A method and system for analyzing process parameters of traditional Chinese medicine production based on big data

Abstract

The present invention relates to the technical field of production parameter analysis, and specifically discloses a method and system for analyzing traditional Chinese medicine production process parameters based on big data, the method comprising: obtaining a large number of traditional Chinese medicine production instances of the type of traditional Chinese medicine product to be analyzed, and extracting all production process parameters and product evaluation information of the corresponding batch of traditional Chinese medicine products; extracting multiple single-dimensional evaluation information from each product evaluation information; based on all production process parameters in all traditional Chinese medicine production instances and the corresponding multiple single-dimensional evaluation information, analyzing the influence of each production process parameter on each evaluation dimension of the traditional Chinese medicine product to be analyzed; based on the influence of all production process parameters on each evaluation dimension of the traditional Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the traditional Chinese medicine product to be analyzed, generating a production optimization report; and realizing accurate optimization of the production process parameters of the traditional Chinese medicine product to be analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of production parameter analysis, and in particular to a method and system for analyzing production process parameters of traditional Chinese medicine based on big data. Background Art

[0002] At present, many studies have made some progress in the analysis of TCM production process parameters based on big data. For example, a mathematical model of the TCM preparation process can be established through machine learning algorithms (such as regression, classification, clustering, dimensionality reduction, etc.), and the experimental process can be optimized based on the prediction results of the model. In addition, chemometrics and data mining techniques can be combined with experimental data to screen and evaluate the key parameters in the preparation process of TCM preparations.

[0003] However, optimizing the experimental process based on the prediction results of the model trained by the artificial intelligence algorithm requires a large number of model training steps, and when the prediction results show that the traditional Chinese medicine product performs poorly in a certain evaluation dimension, it is impossible to accurately determine the production process parameters that need to be optimized and their degree of optimization.

[0004] Therefore, the present invention proposes a method and system for analyzing traditional Chinese medicine production process parameters based on big data. Summary of the invention

[0005] The present invention provides a method and system for analyzing the production process parameters of traditional Chinese medicine based on big data, which are used to accurately analyze the influence of each production process parameter of the traditional Chinese medicine product on each evaluation dimension of the traditional Chinese medicine product to be analyzed. On the premise of knowing that the performance of the traditional Chinese medicine product in a certain evaluation dimension is poor, the production process parameters of the traditional Chinese medicine product to be analyzed can be accurately optimized.

[0006] The present invention provides a method for analyzing process parameters of traditional Chinese medicine production based on big data, comprising:

[0007] S1: Obtain a large number of TCM production examples of the type of TCM product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of TCM products in each TCM production example;

[0008] S2: extracting multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information;

[0009] S3: Based on all the production process parameters in all the TCM production instances and the corresponding multiple single-dimensional evaluation information, the influence of each production process parameter on each evaluation dimension of the TCM product to be analyzed is analyzed;

[0010] S4: Generate a production optimization report based on the degree of influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimensions to be optimized of the Chinese medicine product to be analyzed.

[0011] Preferably, S1: obtaining a large number of Chinese medicine production examples of the type of Chinese medicine product to be analyzed, and extracting all production process parameters and product evaluation information of the corresponding batch of Chinese medicine products in each Chinese medicine production example, including:

[0012] S101: Obtaining a large number of traditional Chinese medicine production examples of the type of traditional Chinese medicine product to be analyzed in a production record information database;

[0013] S102: obtaining the production process record information of the corresponding batch of Chinese medicine products in each Chinese medicine production instance, and using the specific parameters of all adjustable information items in the production process record information as all production process parameters of the corresponding batch of Chinese medicine products;

[0014] S103: Obtain product evaluation information of a corresponding batch of traditional Chinese medicine products in each traditional Chinese medicine production instance.

[0015] Preferably, S2: extracting multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information, including:

[0016] S201: parsing each product evaluation information based on a plurality of preset evaluation dimensions to obtain original evaluation information of a corresponding batch of traditional Chinese medicine products under each evaluation dimension;

[0017] S202: Standardize and refine each piece of original evaluation information to obtain single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products in each evaluation dimension.

