Comprehensive evaluation method and system based on Huoxiang Zhengqi soft capsule finished product

Abstract

The invention provides a comprehensive evaluation method and system based on a Huoxiang Zhengqi soft capsule finished product, and relates to the technical field of intelligent manufacturing and quality evaluation of traditional Chinese medicine preparations, and the method comprises the following steps: collecting near infrared spectrum data of the Huoxiang Zhengqi soft capsule finished product in real time; determining n batches of production data with the best production result according to a production field, and preprocessing the collected near infrared spectrum data; performing PCA dimension reduction analysis on the preprocessed n batches of data, and establishing a PCA model; based on a PCA model, performing Mahalanobis distance calculation according to the score of the selected principal component, and calculating a Mahalanobis distance threshold to obtain a threshold line; the unknown batch is supervised according to the obtained threshold value line, if the unknown batch does not exceed the threshold value line, the production is qualified, and if the unknown batch exceeds the threshold value line, the production quality is poor. By adopting a method of combining a near infrared spectrum technology and chemometrics, rapid and nondestructive evaluation of the quality of the preparation is realized, and the defects of time consumption and complexity of a traditional detection method are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing and quality evaluation of traditional Chinese medicine preparations, and particularly to a comprehensive evaluation method and system based on the finished products of Huoxiang Zhengqi soft capsules. Background Art

[0002] As an important part of traditional Chinese medicine in China, the quality and effectiveness of traditional Chinese medicine preparations are crucial for the treatment effect of patients. However, there are some significant deficiencies in the current quality evaluation methods for traditional Chinese medicine preparations. First of all, when measuring the content of quality markers in preparations by the traditional high performance liquid chromatography (HPLC) method, it is not only time-consuming and the method is complex, but also there is loss of the produced preparations. This undoubtedly increases the production cost and may affect the quality of the preparations. In addition, pharmaceutical companies usually use the active ingredients and moisture in the finished preparations as the quality release standards. Although these are indeed important indicators for evaluating the quality of preparations, measuring all these indicators is both time-consuming and laborious. More importantly, the existing technologies do not provide a simple and efficient method to evaluate the quality of production batches.

[0003] Taking Huoxiang Zhengqi soft capsules as an example, the current evaluation method for the quality of its finished products is to sample and measure the components and moisture content to evaluate batches. However, this method also has its limitations, such as large sample consumption, long detection time, and the need for multiple parts to jointly detect the same batch.

[0004] Chinese Patent CN115293480A discloses an integrated method for evaluating the comprehensive quality digital capabilities of intelligent manufacturing of traditional Chinese medicine preparations. This method collects raw materials, intermediates, finished products, etc. of multiple batches of traditional Chinese medicine preparations, conducts multi-dimensional index detection, and reduces the multi-dimensional indexes to the same dimension. By comparing the weights of different dimensions, the indexes representing the quality of traditional Chinese medicine preparations are screened out. However, this patent does not elaborate on how to use these important indexes to evaluate production batches.

[0005] In summary, there are many deficiencies in the existing technologies, such as complex detection methods, time-consuming and laborious, unclear evaluation of production batches, etc. Therefore, there is an urgent need to provide a faster, more accurate and efficient method for the quality evaluation of traditional Chinese medicine preparations. Summary of the Invention

[0006] For this reason, the embodiments of the present invention provide a comprehensive evaluation method and system based on the finished products of Huoxiang Zhengqi soft capsules to solve the problems of complex detection methods, time-consuming and laborious, unclear evaluation of production batches, etc. in the existing technologies.

