Stress relaxation-based traditional Chinese medicine tablet disintegration characteristic classification method and system

Abstract

The invention relates to a traditional Chinese medicine tablet disintegration characteristic classification method and system based on stress relaxation. The traditional Chinese medicine tablet disintegration characteristic classification method based on stress relaxation comprises the following steps: acquiring disintegration dynamic characteristic parameters of traditional Chinese medicine tablets under stress relaxation; constructing a traditional Chinese medicine tablet disintegration characteristic data set, analyzing correlation between disintegration characteristic data and disintegration dynamic characteristic parameters from the traditional Chinese medicine tablet disintegration characteristic data set, and extracting function related attributes for representing disintegration characteristics of the traditional Chinese medicine tablets; constructing a decision tree rule based on the disintegration characteristics of the traditional Chinese medicine tablets based on the function-related attributes; and classifying traditional Chinese medicine tablet disintegration characteristics of the traditional Chinese medicine sample based on decision tree rules. The disintegration behaviors of different traditional Chinese medicine tablets can be accurately classified, technical support is provided for further prediction of disintegration behavior characteristics, and the method is of great significance to development of traditional Chinese medicine preparation prescriptions and improvement of product quality.

Description

Technical Field

[0001] The present application relates to the technical field of traditional Chinese medicine preparations, and in particular to a method and system for classifying the disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation. Background Art

[0002] Disintegration is the process by which oral solid preparations completely disintegrate, dissolve or become fragments when exposed to a liquid medium. Oral solid preparations such as tablets, capsules or pills need to go through the disintegration and release stages before being absorbed by the human body. The speed of disintegration will directly affect the absorption rate of the drug. As the first step in the bioavailability cascade, disintegration is crucial for drug dissolution, improving bioavailability and exerting reliable clinical efficacy. Elucidating the disintegration behavior of tablets and clarifying the disintegration mechanism are helpful in providing important indicators for the development, production and application of pharmaceutical preparations.

[0003] Tablets composed of chemical drugs usually rely on the addition of disintegrants to achieve disintegration. However, this result may not be fully applicable to TCM tablets. Due to the high drug loading characteristics of TCM tablets, the properties of active drug ingredients will also affect the disintegration process. In addition, the "drug-adjuvant integration" theory is a distinctive feature of TCM preparations, and some drugs in the prescription can often play the role of "drug adjuvant". Therefore, the physical and chemical properties and functional characteristics of TCM ingredients are crucial to the impact on tablet disintegration.

[0004] Currently, the technical means to evaluate the disintegration of traditional Chinese medicine tablets are relatively simple, and there is no effective classification of the disintegration characteristics of traditional Chinese medicine tablets, which hinders the rapid development of drug preparations. Summary of the invention

[0005] Based on this, it is necessary to provide a method and system for classifying the disintegration characteristics of Chinese medicine tablets based on stress relaxation in response to the problems in the related technology.

[0006] In order to achieve the above objectives, in a first aspect, the present application provides a method for classifying the disintegration characteristics of Chinese medicine tablets based on stress relaxation, the method comprising:

[0007] Obtain the disintegration kinetic characteristic parameters of Chinese medicine tablets under stress relaxation;

[0008] Constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between disintegration characteristic data and disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets;

[0009] constructing a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets based on the function-related attributes;

[0010] Based on the decision tree rules, the disintegration characteristics of Chinese medicine tablets are classified for the Chinese medicine samples.

[0011] In some embodiments, the method of obtaining the disintegration kinetic characteristic parameters of the Chinese medicine tablet under stress relaxation includes:

[0012] The disintegration kinetics behavior of the traditional Chinese medicine tablets is measured by the stress relaxation method of the texture analyzer, a curve diagram of the disintegration kinetics behavior of the traditional Chinese medicine tablets is obtained, and disintegration kinetics characteristic parameters are obtained based on the curve diagram of the disintegration kinetics behavior of the traditional Chinese medicine tablets.

[0013] In some embodiments, the method of constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between disintegration characteristic data and disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets include:

[0014] Determine the basic physical properties of the Chinese medicine powder and obtain the quality-related parameters of the Chinese medicine tablets; construct the disintegration characteristic data set of the Chinese medicine tablets based on the basic physical properties of the Chinese medicine powder and the quality-related parameters of the Chinese medicine tablets;

[0015] The correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters obtained by Pearson correlation coefficient analysis is used, and based on the correlation, disintegration characteristic parameters with correlation coefficients higher than preset values ​​are extracted as functional related attributes characterizing the disintegration characteristics of traditional Chinese medicine tablets.