[0018] Preferably, S3: based on all production process parameters in all traditional Chinese medicine production instances and corresponding multiple single-dimensional evaluation information, analyzing the influence of each production process parameter on each evaluation dimension of the traditional Chinese medicine product to be analyzed, including:

[0019] Generate a production process parameter vector for each Chinese medicine production instance based on all production process parameters in each Chinese medicine production instance, and generate a production process parameter matrix for all Chinese medicine production instances based on the production process parameter vectors of all Chinese medicine production instances;

[0020] Orthogonalizing the production process parameter matrix to obtain the production process parameter orthogonal matrix, and determining the production process parameter latent vector of each traditional Chinese medicine production instance in the production process parameter orthogonal matrix;

[0021] The inner product between the latent vectors of the production process parameters of each two traditional Chinese medicine production instances is regarded as the correlation degree between all the production process parameters of the corresponding two traditional Chinese medicine production instances;

[0022] Calculate the similarity between the same production process parameters of each two traditional Chinese medicine production examples;

[0023] Calculate the similarity of the evaluation information of the product of each two traditional Chinese medicine production examples;

[0024] Based on the correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of the product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed.

[0025] Preferably, calculating the evaluation similarity of the product evaluation information of every two traditional Chinese medicine production instances includes:

[0026] Calculate the evaluation similarity between each group of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances;

[0027] The average of the evaluation similarities between all groups of evaluation information of the same dimension in the product evaluation information of every two traditional Chinese medicine production instances is taken as the evaluation similarity of the product evaluation information of every two traditional Chinese medicine production instances.

[0028] Preferably, based on the correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed, including:

[0029] The product of the correlation degree between all production process parameters of each two traditional Chinese medicine production instances, the parameter similarity between the same production process parameters of the two traditional Chinese medicine production instances, and the evaluation similarity of the product evaluation information of the two traditional Chinese medicine production instances is used as the performance weight of the corresponding production process parameters in the two traditional Chinese medicine production instances;

[0030] Screen out all major production process parameters and all minor production process parameters from among all production process parameters based on all performance weights of all production process parameters;

[0031] A multidimensional thermal analysis was performed on each major production process parameter to obtain the degree of influence of each major production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis was performed on each minor production process parameter to obtain the degree of influence of each minor production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed.

[0032] Preferably, all major production process parameters and all minor production process parameters are screened out from all production process parameters based on all performance weights of all production process parameters, including:

[0033] The average of all performance weights of each production process parameter is taken as the importance of each production process parameter;

[0034] All single production process parameters whose importance is not less than the importance threshold are regarded as all main production process parameters. At the same time, all single production process parameters whose importance is less than the importance threshold are regarded as all secondary production process parameters.

[0035] Preferably, a multidimensional thermal analysis is performed on each main production process parameter to obtain the influence of each main production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis is performed on each secondary production process parameter to obtain the influence of each secondary production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed, including:

[0036] Among all the TCM production instances of the type of TCM product to be analyzed, all TCM production instances with a single production process parameter as a single variable shall serve as all reference production instances with a single production process parameter corresponding to the single variable;

[0037] Calculate the data span of all evaluation information of the same dimension in all reference production instances for each production process parameter;

[0038] Normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the main production process parameters, and at the same time, normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the secondary production process parameters to obtain the normalized value of each data span;

[0039] The normalized value of each data span is regarded as the influence of the corresponding production process parameter on the corresponding evaluation dimension of the analyzed traditional Chinese medicine product.

[0040] Preferably, S4: based on the influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed, a production optimization report is generated, including:

[0041] All production process parameters whose impact on the current evaluation dimension to be optimized is not less than the impact threshold of the analyzed traditional Chinese medicine product are regarded as all priority production process parameters of the current evaluation dimension to be optimized;

[0042] Summarize the influence of all priority production process parameters of the current evaluation dimension to be optimized on the current evaluation dimension to be optimized and generate a production optimization report.

[0043] The present invention provides a traditional Chinese medicine production process parameter analysis system based on big data, comprising:

[0044] An information acquisition module is used to obtain a large number of Chinese medicine production examples of the type of Chinese medicine product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of Chinese medicine products in each Chinese medicine production example;

[0045] An information extraction module is used to extract multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information;

[0046] The degree analysis module is used to analyze the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed based on all production process parameters in all Chinese medicine production instances and the corresponding multiple single-dimensional evaluation information;

[0047] The report generation module is used to generate a production optimization report based on the degree of influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed.

[0048] The beneficial effect of the present invention compared with the prior art is: by accurately analyzing the influence of each production process parameter of the traditional Chinese medicine product on each evaluation dimension of the traditional Chinese medicine product to be analyzed, on the premise of knowing that the traditional Chinese medicine product performs poorly in a certain evaluation dimension, accurate optimization of the production process parameters of the traditional Chinese medicine product to be analyzed can be achieved.