[0007] To solve the above problems, the embodiments of the present invention provide a comprehensive evaluation method based on the finished products of Huoxiang Zhengqi soft capsules, and the method includes:

[0008] S1: Collect the near-infrared spectral data of the finished Huoxiang Zhengqi soft capsules in real time;

[0009] S2: Determine the production data of the n batches with the best production results according to the production site, and preprocess the collected near-infrared spectral data;

[0010] S3: Perform PCA dimensionality reduction analysis on the preprocessed data of n batches to establish a PCA model;

[0011] S4: Based on the PCA model, calculate the Mahalanobis distance according to the selected principal component scores, and calculate the Mahalanobis distance threshold to obtain a threshold line;

[0012] S5: Supervise the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production quality is poor.

[0013] Preferably, the method for preprocessing the collected near-infrared spectral data is:

[0014] Preprocess the spectrum using the standard normal transformation method.

[0015] Preferably, the method for calculating the Mahalanobis distance according to the selected principal component scores is:

[0016]

[0017] In the formula, D is the Mahalanobis distance value, M -1 is the inverse matrix of the covariance matrix of the standard spectral data set; A i is the spectral matrix of the sample set; represents the average spectral matrix.

[0018] Preferably, the method for calculating the principal component scores is:

[0019] A n×f = X n×m × P m×f

[0020] In the formula, A is the original spectral matrix; X is the spectral matrix; P is the principal component loading matrix; n is the number of samples; m is the number of variables; f is the number of principal components.

[0021] Preferably, the method for centering the original spectral matrix:

[0022]

[0023] In the formula, A is the original spectral matrix; is the average spectral matrix, A u is the spectral matrix after centering.

[0024] Preferably, the method for calculating the covariance matrix of the standard spectral data set is as follows:

[0025]

[0026] wherein is the transpose matrix of the spectral matrix after centralization processing; A u is the spectral matrix after centralization; n is the number of samples; M is the covariance matrix of the standard spectral data set.

[0027] Preferably, the method for calculating the Mahalanobis distance threshold is as follows:

[0028]

[0029] wherein is the average value of the Mahalanobis distance; σ D is the standard deviation of the Mahalanobis distance; e is the weight coefficient for adjusting the rejection threshold.

[0030] An embodiment of the present invention also provides a comprehensive evaluation system based on the finished product of Huoxiang Zhengqi Soft Capsules, which is used to implement the comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules described above, and specifically includes:

[0031] A data acquisition module, which collects the near-infrared spectral data of the finished product of Huoxiang Zhengqi Soft Capsules in real time;

[0032] A data preprocessing module, which is used to determine the n batches of production data with the best production results according to the production site and preprocess the collected near-infrared spectral data;

[0033] A model establishment module, which is used to perform PCA dimensionality reduction analysis on the preprocessed n batches of data and establish a PCA model;

[0034] A distance calculation module, which is used to calculate the Mahalanobis distance based on the PCA model according to the selected principal component scores and calculate the Mahalanobis distance threshold to obtain a threshold line;

[0035] A determination module, which is used to supervise the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production is unqualified.

[0036] An embodiment of the present invention also provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules described above.

[0037] An embodiment of the present invention also provides a computer storage medium. The computer storage medium stores a computer software product. The computer software product includes a number of instructions for causing a computer device to execute the above-mentioned comprehensive evaluation method based on the finished product of Huoxiang Zhengqi soft capsules.

[0038] As can be seen from the above technical solutions, the present invention application has the following advantages:

[0039] (1) Improved evaluation efficiency: By adopting a method combining near-infrared spectroscopy technology and chemometrics, rapid and non-destructive evaluation of the preparation quality is achieved, avoiding the time-consuming and complex disadvantages of traditional detection methods.

[0040] (2) Ensured preparation quality: By screening important indicators representing the quality of traditional Chinese medicine preparations, the quality of the preparations can be evaluated more accurately, ensuring the treatment effect of patients.

[0041] (3) Applicable to multiple preparations: This method is not only applicable to specific preparations such as Huoxiang Zhengqi soft capsules, but can also be applied to the quality evaluation of other traditional Chinese medicine preparations, with a wider application value.