[0016] In some embodiments, the decision tree rules based on the disintegration characteristics of traditional Chinese medicine tablets are constructed based on function-related attributes, including:

[0017] A single node is used as a root node, and the root node stores all Chinese medicine tablet disintegration characteristic data sets, and the Chinese medicine tablet disintegration characteristic data sets include multiple tuples;

[0018] When all tuples do not belong to the same category, the root node is split and all tuples in the root node are classified according to the value of a specific attribute, thereby generating several subsets to form several new nodes, each of which includes multiple tuples;

[0019] If all tuples in the current new node belong to the same category, the current new node does not need to be further classified and becomes a leaf node; if the current new node still has tuples that do not belong to the same category, a split operation is performed until all new nodes become leaf nodes.

[0020] In some embodiments, the classification of the disintegration characteristics of Chinese medicine tablets of Chinese medicine samples based on the decision tree rule includes:

[0021] Collecting relevant data of the traditional Chinese medicine samples;

[0022] The Chinese medicine samples are classified for their disintegration characteristics based on the relevant data of the Chinese medicine samples and the decision tree rules.

[0023] In some embodiments, before collecting the relevant data of the traditional Chinese medicine sample, the process also includes: crushing the traditional Chinese medicine sample, extracting it with water or extracting it with ethanol.

[0024] In some of the embodiments, the collected data related to the traditional Chinese medicine samples include: basic physical properties of the traditional Chinese medicine sample powder and quality evaluation parameters of the traditional Chinese medicine sample.

[0025] In a second aspect, the present application further provides a classification system for disintegration characteristics of Chinese medicine tablets based on stress relaxation, the classification system for disintegration characteristics of Chinese medicine tablets based on stress relaxation comprising:

[0026] An acquisition module is used to obtain the disintegration kinetic characteristic parameters of the traditional Chinese medicine tablets under stress relaxation;

[0027] Constructing an analysis module for constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets;

[0028] A decision tree construction module, used to construct a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets based on the function-related attributes;

[0029] The classification module is used to classify the disintegration characteristics of Chinese medicine tablets of Chinese medicine samples based on the decision tree rules.

[0030] In the above-mentioned method and system for classifying the disintegration characteristics of Chinese medicine tablets based on stress relaxation, the disintegration kinetic characteristic parameters of Chinese medicine tablets under stress relaxation are obtained; a disintegration characteristic data set of Chinese medicine tablets is constructed, and the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters is analyzed from the disintegration characteristic data set of Chinese medicine tablets, and function-related attributes for characterizing the disintegration characteristics of Chinese medicine tablets are extracted; a decision tree rule based on the disintegration characteristics of Chinese medicine tablets is constructed based on the function-related attributes; based on the decision tree rule, the disintegration characteristics of Chinese medicine tablets are classified for Chinese medicine samples; the disintegration behavior of different Chinese medicine tablets can be accurately classified, and technical support is provided for further predicting the disintegration behavior characteristics, which is of great significance for the development of Chinese medicine preparation prescriptions and the improvement of product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 This is a flow chart of a method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation provided in one embodiment of the present application;

[0033] Figure 2 The disintegration kinetics and characteristic parameters of Chinese medicine tablets in the Chinese medicine tablet disintegration characteristic classification method based on stress relaxation provided in one embodiment of the present application;

[0034] Figure 3 Function-related attribute data in the Chinese medicine tablet disintegration feature classification method based on stress relaxation provided in an embodiment of the present application;

[0035] Figure 4 Extraction and correlation analysis of function-related attributes in the classification method of disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation provided in one embodiment of the present application;

[0036] Figure 5 This is a schematic diagram of a decision tree obtained by the method for classifying disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation provided in one embodiment of the present application.

[0037] Figure 6 This is a classification effect diagram based on function-related attributes in the method for classifying disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation provided in one embodiment of the present application;

[0038] Figure 7 A decision tree rule flow chart of a method for classifying disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation provided in an embodiment of the present application;

[0039] Figure 8 This is a structural block diagram of a Chinese medicine tablet disintegration characteristic classification system based on stress relaxation provided in another embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] In one embodiment, see Figure 1The present application provides a method for classifying the disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation, and the method for classifying the disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation includes: S10 to S40.