[0049] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 This is a flow chart of a method for analyzing process parameters of traditional Chinese medicine production based on big data in an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of a traditional Chinese medicine production process parameter analysis system based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0055] Example 1: The present invention provides a method for analyzing the production process parameters of traditional Chinese medicine based on big data, referring to Figure 1 ,include:

[0056] S1: Obtain a large number of TCM production examples of the type of TCM product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of TCM products in each TCM production example;

[0057] S2: extracting multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information;

[0058] S3: Based on all the production process parameters in all the TCM production instances and the corresponding multiple single-dimensional evaluation information, the influence of each production process parameter on each evaluation dimension of the TCM product to be analyzed is analyzed;

[0059] S4: Generate a production optimization report based on the degree of influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimensions to be optimized of the Chinese medicine product to be analyzed.

[0060] In this embodiment, the type of Chinese medicine product to be analyzed is the type of Chinese medicine product that needs to be analyzed using the Chinese medicine production process parameter analysis method based on big data in this embodiment, wherein the Chinese medicine product is a medicine or a medicine intermediate produced using Chinese medicine ingredients.

[0061] In this embodiment, the Chinese medicine production instance is an instance record that records relevant information of the complete production process of a single batch of Chinese medicine products to be analyzed and product evaluation information of the batch of Chinese medicine products to be analyzed.

[0062] In this embodiment, the corresponding batch of Chinese medicine products is the Chinese medicine product produced by the complete production process recorded in the corresponding Chinese medicine production instance.

[0063] In this embodiment, all production process parameters include, for example, raw material composition ratio, production temperature, humidity, pressure, extraction speed and concentration, and other process parameters related to the production process of traditional Chinese medicine.

[0064] In this embodiment, the product evaluation information is the evaluation information given by professionals for the corresponding batch of traditional Chinese medicine products.

[0065] In this embodiment, the single-dimensional evaluation information is the evaluation information contained in the product evaluation information, which evaluates the corresponding batch of traditional Chinese medicine products from a single dimension, for example, the evaluation information that evaluates the corresponding batch of traditional Chinese medicine products from any dimension such as efficacy, product form or output.

[0066] In this embodiment, the influence degree of each production process parameter on each evaluation dimension of the Chinese medicinal product to be analyzed represents the influence degree of each production process parameter on the performance of the Chinese medicinal product to be analyzed in each evaluation dimension.

[0067] In this embodiment, the current evaluation dimension to be optimized represents the evaluation dimension of the Chinese medicine product to be analyzed that currently needs to be optimized. It can also be understood that the Chinese medicine product obtained by the complete production process to be optimized of the Chinese medicine product to be analyzed performs poorly in the current evaluation dimension to be optimized.

[0068] The beneficial effect of the above technology is: by accurately analyzing the influence of each production process parameter of the traditional Chinese medicine product on each evaluation dimension of the traditional Chinese medicine product to be analyzed, on the premise of knowing that the traditional Chinese medicine product performs poorly in a certain evaluation dimension, the production process parameters of the traditional Chinese medicine product to be analyzed can be accurately optimized.

[0069] Example 2: Based on Example 1, S1: obtaining a large number of Chinese medicine production examples of the type of Chinese medicine product to be analyzed, and extracting all production process parameters and product evaluation information of the corresponding batch of Chinese medicine products in each Chinese medicine production example, including:

[0070] S101: Obtaining a large number of traditional Chinese medicine production examples of the type of traditional Chinese medicine product to be analyzed in a production record information database;

[0071] S102: obtaining the production process record information of the corresponding batch of Chinese medicine products in each Chinese medicine production instance, and using the specific parameters of all adjustable information items in the production process record information as all production process parameters of the corresponding batch of Chinese medicine products;

[0072] S103: Obtain product evaluation information of a corresponding batch of traditional Chinese medicine products in each traditional Chinese medicine production instance.

[0073] In this embodiment, the production process record information is information recording the complete production process of the Chinese medicine product to be analyzed.

[0074] In this embodiment, all items may be adjustable information items such as temperature, humidity, pressure in a certain step of the production process or parameter items such as extraction concentration or speed in the extraction step.

[0075] In this embodiment, all items can adjust specific parameters of the information items, such as the specific value of the extraction concentration in the extraction step.

