S2 specifically includes: In this embodiment, an ultra-high performance liquid chromatography-tandem triple quadrupole mass spectrometer (UHPLC-MS / MS) was used to conduct non-targeted metabolomics detection and accurately obtain full-spectrum data of tea metabolomics.
[0031] The UHPLC-MS / MS detection conditions are as follows: Chromatographic conditions: Hypersil GOLD™ C18 column (175 Å, 3 μm, 2.1 × 100 mm); mobile phase A was 0.1% formic acid aqueous solution, and mobile phase B was methanol solution; linear gradient elution program: 0-2 min hold 1% B, 2-4 min increase from 1% B to 15% B, 4-12 min increase from 15% B to 32% B, 12-18 min increase from 32% B to 95% B, 18-23 min hold 95% B, 23-24 min decrease from 95% B to 1% B, 24-25 min hold 1% B; flow rate 0.3 mL / min, column temperature 40 °C, injection volume 3 μL.
[0032] Mass spectrometry conditions: Selective reaction monitoring (SRM) scan mode was used; targeted quantitative analysis was carried out using a compound SRM conversion table established based on LC-HRMS high-resolution mass spectrometry data; metabolite quantification and manual verification were performed using TraceFinder 4.1 software.
[0033] In a specific embodiment, step S3 specifically includes: preprocessing the sample near-infrared spectral data using an optimal preprocessing method; and extracting sample feature spectral bands from the optimally preprocessed sample near-infrared spectral data using a feature selection algorithm.
[0034] Before step S3, the method further includes: synchronously acquiring the sample Raman spectral data of the compressed sample; performing mean preprocessing on the sample near-infrared spectral data and the sample Raman spectral data respectively; constructing OPLS-DA models based on the preprocessed sample near-infrared spectral data and the preprocessed sample Raman spectral data respectively, and comparing the goodness of fit and predictive ability of the OPLS-DA models; determining the spectral data type corresponding to the OPLS-DA model with better predictive ability as sample near-infrared spectral data.
[0035] (1) Near-infrared spectral acquisition.
[0036] Near-infrared spectral data were acquired using an Antaris II near-infrared analyzer. The instrument was warmed up for 20-30 minutes after power-on to ensure stable performance. The preset detection procedure was then invoked using the TQ-Analyzer software. The spectral scanning parameters were set to a scanning range of 10000~4000 cm⁻¹. -1(Corresponding wavelength range 1000~2500nm), resolution 8nm, 16 scans per scan; 33 uniformly distributed measurement points are selected for each sample, and each point is scanned 3 times. A total of 99 near-infrared spectral data are obtained for each sample, and the average value is taken as the final spectral data of the sample.
[0037] (2) Raman spectroscopy acquisition.
[0038] A Spider 2000 microconfocal Raman spectrometer was used with the following parameters: excitation wavelength 785 nm, power 2 mW, integration time 50 ms. The same measurement point selection strategy as that used for near-infrared spectroscopy was adopted, and 99 effective Raman spectral data points (each containing 2048 data points) were obtained for each sample.
[0039] (3) Basic modeling.
[0040] For each sample, 99 near-infrared spectra and 99 Raman spectra were preprocessed by mean normalization to improve data stability. Based on the preprocessed spectral data, OPLS-DA models were constructed, such as... Figure 5 As shown in (a) and (b), the OPLS-DA model constructed based on near-infrared spectral data has significantly better fitting and predictive ability than the OPLS-DA model constructed based on Raman spectral data. Therefore, near-infrared spectral data was selected for subsequent modeling and analysis.
[0041] (4) Feature filtering.
[0042] The near-infrared spectral data of 57 samples were randomly divided into a training set (n=38) and a test set (n=19) at a ratio of 2:1. Three preprocessing methods were used for comparative analysis: Standard Normal Variable Transform (SNV), Savitzky-Golay Smoothing (SG), and SG-SNV combined preprocessing. A machine learning classification model was built based on the preprocessed near-infrared spectral data, and the classification accuracy of the model was evaluated. The results are shown in Table 1. Table 1
[0043] The results show that all preprocessing methods achieved 100% classification accuracy on the training set; on the test set, the accuracy of the model with SG preprocessing combined with SG-SNV preprocessing decreased to 84.21%, while the models without preprocessing and those with SNV preprocessing alone achieved the highest test accuracy of 89.47%. Therefore, SNV was selected as the optimal preprocessing method. Visualization of the confusion matrix using the SNV preprocessing results shows that 88.89% of the Huangshan Maofeng samples were accurately classified (e.g., ...). Figure 6 As shown in the figure, only a few Huangshan Maofeng samples were misclassified as non-Huangshan Maofeng.
[0044] Feature spectral band selection: Feature spectral selection of near-infrared spectral data is performed using Competitive Adaptive Reweighted Sampling (CARS) and Random Forest (RF) algorithms, such as... Figure 7 As shown in (a) and (b) of the figure, core features are provided to support subsequent multi-dimensional data fusion.