[0042] S10: Obtain the disintegration kinetic characteristic parameters of Chinese medicine tablets under stress relaxation.

[0043] S20: constructing a disintegration characteristic data set for traditional Chinese medicine tablets, analyzing the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters from the disintegration characteristic data set for traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets.

[0044] S30: Constructing a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets based on the function-related attributes.

[0045] S40: Classifying the disintegration characteristics of Chinese medicine tablets of the Chinese medicine samples based on the decision tree rules.

[0046] In the method for classifying the disintegration characteristics of Chinese medicine tablets based on stress relaxation of the present application, the disintegration kinetic characteristic parameters of Chinese medicine tablets under stress relaxation are obtained; a disintegration characteristic data set of Chinese medicine tablets is constructed, and the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters is analyzed from the disintegration characteristic data set of Chinese medicine tablets, and function-related attributes for characterizing the disintegration characteristics of Chinese medicine tablets are extracted; a decision tree rule based on the disintegration characteristics of Chinese medicine tablets is constructed based on the function-related attributes; and based on the decision tree rule, the disintegration characteristics of Chinese medicine tablets are classified for Chinese medicine samples; the disintegration behaviors of different Chinese medicine tablets can be accurately classified, and technical support is provided for further predicting the disintegration behavior characteristics, which is of great significance for the development of Chinese medicine preparation prescriptions and the improvement of product quality.

[0047] In step S10, refer to Figure 1 In step S10, characteristic parameters of disintegration kinetics of Chinese medicine tablets under stress relaxation are obtained.

[0048] As an example, in step S10, the obtaining of the disintegration kinetic characteristic parameters of the Chinese medicine tablets under stress relaxation may include the following steps: using the stress relaxation method of a texture analyzer to determine the disintegration kinetic behavior of the Chinese medicine tablets, obtaining a curve graph of the disintegration kinetic behavior of the Chinese medicine tablets, and obtaining the disintegration kinetic characteristic parameters based on the curve graph of the disintegration kinetic behavior of the Chinese medicine tablets.

[0049] Specifically, the disintegration kinetics behavior curve of the traditional Chinese medicine tablet can be calculated according to the Macro language in the texture analyzer software to obtain the disintegration kinetics characteristic parameters.

[0050] As an example, in the process of measuring the disintegration kinetics of the Chinese medicine tablet using the stress relaxation method of the texture analyzer, the disintegration process can be recorded by a force-time curve. Stress relaxation is taken as a function of time and normalized and analyzed by Origin Pro 2023 software.

[0051] As an example, see Figure 2 , 9 disintegration kinetic characteristic parameters (for example, Fs, Fp, Dp, Tp, Te, Fe, kr, kf and AUC) can be used, among which Fs is the stress at 500s; Fp is the stress at the highest point of the rise; Dp represents the displacement at the highest point of the rise; Tp represents the time of rising to the highest point; Te represents the end time of disintegration; Fe represents the stress at the end of disintegration; kr is the expansion rate; kf is the disintegration rate; AUC represents the area under the curve. The above 9 disintegration kinetic characteristic parameters are used to characterize the expansion and disintegration characteristics of traditional Chinese medicine tablets. The characteristic parameters are obtained by the Macro macro language inside the texture analyzer software.

[0052] Specifically, Figure 2 In Figure (a), Group 1 is the stress-time curve of the disintegration kinetics of swelling type Chinese medicine tablets, Group 2 is the stress-time curve of the disintegration kinetics of disintegration type Chinese medicine tablets, and Group 3 is the stress-time curve of the disintegration kinetics of disintegration type Chinese medicine tablets; among them, the swelling type Chinese medicine in Group 1 can obtain the characteristic parameters of Fs, Fp, Dp, Tp, Te, kr, kf and AUC, the disintegration (erosion) type Chinese medicine in Group 2 can obtain the characteristic parameters of Fs, Te, kf and AUC, and the disintegration type Chinese medicine in Group 3 can obtain the characteristic parameters of Fs, Te, Fe, kf and AUC. Figure 2 Figure (b) is the stress-time curve corresponding to 9 disintegration kinetic characteristic parameters.

[0053] In step S20, refer to Figure 1 In step S20, a disintegration characteristic data set of traditional Chinese medicine tablets is constructed, the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters is analyzed from the disintegration characteristic data set of traditional Chinese medicine tablets, and the function-related attributes used to characterize the disintegration characteristics of traditional Chinese medicine tablets are extracted.