[0076] The beneficial effects of the above technology are: completing the acquisition of a large number of traditional Chinese medicine production examples of the types of traditional Chinese medicine products to be analyzed, and extracting all production process parameters and product evaluation information of each batch of traditional Chinese medicine products.

[0077] Example 3: Based on Example 1, S2: extracting multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information, including:

[0078] S201: parsing each product evaluation information based on a plurality of preset evaluation dimensions to obtain original evaluation information of a corresponding batch of traditional Chinese medicine products under each evaluation dimension;

[0079] S202: Standardize and refine each piece of original evaluation information to obtain single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products in each evaluation dimension.

[0080] In this embodiment, the original evaluation information under each evaluation dimension is information directly extracted from the product evaluation information, which evaluates the corresponding batch of traditional Chinese medicine products from a single dimension.

[0081] In this embodiment, each piece of original evaluation information is standardized and refined to obtain single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products in each evaluation dimension by using existing technologies to remove redundant words, replace them with synonyms or idioms, use short words, etc.

[0082] The beneficial effect of the above technology is: completing the extraction and standardized refinement process of multiple single-dimensional evaluation information for each batch of traditional Chinese medicine products.

[0083] Example 4: Based on Example 1, S3: Based on all production process parameters in all Chinese medicine production examples and the corresponding multiple single-dimensional evaluation information, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed, including:

[0084] Generate a production process parameter vector for each Chinese medicine production instance based on all production process parameters in each Chinese medicine production instance, and generate a production process parameter matrix for all Chinese medicine production instances based on the production process parameter vectors of all Chinese medicine production instances;

[0085] Orthogonalizing the production process parameter matrix to obtain the production process parameter orthogonal matrix, and determining the production process parameter latent vector of each traditional Chinese medicine production instance in the production process parameter orthogonal matrix;

[0086] The inner product between the latent vectors of the production process parameters of each two traditional Chinese medicine production instances is regarded as the correlation degree between all the production process parameters of the corresponding two traditional Chinese medicine production instances;

[0087] Calculate the similarity between the same production process parameters of each two traditional Chinese medicine production examples;

[0088] Calculate the similarity of the evaluation information of the product of each two traditional Chinese medicine production examples;

[0089] Based on the correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of the product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed.

[0090] In this embodiment, the production process parameter vector of each Chinese medicine production instance is generated based on all production process parameters in each Chinese medicine production instance, that is:

[0091] The numerical values ​​of all production process parameters in each traditional Chinese medicine production instance are sorted in a preset order to generate a column vector, that is, a production process parameter vector for each traditional Chinese medicine production instance.

[0092] In this embodiment, the production process parameter matrix of all Chinese medicine production instances is generated based on the production process parameter vectors of all Chinese medicine production instances, namely:

[0093] The production process parameter vectors of all traditional Chinese medicine production instances are sorted and combined according to the recording time of the traditional Chinese medicine production instances from early to late or other sorting rules to obtain the production process parameter matrix of all traditional Chinese medicine production instances.

[0094] In this embodiment, the hidden vector of the production process parameters of each Chinese medicine production instance is:

[0095] When the production process parameter vector of each traditional Chinese medicine production instance is in the column number j in the production process parameter matrix of all traditional Chinese medicine production instances, the column vector composed of the j-th column elements in the production process parameter orthogonal matrix is ​​regarded as the latent vector of the production process parameters of the corresponding traditional Chinese medicine production instance.

[0096] In this embodiment, the similarity between the same production process parameters of each two traditional Chinese medicine production examples is calculated, that is:

[0097] The ratio of twice the difference between the same production process parameters of each two traditional Chinese medicine production instances to the sum of the same production process parameters of the corresponding two traditional Chinese medicine production instances is regarded as the parameter similarity between the same production process parameters of the corresponding two traditional Chinese medicine production instances.

[0098] The beneficial effects of the above technology are: by sequentially generating a production process parameter vector for each Chinese medicine production instance and a production process parameter matrix for all Chinese medicine production instances, and performing matrix orthogonalization on the production process parameter matrix to determine the latent vector of the production process parameters for each Chinese medicine production instance, a vector that can simply represent the macro characteristics of all production process parameters of each Chinese medicine production instance is determined, and further by calculating the degree of correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters, and the evaluation similarity of product evaluation information, an accurate analysis of the degree of influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is achieved.