[0042] (4) Promoted the intelligent manufacturing of traditional Chinese medicine preparations: The integrated method for evaluating the comprehensive quality digital capabilities of intelligent manufacturing of traditional Chinese medicine preparations provided by the present invention can objectively evaluate the digital capabilities of each manufacturing unit, and has important guiding value for the development of intelligent manufacturing of traditional Chinese medicine preparations. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly describe the drawings required to be used in the embodiments. By referring to the drawings, the features and advantages of the present invention will be more clearly understood. The drawings are schematic and should not be construed as limiting the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0044] Figure 1 It is a flowchart of a comprehensive evaluation method based on the finished product of Huoxiang Zhengqi soft capsules provided in the embodiment;

[0045] Figure 2 It is a schematic diagram of the threshold line of the Mahalanobis distance in the embodiment;

[0046] Figure 3 It is a prediction schematic diagram in the embodiment;

[0047] Figure 4 It is a block diagram of a comprehensive evaluation system based on the finished product of Huoxiang Zhengqi soft capsules provided in the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0049] Embodiment 1

[0050] To address issues in the prior art such as complex detection methods, time-consuming and laborious processes, and unclear evaluation of production batches, as Figure 1 shown, an embodiment of the present invention proposes a comprehensive evaluation method based on the finished products of Huoxiang Zhengqi Soft Capsules. The method includes:

[0051] S1: Real-time collect the near-infrared spectral data of the finished products of Huoxiang Zhengqi Soft Capsules;

[0052] S2: Determine the n batches of production data with the best production results according to the production site, and preprocess the collected near-infrared spectral data;

[0053] S3: Perform PCA dimensionality reduction analysis on the preprocessed n batches of data to establish a PCA model;

[0054] S4: Based on the PCA model, calculate the Mahalanobis distance according to the selected principal component scores, and calculate the Mahalanobis distance threshold to obtain a threshold line;

[0055] S5: Supervise the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production quality is poor.

[0056] As can be seen from the above technical solutions, the present invention provides a comprehensive evaluation method based on the finished products of Huoxiang Zhengqi Soft Capsules. By real-time collecting the near-infrared spectral data of the finished products of Huoxiang Zhengqi Soft Capsules; determining the n batches of production data with the best production results according to the production site, and preprocessing the collected near-infrared spectral data; performing PCA dimensionality reduction analysis on the preprocessed n batches of data to establish a PCA model; based on the PCA model, calculating the Mahalanobis distance according to the selected principal component scores, and calculating the Mahalanobis distance threshold to obtain a threshold line; supervising the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production quality is poor. The present invention aims to simplify the evaluation process, improve the evaluation efficiency, and at the same time maintain an accurate assessment of the preparation quality. Through near-infrared spectroscopy technology, the chemical information of the preparation can be quickly obtained without destroying the sample. Combining chemometric algorithms, these information can be deeply analyzed, thereby realizing a rapid and accurate evaluation of the preparation quality.

[0057] In this embodiment, in step S1, a near-infrared spectrometer is used to collect the near-infrared spectral data of the finished Huoxiang Zhengqi soft capsules in real time. The collection time interval is 10 s, and the collection time is 15 min.

[0058] In this embodiment, in step S2, according to the production site, the best n (n≥5) batches of production data are determined, and in this embodiment, n = 7, and the collected near-infrared spectral data are preprocessed. Specifically, the collected near-infrared spectral data are imported into Unscrambler software, and the standard normal variate transformation (SNV) method - first derivative (1st derivative) is used to preprocess the spectrum.

[0059] In this embodiment, in step S3, the preprocessed 7 batches of data are subjected to PCA dimensionality reduction analysis to establish a PCA model.

[0060] In this embodiment, in step S4, based on the PCA model, the Mahalanobis distance is calculated according to the selected principal component scores, and the Mahalanobis distance threshold is calculated to obtain a threshold line.