[0045] In a specific embodiment, step S4 specifically includes: normalizing the full spectrum data of sample metabolomics and the characteristic spectral bands of the sample; and splicing or weighting the normalized full spectrum data of sample metabolomics and the normalized characteristic spectral bands of the sample.
[0046] In one specific embodiment, step S5 specifically includes: The full-spectrum metabolomics data of the samples obtained in step S2 is spliced or weighted and fused with the characteristic spectral bands of the samples selected in step S3. Data normalization is used to eliminate dimensional differences. Based on the fused multidimensional data, an OPLS-DA model is constructed in the software SIMCA as an origin discrimination model. Figure 8 As shown, compared to a single spectral model or chemical fingerprint model, the accuracy and stability of origin identification are significantly improved (R0). 2 Y=0.994, Q 2 =0.775), which can effectively avoid detection bias from a single data source.
[0047] The method for identifying the origin of Huangshan Maofeng tea provided in this embodiment further includes: screening out the core differential metabolites of the sample from the full spectrum of metabolomics data of the sample; and performing correlation analysis on the core differential metabolites of the sample and the characteristic spectral bands of the sample.
[0048] In this embodiment, an orthogonal partial least squares discriminant analysis (OPLS-DA) model is constructed using the full spectrum data of the sample metabolomics as input variables. Based on this model, the variable importance projection value (VIP) and significance test (P) value of each metabolite in the full spectrum data of metabolomics are determined. The core differential metabolites are identified by using VIP>1 and P<0.05 as screening criteria, forming a specific chemical fingerprint discrimination basis.
[0049] Specifically, a total of 214 metabolites were identified, including 11 catechins, 31 amino acids, 4 alkaloids, 23 flavonoids, 31 organic acids, and 114 other substances. An OPLS-DA model was constructed based on the above full-spectrum metabolomics data. Figure 2 As shown, the parameters R of the OPLS-DA model are... 2 Y=0.905, Q 2 =0.734, R 2 Y represents the explanatory power of the model's dependent variable, Q 2The model demonstrates predictive ability. It clearly separates Huangshan Maofeng samples from non-Huangshan Maofeng samples, with no overlap between the two groups. Using VIP>1 and P<0.05 as screening criteria, 15 core differentially expressed metabolites were identified, mainly including alkaloids (caffeine, theobromine), catechins (EGC, EGCG, CG, EC, ECG, GC), and flavonol glycosides (quercetin-3-rutin, kaempferol-3-O-galactoside). Heatmap analysis clearly divides 57 samples into two categories, consistent with the OPLS-DA model, clearly showing the systematic expression differences of differentially expressed metabolites in the two groups. Flavonol glycosides and catechin metabolites were relatively enriched in the HSMF samples. Figure 3 The distribution map of core differential metabolite content between Huangshan Maofeng samples and non-Huangshan Maofeng samples is shown, and the corresponding VIP value ranking results are as follows. Figure 4 As shown.
[0050] Pearson correlation analysis was performed on the selected characteristic spectral bands and core differentially expressed metabolites, such as... Figure 9 As shown, the results indicate: 7800–8200cm -1 With 9000–10000cm -1 The spectral signals in the specified intervals showed a significant positive correlation with flavonoid glycosides (correlation coefficients r = 0.46 and 0.47, respectively, P < 0.001); and a significant negative correlation with catechins (ECG: r = -0.33, -0.34; CG: r = -0.33, -0.34; EGCG: r = -0.35, -0.36) and caffeine (r = -0.37, -0.35) (P < 0.05). Based on the spectral-structure-component correlation, the identification mechanism is elucidated as follows: 7800–8200 cm -1 The 9000–10000 cm⁻¹ band (CH second harmonics) mainly corresponds to aromatic rings and aliphatic CH vibrations. In Huangshan Maofeng tea, flavonoid glycosides have densely packed aromatic rings and glycosyl groups; the superposition of these two elements enhances the signal in this band, resulting in a significant positive correlation with flavonoid glycoside content. Catechins, with their simple structure, have a weaker influence. -1 The OH second-order overtone band primarily reflects bound hydroxyl groups. Flavonoid glycosides are rich in phenolic and alcoholic hydroxyl groups, resulting in strong signals and a positive correlation. Ester-type catechins (such as EGCG and ECG) readily form strong intramolecular and intermolecular hydrogen bonds, leading to suppressed hydroxyl vibrations and weakened signals, thus exhibiting a negative correlation.
[0051] In summary, these two bands sensitively captured the differences in functional group abundance and hydrogen bond state in the metabolic characteristics of Huangshan Maofeng tea, which is characterized by "high flavonoid glycosides and high catechins," providing a mechanistic basis for the ability of near-infrared spectroscopy data to identify the place of origin.
[0052] Based on the same inventive concept, this application also provides a system for implementing the Huangshan Maofeng origin identification method described above. The solution provided by this system is similar to the solution described in the above method; therefore, the specific limitations of one or more Huangshan Maofeng origin identification system embodiments provided below can be found in the limitations of the Huangshan Maofeng origin identification method described above, and will not be repeated here.
[0053] In one exemplary embodiment, a system for identifying the origin of Huangshan Maofeng tea is provided, comprising the following modules.