[0099] Example 5: Based on Example 4, the evaluation similarity of the product evaluation information of every two traditional Chinese medicine production examples is calculated, including:

[0100] Calculate the evaluation similarity between each group of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances;

[0101] The average of the evaluation similarities between all groups of evaluation information of the same dimension in the product evaluation information of every two traditional Chinese medicine production instances is taken as the evaluation similarity of the product evaluation information of every two traditional Chinese medicine production instances.

[0102] In this embodiment, each group of evaluation information of the same dimension includes evaluation information belonging to the same evaluation dimension in the product evaluation information of two traditional Chinese medicine production instances.

[0103] In this embodiment, the evaluation similarity between each group of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances is calculated, including:

[0104] The sensitive hashing algorithm is used to map the two single-dimensional evaluation information in each group of same-dimensional evaluation information into a one-dimensional vector with a length of 64 and element values ​​of 0 or 1, and the evaluation similarity between the corresponding groups of same-dimensional evaluation information is obtained by calculating the cosine similarity between the two one-dimensional vectors.

[0105] The beneficial effect of the above technology is: realizing the calculation of the evaluation similarity of the product evaluation information of every two traditional Chinese medicine production instances.

[0106] Example 6: On the basis of Example 4, based on the correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed, including:

[0107] The product of the correlation degree between all production process parameters of each two traditional Chinese medicine production instances, the parameter similarity between the same production process parameters of the two traditional Chinese medicine production instances, and the evaluation similarity of the product evaluation information of the two traditional Chinese medicine production instances is used as the performance weight of the corresponding production process parameters in the two traditional Chinese medicine production instances;

[0108] Screen out all major production process parameters and all minor production process parameters from among all production process parameters based on all performance weights of all production process parameters;

[0109] A multidimensional thermal analysis was performed on each major production process parameter to obtain the degree of influence of each major production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis was performed on each minor production process parameter to obtain the degree of influence of each minor production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed.

[0110] In this embodiment, the performance weight of a single production process parameter in two traditional Chinese medicine production examples represents the traditional Chinese medicine degree of the single production process parameter in the two traditional Chinese medicine production examples.

[0111] In this embodiment, the main production process parameter refers to a single production process parameter that has a greater impact on product evaluation information among all production process parameters.

[0112] In this embodiment, the minor production process parameter refers to a single production process parameter that has a smaller impact on the product evaluation information among all production process parameters.

[0113] The beneficial effects of the above technology are: based on the degree of correlation between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of the product evaluation information of every two Chinese medicine production instances, all major production process parameters and all minor production process parameters are distinguished, and by performing multidimensional thermal analysis on each major production process parameter and each minor production process parameter respectively, the degree of influence of each minor production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is accurately analyzed.

[0114] Example 7: Based on Example 6, all major production process parameters and all minor production process parameters are screened out from all production process parameters based on all performance weights of all production process parameters, including:

[0115] The average of all performance weights of each production process parameter is taken as the importance of each production process parameter;

[0116] All single production process parameters whose importance is not less than the importance threshold are regarded as all main production process parameters. At the same time, all single production process parameters whose importance is less than the importance threshold are regarded as all secondary production process parameters.

[0117] In this embodiment, the importance of each production process parameter represents the importance of each production process parameter in all traditional Chinese medicine production examples.

[0118] In this embodiment, the importance threshold is a value that the importance of the preset main production process parameter cannot be less than.

[0119] The beneficial effect of the above technology is: by comparing the calculated importance of each production process parameter with the importance threshold, all major production process parameters and all minor production process parameters can be reasonably distinguished.

[0120] Example 8: Based on Example 6, a multidimensional thermal analysis is performed on each main production process parameter to obtain the influence of each main production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis is performed on each secondary production process parameter to obtain the influence of each secondary production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed, including:

[0121] Among all the TCM production instances of the type of TCM product to be analyzed, all TCM production instances with a single production process parameter as a single variable shall serve as all reference production instances with a single production process parameter corresponding to the single variable;

[0122] Calculate the data span of all evaluation information of the same dimension in all reference production instances for each production process parameter;

[0123] Normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the main production process parameters, and at the same time, normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the secondary production process parameters to obtain the normalized value of each data span;

[0124] The normalized value of each data span is regarded as the influence of the corresponding production process parameter on the corresponding evaluation dimension of the analyzed traditional Chinese medicine product.

[0125] In this embodiment, the same-dimensional evaluation information is single-dimensional evaluation information belonging to the same evaluation dimension.