[0061] Specifically, the method for calculating the Mahalanobis distance according to the selected principal component scores is as follows:

[0062]

[0063] In the formula, D is the Mahalanobis distance value, M -1 is the inverse matrix of the covariance matrix of the standard spectral data set; A i is the spectral matrix of the sample set; represents the average spectral matrix.

[0064] Furthermore, the method for calculating the principal component scores is as follows:

[0065] A n×f = X n×m × P m×f

[0066] In the formula, A is the original spectral matrix; X is the spectral matrix; P is the principal component loading matrix; n is the number of samples; m is the number of variables; f is the number of principal components.

[0067] Furthermore, the method for centering the original spectral matrix:

[0068]

[0069] In the formula, A is the original spectral matrix; is the average spectral matrix, A u is the spectral matrix after centering.

[0070] Furthermore, the method for calculating the covariance matrix of the standard spectral data set is as follows:

[0071]

[0072] In the formula, is the transpose matrix of the spectral matrix after centering; A u is the spectral matrix after centering; n is the number of samples; M is the covariance matrix of the standard spectral data set.

[0073] Furthermore, the method for calculating the Mahalanobis distance threshold is as follows:

[0074]

[0075] In the formula, is the average value of the Mahalanobis distance; σ D is the standard deviation of the Mahalanobis distance; e is the weight coefficient for adjusting the rejection threshold.

[0076] The Mahalanobis distance of each sample is obtained from the data after dimensionality reduction, and the threshold line of the Mahalanobis distance is calculated. The threshold line is 0.00889, as Figure 2 shown.

[0077] In this embodiment, in step S5, the unknown batch is supervised according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production quality is poor.

[0078] Collect the spectral data of the new batch, import it into the Unscrambler software, use the established PCA model to predict the new batch, obtain the Mahalanobis distance value corresponding to each spectral point of the new batch, and evaluate the finished product of the new production batch according to the known control line, as Figure 3 shown. According to the fact that it does not exceed the control line, it can be known that the production quality of the new batch is good.

[0079] Embodiment 2

[0080] As Figure 4 shown, the present invention provides a comprehensive evaluation system for Huoxiang Zhengqi soft capsules. This system is used to implement the comprehensive evaluation method for Huoxiang Zhengqi soft capsules in the above Embodiment 1, and specifically includes:

[0081] A data acquisition module that real-time collects the near-infrared spectral data of Huoxiang Zhengqi soft capsules;

[0082] A data preprocessing module that is used to determine the n batches of production data with the best production results according to the production site and preprocess the collected near-infrared spectral data;

[0083] A model establishment module, configured to perform PCA dimensionality reduction analysis on the preprocessed data of n batches and establish a PCA model;

[0084] A distance calculation module, configured to calculate the Mahalanobis distance based on the PCA model according to the selected principal component scores, and calculate the Mahalanobis distance threshold to obtain a threshold line;

[0085] A determination module, configured to supervise the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production is unqualified.

[0086] A comprehensive evaluation system for Huoxiang Zhengqi soft capsules according to this embodiment is used to implement the foregoing comprehensive evaluation method for Huoxiang Zhengqi soft capsules. Therefore, the specific implementation manners in the comprehensive evaluation system for Huoxiang Zhengqi soft capsules can be seen in the embodiment part of the foregoing comprehensive evaluation method for Huoxiang Zhengqi soft capsules. For example, the data acquisition module 10, the data preprocessing module 20, the model establishment module 30, the distance calculation module 40, and the determination module 50 are respectively used to implement steps S1, S2, S3, S4, and S5 in the foregoing comprehensive evaluation method for Huoxiang Zhengqi soft capsules. Therefore, the specific implementation manners thereof can refer to the descriptions of the corresponding respective part embodiments. To avoid redundancy, they will not be elaborated herein.

[0087] Embodiment III

[0088] The embodiment of the present invention further provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the foregoing comprehensive evaluation method for Huoxiang Zhengqi soft capsules.