[0054] As an example, step S20 may include the following steps: S201 - S202 .

[0055] S201: Determine the basic physical properties of the Chinese medicine powder and obtain the quality-related parameters of the Chinese medicine tablets; and construct the disintegration characteristic data set of the Chinese medicine tablets based on the basic physical properties of the Chinese medicine powder and the quality-related parameters of the Chinese medicine tablets.

[0056] S202: analyzing the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters using the Pearson correlation coefficient, and extracting the disintegration characteristic parameters with correlation coefficients higher than preset values ​​based on the correlation as functional related attributes characterizing the disintegration characteristics of the traditional Chinese medicine tablets.

[0057] As an example, the basic physical properties of the Chinese medicine powder may include particle size, particle size distribution, water content and true density. The quality-related parameters of the Chinese medicine tablet may include tablet disintegration time, tensile strength, porosity and wettability.

[0058] As an example, the moisture content (MC) in the Chinese medicine powder can be measured first, and about 1.000g of the sample is placed in the aluminum pan of the infrared rapid moisture meter, and the heating temperature is set to 105°C. After the infrared rapid moisture meter prompts that the measurement is completed, the measured value of the moisture content is recorded. Each sample can be measured three times in parallel and the average value is taken.

[0059] As an example, regarding particle size and particle size distribution, D50 (particle size) and Span (particle size distribution) can be measured using the Malvern 2000 laser particle size analyzer dry Scrocco module. The measurement method can be: refractive index 1.59, vibration sampling rate 50%, measurement time 12s, dispersed air pressure 2bar. Span is obtained according to the following formula:

[0060]

[0061] Among them, D 10 is the particle size corresponding to the cumulative distribution in the system when it accounts for 10%, D 50 is the particle size corresponding to the cumulative distribution in the system when it accounts for 50%, D 90 It is the corresponding particle size when the cumulative distribution accounts for 90% in the system.

[0062] As an example, the true density of the sample can be measured using a Heliumpycnometer. The porosity of Chinese medicine powder is the ratio of the volume occupied by the pores within the particles and the pores between the particles to the total volume of the powder. The porosity ε can be obtained according to the following formula:

[0063]

[0064] Among them, ρtrue is the true density of Chinese medicine powder, ρb is the density of Chinese medicine tablets, and the formula of ρb is as follows:

[0065]

[0066] Among them, m is the mass of the Chinese medicine tablet, D is the diameter of the Chinese medicine tablet, and H is the thickness of the Chinese medicine tablet.

[0067] As an example, a Korsch XP-1 intelligent induction tablet press can be used to perform uniaxial compression experiments on different powders. The punch diameter of the tablet press is a flat circle with a diameter of 8.5 mm, the tableting speed is 10 tablets / min, the compression pressure is 30-380 MPa, and the tablet weight (i.e., the weight of the Chinese medicine tablet) is 250 mg.

[0068] As an example, the disintegration time of traditional Chinese medicine tablets can be tested according to the disintegration time test method 09216 of Part IV of the 2020 edition of the "Chinese Pharmacopoeia". Water is used as the disintegration medium, the temperature is (37±1)°C, 6 tablets are measured separately, and the average value is calculated as the disintegration time (DT) of such tablets.

[0069] As an example, tensile strength refers to the maximum load that causes a Chinese medicine tablet to break from its original cross section, also known as maximum stress or maximum tensile stress. The tensile strength σ (tensile strength, TS) of a Chinese medicine tablet is obtained according to the following formula:

[0070]

[0071] Among them, F is the hardness of the Chinese medicine tablet, the unit is N (Newton); D is the diameter of the Chinese medicine tablet, the unit is mm; H is the thickness of the Chinese medicine tablet, the unit is mm.

[0072] As an example, ultrapure water is used as the detection liquid to measure the contact angle (CA) formed between the surface of the Chinese medicine tablet and the detection liquid. When measuring the contact angle, the solution dosage and the liquid addition rate are set to 2.0μL and 0.5μL / s respectively. Record the angle formed when the detection droplet initially contacts the surface of the material. Each sample is measured three times in parallel, and the average value of the three times is the contact angle of this material. At the same time, diiodomethane is used as the second detection liquid to measure the contact angle formed between the surface of the Chinese medicine tablet and the detection liquid, and the surface free energy (SE) is calculated.