[0126] In this embodiment, the data span of all the same-dimensional evaluation information in all the reference production instances of each production process parameter is calculated, including:

[0127] Calculate the average AVG of the differences between all pairwise values ​​of all the evaluation information of the same dimension in all the reference production instances of each production process parameter, and take the ratio of the difference delt between the maximum and minimum values ​​of all the evaluation information of the same dimension in all the reference production instances of each production process parameter to the average AVG as the data span of all the evaluation information of the same dimension in all the reference production instances of each production process parameter.

[0128] The beneficial effects of the above technology are: by determining all reference production instances of each production process parameter, calculating the data span of all evaluation information of the same dimension in all reference production instances of each production process parameter, and by normalizing the data span of all evaluation information of the same dimension in all reference production instances of all major production process parameters (secondary production process parameters) respectively, an accurate analysis of the degree of influence of each production process parameter on the corresponding evaluation dimension of the Chinese medicine product to be analyzed is achieved.

[0129] Example 9: Based on Example 1, S4: Based on the influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed, a production optimization report is generated, including:

[0130] All production process parameters whose impact on the current evaluation dimension to be optimized is not less than the impact threshold of the analyzed traditional Chinese medicine product are regarded as all priority production process parameters of the current evaluation dimension to be optimized;

[0131] Summarize the influence of all priority production process parameters of the current evaluation dimension to be optimized on the current evaluation dimension to be optimized and generate a production optimization report.

[0132] In this embodiment, the impact degree threshold is a value that cannot be less than the impact degree of the preset priority production process parameter on the current evaluation dimension to be optimized of the analyzed traditional Chinese medicine product.

[0133] In this embodiment, all the priority production process parameters of the current evaluation dimension to be optimized are single production process parameters that are given priority for optimization when the purpose is to optimize the performance of the analyzed traditional Chinese medicine product in the current evaluation dimension to be optimized.

[0134] The beneficial effect of the above technology is: by comparing the degree of influence of the current evaluation dimension to be optimized of the analyzed traditional Chinese medicine product with the influence degree threshold, all priority production process parameters of the current evaluation dimension to be optimized are determined, and based on this, with the purpose of optimizing the performance of the traditional Chinese medicine product to be analyzed in the current evaluation dimension to be optimized, a single production process parameter that is given priority to be optimized is used to generate a production optimization report for reference by production managers.

[0135] Example 10: The present invention provides a Chinese medicine production process parameter analysis system based on big data, referring to Figure 2 ,include:

[0136] An information acquisition module is used to obtain a large number of Chinese medicine production examples of the type of Chinese medicine product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of Chinese medicine products in each Chinese medicine production example;

[0137] An information extraction module is used to extract multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information;

[0138] The degree analysis module is used to analyze the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed based on all production process parameters in all Chinese medicine production instances and the corresponding multiple single-dimensional evaluation information;

[0139] The report generation module is used to generate a production optimization report based on the degree of influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed.