[0089] Embodiment IV

[0090] The embodiment of the present invention further provides a computer storage medium, which stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the foregoing comprehensive evaluation method for Huoxiang Zhengqi soft capsules.

[0091] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0092] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in the Figure 1 single flow or multiple flows and / or blocks Figure 1 single block or multiple blocks.

[0093] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in the Figure 1 single flow or multiple flows and / or blocks Figure 1 single block or multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 single flow or multiple flows and / or blocks Figure 1 single block or multiple blocks.

[0094] Obviously, the above embodiments are only examples for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules, characterized in that Including: S1: Real-time collect the near-infrared spectral data of the finished Huoxiang Zhengqi Soft Capsules; S2: Determine the n batches of production data with the best production results according to the production site, and preprocess the collected near-infrared spectral data; S3: Perform PCA dimensionality reduction analysis on the preprocessed n batches of data to establish a PCA model; S4: Based on the PCA model, calculate the Mahalanobis distance according to the selected principal component scores, and calculate the Mahalanobis distance threshold to obtain a threshold line; S5: Supervise the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production quality is poor.

2. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules according to claim 1, characterized in that The method for preprocessing the collected near-infrared spectral data is as follows: Preprocess the spectrum using the standard normal transformation method.

3. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules according to claim 1, wherein The method for calculating the Mahalanobis distance according to the selected principal component scores is as follows: where D is the Mahalanobis distance value, and M -1 is the inverse matrix of the covariance matrix of the standard spectral data set; A i is the spectral matrix of the sample set; represents the average spectral matrix.

4. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi soft capsules according to claim 3, characterized in that, The method for calculating the principal component scores is as follows: A n×f = X n×m × P m×f In the formula, A is the original spectral matrix; X is the spectral matrix; P is the principal component loading matrix; n is the number of samples; m is the number of variables; f is the number of principal components.

5. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules according to claim 3, characterized in that, The method for centering the original spectral matrix: Where A is the original spectral matrix; is the average spectral matrix, and A u is the spectral matrix after centering.

6. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules according to claim 3, characterized in that, The method for calculating the covariance matrix of the standard spectral data set: In the formula, is the transposed matrix of the spectral matrix after centering; A u is the spectral matrix after centering; n is the number of samples; M is the covariance matrix of the standard spectral data set.

7. The comprehensive evaluation method based on the finished product of Huoxiang Zhengqi Soft Capsules according to claim 1, wherein The method for calculating the Mahalanobis distance threshold: Wherein, is the average value of Mahalanobis distance; σ D is the standard deviation of Mahalanobis distance; e is the weight coefficient for adjusting the rejection threshold.

8. An integrated evaluation system based on the finished product of Huoxiang Zhengqi Soft Capsules, characterized in that, The system is used to implement the comprehensive evaluation method based on the finished Huoxiang Zhengqi Soft Capsules described in any one of claims 1 to 7, specifically including: A data acquisition module that real-time collects the near-infrared spectral data of the finished Huoxiang Zhengqi Soft Capsules; A data preprocessing module for determining the n batches of production data with the best production results according to the production site and preprocessing the collected near-infrared spectral data; A model establishment module for performing PCA dimensionality reduction analysis on the preprocessed n batches of data to establish a PCA model; A distance calculation module for calculating the Mahalanobis distance based on the PCA model according to the selected principal component scores and calculating the Mahalanobis distance threshold to obtain a threshold line; A determination module for supervising the unknown batches according to the obtained threshold line. If it does not exceed the threshold line, the production is qualified; if it exceeds the threshold line, the production is unqualified.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the comprehensive evaluation method based on the finished Huoxiang Zhengqi Soft Capsules described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer software product. The computer software product includes several instructions for causing a computer device to execute the comprehensive evaluation method based on the finished Huoxiang Zhengqi Soft Capsules described in any one of claims 1 to 7.

Images