[0073] As an example, the preset value that the correlation coefficient of the function-related attribute characterizing the disintegration characteristics of the traditional Chinese medicine tablet obtained in step S202 needs to be higher than may be 0.6.

[0074] As an example, by integrating the basic physical properties of Chinese medicine powder and tablet quality-related parameters and constructing a Chinese medicine tablet disintegration characteristics dataset, such as Figure 3 shown. Figure 3 The horizontal axis represents 74 sample Chinese medicines, and the vertical axis represents the relevant parameters of the disintegration characteristic data of Chinese medicine tablets and the disintegration kinetic characteristic parameters. Figure 3 The parameters in the data have been normalized using the origin 2023 software and are Figure 3 The color depth indicates the value, the darker the color, the larger the value, and the lighter the color, the smaller the value.

[0075] The Pearson correlation coefficient was used to analyze the correlation between the above disintegration characteristic data and the disintegration kinetic characteristic parameters. The principal component analysis was used to reflect the disintegration characteristic relationship of the data set. The hierarchical clustering was used to verify the classification results of Chinese medicine under the stress relaxation method. The correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters can be found in Figure 4 . Figure 4 In it, ρtrue is the true density of Chinese medicine powder; MC is the water content of Chinese medicine powder; D50 is the particle size of Chinese medicine powder; Span is the particle size distribution of Chinese medicine powder; DT is the disintegration time, TS is the tensile strength, CA is the contact angle; SE is the surface free energy; lnFs is the logarithm of the stress at 500s; lnFp is the logarithm of the stress at the highest point of rise, lnDp is the logarithm of the displacement at the highest point of rise; lnTp is the logarithm of the time to rise to the highest point; lnTe is the logarithm of the end of disintegration time; lnFe is the logarithm of the stress at the end of disintegration; lnkr is the logarithm of the expansion rate; lnkf is the logarithm of the disintegration rate; lnAUC is the logarithm of the area under the curve. According to Figure 4 The colors in the figure show that the higher the correlation coefficient of each parameter, the stronger the correlation. Therefore, when the correlation coefficient is higher than 0.6, it means that the correlation between the two parameters is strong. Therefore, the parameters with correlation coefficients higher than 0.6 are extracted as functional related attributes to characterize the disintegration characteristics of traditional Chinese medicine tablets. In addition, the color represents a positive or negative relationship, red represents a positive correlation, and blue represents a negative correlation. Figure 4 The * in the table indicates significance.

[0076] As an example, in step S20, the contribution of the function-related attributes to the tablet disintegration is also analyzed.

[0077] As an example, the classification results of traditional Chinese medicine under the stress relaxation method can be verified through principal component analysis and hierarchical clustering, and the contribution of the functional-related attributes of traditional Chinese medicine powder properties and tablet disintegration characteristics to the tablet disintegration can be further explored to achieve the classification effect of traditional Chinese medicine preparation raw materials based on disintegration function-related attributes.

[0078] In step S30, refer to Figure 1 In step S30, a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets is constructed based on the correlation.

[0079] As an example, step S30 may include the following steps: S301 to S303.

[0080] S301: A single node is used as a root node, and the root node stores all Chinese medicine tablet disintegration characteristic data sets, and the Chinese medicine tablet disintegration characteristic data sets include multiple tuples.

[0081] S302: When all tuples do not belong to the same category, the root node is split and all tuples in the root node are classified according to the value of a specific attribute, thereby generating several subsets to form several new nodes Ni, each of which includes multiple tuples; each of the new nodes Ni represents a new data partition Dj that has been divided.

[0082] S303: If all tuples in the data partition Dj in the current new node Ni belong to the same category, the current new node does not need to be further classified and becomes a leaf node; if there are still tuples that do not belong to the same category in the data partition Dj in the current new node Ni, the splitting operation (i.e., similar to the splitting operation of the root node) is repeated until all new nodes become leaf nodes, and the classification process ends.

[0083] As an example, an example of the decision tree obtained in step S30 is as follows: Figure 5 shown.

[0084] As an example, Figure 6 (a) shows the cumulative explained variance of the functionally related attributes of the first and second principal components, (b) shows the main contribution, (c) shows the score diagram, and (d) shows the loading diagram; Figure 6 From Figure (a) in Figure 1, we can see that the first principal component (PC-1) and the first principal component (PC-2) contribute 50.5% and 18.2% to the total variance respectively. Figure 6 Figure (b) shows the contribution of each function-related attribute to the principal component; Figure 6 As shown in Figure (c), Chinese medicines with similar disintegration characteristics tend to aggregate and can be divided into three different groups; Figure 6 Figure (d) shows the overall attributes of each variable, that is, the degree of explanation between function-related attributes and Chinese medicines with different disintegration properties.