[0140] The beneficial effect of the above technology is: by accurately analyzing the influence of each production process parameter of the traditional Chinese medicine product on each evaluation dimension of the traditional Chinese medicine product to be analyzed, on the premise of knowing that the traditional Chinese medicine product performs poorly in a certain evaluation dimension, the production process parameters of the traditional Chinese medicine product to be analyzed can be accurately optimized.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for analyzing traditional Chinese medicine production process parameters based on big data, characterized in that: include: S1: Obtain a large number of TCM production examples of the type of TCM product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of TCM products in each TCM production example; S2: extracting multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information; S3: Based on all the production process parameters in all the TCM production instances and the corresponding multiple single-dimensional evaluation information, the influence of each production process parameter on each evaluation dimension of the TCM product to be analyzed is analyzed; S4: Generate a production optimization report based on the influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed; Among them, S3: Based on all the production process parameters in all the traditional Chinese medicine production instances and the corresponding multiple single-dimensional evaluation information, the influence of each production process parameter on each evaluation dimension of the traditional Chinese medicine product to be analyzed is analyzed, including: Generate a production process parameter vector for each Chinese medicine production instance based on all production process parameters in each Chinese medicine production instance, and generate a production process parameter matrix for all Chinese medicine production instances based on the production process parameter vectors of all Chinese medicine production instances; Orthogonalizing the production process parameter matrix to obtain the production process parameter orthogonal matrix, and determining the production process parameter latent vector of each traditional Chinese medicine production instance in the production process parameter orthogonal matrix; The inner product between the latent vectors of the production process parameters of each two traditional Chinese medicine production instances is regarded as the correlation degree between all the production process parameters of the corresponding two traditional Chinese medicine production instances; Calculate the similarity between the same production process parameters of each two traditional Chinese medicine production examples; Calculate the similarity of the evaluation information of the product of each two traditional Chinese medicine production examples; Based on the correlation between all production process parameters of every two TCM production instances, the similarity between the same production process parameters of every two TCM production instances, and the similarity between the evaluation information of the products of every two TCM production instances, the influence of each production process parameter on each evaluation dimension of the TCM products to be analyzed is analyzed; Among them, the evaluation similarity of the product evaluation information of each two traditional Chinese medicine production instances is calculated, including: Calculate the evaluation similarity between each group of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances; The average of the evaluation similarity between all groups of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances is regarded as the evaluation similarity of the product evaluation information of each two traditional Chinese medicine production instances; Among them, based on the correlation degree between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of the product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed, including: The product of the correlation degree between all production process parameters of each two traditional Chinese medicine production instances, the parameter similarity between the same production process parameters of the two traditional Chinese medicine production instances, and the evaluation similarity of the product evaluation information of the two traditional Chinese medicine production instances is used as the performance weight of the corresponding production process parameters in the two traditional Chinese medicine production instances; Based on all performance weights of all production process parameters, all major production process parameters and all minor production process parameters are screened out from all production process parameters; Perform multidimensional thermal analysis on each major production process parameter to obtain the degree of influence of each major production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, perform multidimensional thermal analysis on each minor production process parameter to obtain the degree of influence of each minor production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. Among them, a multidimensional thermal analysis is performed on each main production process parameter to obtain the influence of each main production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis is performed on each secondary production process parameter to obtain the influence of each secondary production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed, including: Among all the TCM production instances of the type of TCM product to be analyzed, all TCM production instances with a single production process parameter as a single variable shall serve as all reference production instances with a single production process parameter corresponding to the single variable; Calculate the data span of all evaluation information of the same dimension in all reference production instances for each production process parameter; Normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the main production process parameters, and at the same time, normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the secondary production process parameters to obtain the normalized value of each data span; The normalized value of each data span is regarded as the influence of the corresponding production process parameter on the corresponding evaluation dimension of the Chinese medicine product to be analyzed.

2. The method for analyzing the production process parameters of traditional Chinese medicine based on big data according to claim 1, characterized in that: S1: Obtain a large number of TCM production examples of the type of TCM product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of TCM products in each TCM production example, including: S101: Obtaining a large number of traditional Chinese medicine production examples of the type of traditional Chinese medicine product to be analyzed in a production record information database; S102: obtaining the production process record information of the corresponding batch of Chinese medicine products in each Chinese medicine production instance, and using the specific parameters of all adjustable information items in the production process record information as all production process parameters of the corresponding batch of Chinese medicine products; S103: Obtain product evaluation information of a corresponding batch of traditional Chinese medicine products in each traditional Chinese medicine production instance.

3. The method for analyzing the production process parameters of traditional Chinese medicine based on big data according to claim 1, characterized in that: S2: Extract multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information, including: S201: parsing each product evaluation information based on a plurality of preset evaluation dimensions to obtain original evaluation information of a corresponding batch of traditional Chinese medicine products under each evaluation dimension; S202: Standardize and refine each piece of original evaluation information to obtain single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products in each evaluation dimension.

4. The method for analyzing the production process parameters of traditional Chinese medicine based on big data according to claim 1, characterized in that: Based on all performance weights of all production process parameters, all major production process parameters and all minor production process parameters are screened out from all production process parameters, including: The average of all performance weights of each production process parameter is taken as the importance of each production process parameter; All single production process parameters whose importance is not less than the importance threshold are regarded as all main production process parameters. At the same time, all single production process parameters whose importance is less than the importance threshold are regarded as all secondary production process parameters.

5. The method for analyzing the production process parameters of traditional Chinese medicine based on big data according to claim 1, characterized in that: S4: Generate a production optimization report based on the influence of all production process parameters on each evaluation dimension of the TCM product to be analyzed and the current evaluation dimension to be optimized of the TCM product to be analyzed, including: All production process parameters whose impact on the current evaluation dimension to be optimized is not less than the impact threshold of the analyzed traditional Chinese medicine product are regarded as all priority production process parameters of the current evaluation dimension to be optimized; Summarize the influence of all priority production process parameters of the current evaluation dimension to be optimized on the current evaluation dimension to be optimized and generate a production optimization report.