[0054] The sample preparation module is used to collect Huangshan Maofeng tea samples from known origins and prepare extract samples and tablet samples respectively.
[0055] The sample metabolomics full-spectrum data acquisition module is used to perform metabolomics detection on the extracted sample to obtain sample metabolomics full-spectrum data.
[0056] The sample characteristic spectral band screening module is used to collect the near-infrared spectral data of the tablet sample, and screen out the sample characteristic spectral bands after preprocessing the near-infrared spectral data.
[0057] The data fusion module is used to fuse the full spectrum data of the sample metabolomics with the characteristic spectral bands of the sample to obtain fused data.
[0058] The model building module is used to build an origin discrimination model based on the fused data.
[0059] The test information acquisition module is used to acquire the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands to be tested.
[0060] The Zen-based discrimination module is used to input the full spectrum data of the metabolomics to be tested and the spectral bands of the characteristic to be tested into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
[0061] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the steps in the above-described method embodiments.
[0062] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0063] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0064] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0065] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0066] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0067] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.
[0068] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for identifying the origin of Huangshan Maofeng tea, characterized in that, include: Samples of Huangshan Maofeng tea from known production areas were collected, and extract samples and tablet samples were prepared respectively. The extract sample was subjected to metabolomics analysis to obtain full-spectrum metabolomics data of the sample; Near-infrared spectral data of the compressed sample were collected, and the characteristic spectral bands of the sample were screened out after preprocessing the near-infrared spectral data. The full spectrum data of the sample metabolomics and the characteristic spectral bands of the sample are fused to obtain fused data. A country of origin discrimination model is constructed based on the fused data; Obtain the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands of the sample to be tested; The full spectrum data of the metabolomics to be tested and the spectral bands of the to be tested are input into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
2. The method for identifying the origin of Huangshan Maofeng tea according to claim 1, characterized in that, Before acquiring the near-infrared spectral data of the compressed sample, the following steps are also included: Simultaneously acquire Raman spectral data of the compressed sample; The near-infrared spectral data and the Raman spectral data of the samples were respectively subjected to mean preprocessing. OPLS-DA models were constructed based on preprocessed near-infrared spectral data and preprocessed Raman spectral data of the samples, and the goodness of fit and predictive ability of the OPLS-DA models were compared. The spectral data type corresponding to the OPLS-DA model with better predictive ability is determined to be sample near-infrared spectral data.
3. The method for identifying the origin of Huangshan Maofeng tea according to claim 1, characterized in that, After preprocessing the near-infrared spectral data of the samples, characteristic spectral bands of the samples were selected, specifically including: The near-infrared spectral data of the sample were preprocessed using the optimal preprocessing method; Feature selection algorithms are used to extract characteristic spectral bands from the near-infrared spectral data of the samples after optimal preprocessing.
4. The method for identifying the origin of Huangshan Maofeng tea according to claim 3, characterized in that, The optimal preprocessing method is standard normal variable transformation; the feature selection algorithm is one or a combination of competitive adaptive reweighted sampling algorithm and random forest algorithm.
5. The method for identifying the origin of Huangshan Maofeng tea according to claim 1, characterized in that, The data fusion of the full-spectrum metabolomics data of the sample with the characteristic spectral bands of the sample specifically includes: The full spectrum of metabolomics data of the samples was normalized with the characteristic spectral bands of the samples. The normalized full-spectrum metabolomics data of the samples and the normalized characteristic spectral bands of the samples are spliced or weighted and fused.
6. The method for identifying the origin of Huangshan Maofeng tea according to claim 1, characterized in that, Also includes: Core differentially expressed metabolites of the samples were screened from the full spectrum of metabolomics data of the samples; Correlation analysis was performed on the core differential metabolites of the sample and the characteristic spectral bands of the sample.
7. A system for identifying the origin of Huangshan Maofeng tea, characterized in that, include: The sample preparation module is used to collect Huangshan Maofeng tea samples from known origins and prepare extract samples and tablet samples respectively. The sample metabolomics full-spectrum data acquisition module is used to perform metabolomics detection on the extract sample to obtain sample metabolomics full-spectrum data; The sample characteristic spectral band screening module is used to collect the near-infrared spectral data of the tablet sample, and screen out the sample characteristic spectral bands after preprocessing the near-infrared spectral data. The data fusion module is used to fuse the full spectrum data of the sample metabolomics with the characteristic spectral bands of the sample to obtain fused data; The model building module is used to build an origin discrimination model based on the fused data; The test information acquisition module is used to acquire the full spectrum data of the metabolomics of the tea sample to be tested and the characteristic spectral bands to be tested. The Zen-based discrimination module is used to input the full spectrum data of the metabolomics to be tested and the spectral bands of the characteristic to be tested into the origin discrimination model to determine whether the origin of the tea sample to be tested is Huangshan Maofeng production area.
8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for identifying the origin of Huangshan Maofeng tea as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for identifying the origin of Huangshan Maofeng tea as described in any one of claims 1-6.
10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for identifying the origin of Huangshan Maofeng tea as described in any one of claims 1-6.