[0085] As an example, the Chinese medicine tablet disintegration feature data set may include a training sample set and a validation set. The training sample set and the validation set are used as inputs together. All records in the training sample set are put into the root node of the decision tree as a node, and it is determined whether the attributes of all samples in the root node are the same or empty. If so, it is directly set as a leaf node. If not, proceed to the next step; run each splitting method for each attribute, determine the most partitioning attribute, complete node splitting, and repeat the above steps for each new decision tree node until all internal nodes become leaf nodes.

[0086] As an example, the decision tree can also be pruned, including limiting the number of leaf nodes and setting the minimum number of samples to control the growth of the decision tree and prevent overfitting of a few samples. The path from the root node to the leaf node is extracted from the trained decision tree model as a rule, and the decision condition of each node is used as the premise of the rule, and the prediction result of the leaf node is used as the conclusion of the rule. At the same time, the rule set is further optimized by merging similar rules and deleting rules with low support or low confidence. On this basis, the decision tree knowledge rules based on the classification of the disintegration characteristics of traditional Chinese medicine tablets will be obtained.

[0087] In step S40, refer to Figure 1 In step S40, based on the decision tree rule, the Chinese medicine samples are classified into the disintegration characteristics of Chinese medicine tablets.

[0088] As an example, step S40 may include the following steps: S401 - S402 .

[0089] S401: Collect relevant data of the traditional Chinese medicine samples.

[0090] S402: Classifying the Chinese medicine tablet disintegration characteristics of the Chinese medicine sample based on the relevant data of the Chinese medicine sample and the decision tree rule.

[0091] As an example, before collecting the relevant data of the traditional Chinese medicine sample, the process may also include: crushing the traditional Chinese medicine sample, extracting it with water or extracting it with ethanol.

[0092] As an example, the Chinese medicine sample can be any unknown Chinese medicine, and its medicinal parts can include whole herbs, leaves, roots and rhizomes, barks, flowers, above-ground parts, animals, minerals, etc.; its medicinal flavors can include but are not limited to single-flavor, two-flavor and multi-flavor compound Chinese medicines.

[0093] As an example, the directly pulverized material may include directly pulverizing to obtain Chinese herbal medicine powders with different particle sizes; the ethanol extract may include a 100% ethanol solution and an ethanol solution with different concentrations mixed with different amounts of water.

[0094] As an example, the collected data related to the traditional Chinese medicine sample may include: basic physical properties of the traditional Chinese medicine sample powder and quality evaluation parameters of the traditional Chinese medicine sample.

[0095] As an example, the basic physical properties of the Chinese medicine sample powder may include: particle size, particle size distribution, true density, tap density, bulk density, angle of repose, Carr index and Hausenner ratio. The evaluation parameters of the Chinese medicine sample may include: disintegration time, tensile strength, porosity, wettability, tablet weight difference, friability and dissolution. The disintegration kinetics of Chinese medicine tablets are evaluated by stress relaxation, and classified according to the decision tree rules to obtain the classification results reflecting the disintegration characteristics of Chinese medicine tablets, see Figure 7 Through the analysis of the "Bootstrap forest method" decision tree, it can be seen that lnFp, lnTp, CA and lnTe have the highest contribution to the classification results and are the strongest predictive variables for the classification of disintegration characteristics of traditional Chinese medicine tablets. Figure 7 It can be seen that when lnFp≥3.73, the Chinese medicine tablets are classified into category 1; if lnFp<3.73, it is determined whether lnTe<6.36, then the Chinese medicine tablets are classified into category 2; if lnTe≥6.36, then the Chinese medicine tablets are classified into category 3.

[0096] In another embodiment, see Figure 8 The present application also provides a Chinese medicine tablet disintegration characteristic classification system based on stress relaxation, and the Chinese medicine tablet disintegration characteristic classification system based on stress relaxation may include: an acquisition module 10, the acquisition module 10 is used to obtain the disintegration kinetic characteristic parameters of the Chinese medicine tablet under stress relaxation; a construction and analysis module 20, the construction and analysis module 20 is used to construct a Chinese medicine tablet disintegration characteristic data set, analyze the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters from the Chinese medicine tablet disintegration characteristic data set, and extract function-related attributes for characterizing the disintegration characteristics of the Chinese medicine tablet; a decision tree construction module 30, the decision tree construction module 30 is used to construct a decision tree rule based on the disintegration characteristics of the Chinese medicine tablet based on the function-related attributes; a classification module 40, the classification module 40 is used to classify the Chinese medicine tablet disintegration characteristics of the Chinese medicine sample based on the decision tree rule.