6. A traditional Chinese medicine production process parameter analysis system based on big data, characterized in that: include: An information acquisition module is used to obtain a large number of Chinese medicine production examples of the type of Chinese medicine product to be analyzed, and extract all production process parameters and product evaluation information of the corresponding batch of Chinese medicine products in each Chinese medicine production example; An information extraction module is used to extract multiple single-dimensional evaluation information of the corresponding batch of traditional Chinese medicine products from each product evaluation information; The degree analysis module is used to analyze the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed based on all production process parameters in all Chinese medicine production instances and the corresponding multiple single-dimensional evaluation information; A report generation module, for generating a production optimization report based on the influence of all production process parameters on each evaluation dimension of the Chinese medicine product to be analyzed and the current evaluation dimension to be optimized of the Chinese medicine product to be analyzed; The degree analysis module analyzes the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed based on all production process parameters and corresponding multiple single-dimensional evaluation information in all Chinese medicine production instances, including: Generate a production process parameter vector for each Chinese medicine production instance based on all production process parameters in each Chinese medicine production instance, and generate a production process parameter matrix for all Chinese medicine production instances based on the production process parameter vectors of all Chinese medicine production instances; Orthogonalizing the production process parameter matrix to obtain the production process parameter orthogonal matrix, and determining the production process parameter latent vector of each traditional Chinese medicine production instance in the production process parameter orthogonal matrix; The inner product between the latent vectors of the production process parameters of each two traditional Chinese medicine production instances is regarded as the correlation degree between all the production process parameters of the corresponding two traditional Chinese medicine production instances; Calculate the similarity between the same production process parameters of each two traditional Chinese medicine production examples; Calculate the similarity of the evaluation information of the product of each two traditional Chinese medicine production examples; Based on the correlation between all production process parameters of every two TCM production instances, the similarity between the same production process parameters of every two TCM production instances, and the similarity between the evaluation information of the products of every two TCM production instances, the influence of each production process parameter on each evaluation dimension of the TCM products to be analyzed is analyzed; Among them, the evaluation similarity of the product evaluation information of each two traditional Chinese medicine production instances is calculated, including: Calculate the evaluation similarity between each group of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances; The average of the evaluation similarity between all groups of evaluation information of the same dimension in the product evaluation information of each two traditional Chinese medicine production instances is regarded as the evaluation similarity of the product evaluation information of each two traditional Chinese medicine production instances; Among them, based on the correlation degree between all production process parameters of every two Chinese medicine production instances, the parameter similarity between the same production process parameters of every two Chinese medicine production instances, and the evaluation similarity of the product evaluation information of every two Chinese medicine production instances, the influence of each production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed is analyzed, including: The product of the correlation degree between all production process parameters of each two traditional Chinese medicine production instances, the parameter similarity between the same production process parameters of the two traditional Chinese medicine production instances, and the evaluation similarity of the product evaluation information of the two traditional Chinese medicine production instances is used as the performance weight of the corresponding production process parameters in the two traditional Chinese medicine production instances; Based on all performance weights of all production process parameters, all major production process parameters and all minor production process parameters are screened out from all production process parameters; Perform multidimensional thermal analysis on each major production process parameter to obtain the degree of influence of each major production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, perform multidimensional thermal analysis on each minor production process parameter to obtain the degree of influence of each minor production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. Among them, a multidimensional thermal analysis is performed on each main production process parameter to obtain the influence of each main production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed. At the same time, a multidimensional thermal analysis is performed on each secondary production process parameter to obtain the influence of each secondary production process parameter on each evaluation dimension of the Chinese medicine product to be analyzed, including: Among all the TCM production instances of the type of TCM product to be analyzed, all TCM production instances with a single production process parameter as a single variable shall serve as all reference production instances with a single production process parameter corresponding to the single variable; Calculate the data span of all evaluation information of the same dimension in all reference production instances for each production process parameter; Normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the main production process parameters, and at the same time, normalize the data spans of all the same-dimensional evaluation information in all the reference production instances of all the secondary production process parameters to obtain the normalized value of each data span; The normalized value of each data span is regarded as the influence of the corresponding production process parameter on the corresponding evaluation dimension of the Chinese medicine product to be analyzed.

Images