[0097] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features of the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A classification method for disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation, characterized in that: include: Obtain the disintegration kinetic characteristic parameters of Chinese medicine tablets under stress relaxation; Constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between disintegration characteristic data and disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets; constructing a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets based on the function-related attributes; Based on the decision tree rules, the disintegration characteristics of Chinese medicine tablets are classified for the Chinese medicine samples.

2. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to claim 1, characterized in that: The method of obtaining the disintegration kinetic characteristic parameters of the traditional Chinese medicine tablet under stress relaxation comprises: The disintegration kinetics behavior of the traditional Chinese medicine tablets is measured by the stress relaxation method of the texture analyzer, a curve diagram of the disintegration kinetics behavior of the traditional Chinese medicine tablets is obtained, and disintegration kinetics characteristic parameters are obtained based on the curve diagram of the disintegration kinetics behavior of the traditional Chinese medicine tablets.

3. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to claim 1, characterized in that: The method of constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between disintegration characteristic data and disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets, includes: Determine the basic physical properties of the Chinese medicine powder and obtain the quality-related parameters of the Chinese medicine tablets; construct the disintegration characteristic data set of the Chinese medicine tablets based on the basic physical properties of the Chinese medicine powder and the quality-related parameters of the Chinese medicine tablets; The correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters obtained by Pearson correlation coefficient analysis is used, and based on the correlation, disintegration characteristic parameters with correlation coefficients higher than preset values ​​are extracted as functional related attributes characterizing the disintegration characteristics of traditional Chinese medicine tablets.

4. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to claim 1, characterized in that: The decision tree rules based on the correlation and the disintegration characteristics of the traditional Chinese medicine tablets are constructed, comprising: A single node is used as a root node, and the root node stores all Chinese medicine tablet disintegration characteristic data sets, and the Chinese medicine tablet disintegration characteristic data sets include multiple tuples; When all tuples do not belong to the same category, the root node is split and all tuples in the root node are classified according to the value of a specific attribute, thereby generating several subsets to form several new nodes, each of which includes multiple tuples; If all tuples in the current new node belong to the same category, the current new node does not need to be further classified and becomes a leaf node; if the current new node still has tuples that do not belong to the same category, a split operation is performed until all new nodes become leaf nodes.

5. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to any one of claims 1 to 4, characterized in that: The method of classifying the disintegration characteristics of Chinese medicine tablets of Chinese medicine samples based on the decision tree rule includes: Collecting relevant data of the traditional Chinese medicine samples; The Chinese medicine samples are classified for their disintegration characteristics based on the relevant data of the Chinese medicine samples and the decision tree rules.

6. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to claim 5, characterized in that: Before collecting the relevant data of the traditional Chinese medicine sample, the method also includes: crushing the traditional Chinese medicine sample, extracting it with water or ethanol.

7. The method for classifying disintegration characteristics of Chinese medicine tablets based on stress relaxation according to claim 6, characterized in that: The collected data related to the Chinese medicine samples include: basic physical properties of the Chinese medicine sample powder and quality evaluation parameters of the Chinese medicine sample.

8. A classification system for disintegration characteristics of traditional Chinese medicine tablets based on stress relaxation, characterized in that: include: An acquisition module is used to obtain the disintegration kinetic characteristic parameters of the traditional Chinese medicine tablets under stress relaxation; Constructing an analysis module for constructing a disintegration characteristic data set of traditional Chinese medicine tablets, analyzing the correlation between the disintegration characteristic data and the disintegration kinetic characteristic parameters from the disintegration characteristic data set of traditional Chinese medicine tablets, and extracting function-related attributes for characterizing the disintegration characteristics of traditional Chinese medicine tablets; A decision tree construction module, used to construct a decision tree rule based on the disintegration characteristics of traditional Chinese medicine tablets based on the function-related attributes; The classification module is used to classify the disintegration characteristics of Chinese medicine tablets of Chinese medicine samples based on the decision tree rules.

Images