Method and system for detecting total solid content of traditional Chinese medicine preparation intermediate

Abstract

The invention provides a method and a system for detecting the total solid content of a traditional Chinese medicine preparation intermediate, which solve the problems of monitoring the total solid content of the traditional Chinese medicine preparation intermediate and the like, and comprises the following steps: S1, selecting the intermediate in the production process of the traditional Chinese medicine preparation; s2, measuring the refractive indexes of different batches of intermediates; s3, measuring the total solid amount of different batches of intermediates; s4, establishing a total solid quantity prediction model by taking the refractive index of the intermediate as input and the total solid quantity of the intermediate as output; and S5, collecting the refractive index of the to-be-detected traditional Chinese medicine preparation intermediate, and calculating the total solid content of the to-be-detected traditional Chinese medicine preparation intermediate according to the established total solid content prediction model. The method has the advantages of good detection effect, high applicability and the like.

Description

Technical Field

[0001] The invention belongs to the technical field of traditional Chinese medicine reagent detection, and particularly relates to a method and system for detecting the total solid content of a traditional Chinese medicine preparation intermediate. Background Art

[0002] Intelligent manufacturing of traditional Chinese medicine is one of the important directions for the development of the traditional Chinese medicine industry. The introduction of intelligent manufacturing technology has injected new vitality into the development of the traditional Chinese medicine industry and is of great significance for improving production efficiency and product quality. In the production process of traditional Chinese medicine preparations, the quality of intermediates is directly related to the safety and effectiveness of the final preparations. The total solid content is a key indicator for the quality evaluation of liquid intermediates of traditional Chinese medicine preparations. It not only reflects the content of active ingredients in the preparations, but also is an important parameter for measuring the content of impurities. Too low total solid content may imply insufficient active ingredients, which may weaken the efficacy of the drug and affect the treatment effect of patients. On the contrary, too high total solid content may mean excessive ineffective ingredients or impurities, which will not only reduce the purity of the drug, but also increase the risk of adverse reactions. At present, many guidelines for the quality control of traditional Chinese medicine injections regard total solid content as one of the key quality attributes affecting the quality of drugs. The total solid content has also been included in the quality control standards of some traditional Chinese medicine liquid preparations and has become an important indicator for measuring drug quality. Therefore, accurately measuring and controlling the total solid content of traditional Chinese medicine preparation intermediates is of vital importance to ensure the overall quality of the preparations.

[0003] The rapid development of intelligent manufacturing of traditional Chinese medicine has put forward higher requirements for the quality monitoring of traditional Chinese medicine. Efficient quality monitoring technology is not only the key to improving production efficiency, but also an important means to ensure the stable and controllable quality of traditional Chinese medicine preparations. At present, the conventional method of detecting total solid content has certain limitations, resulting in long detection time and low analysis efficiency, which is difficult to meet the development needs of intelligent manufacturing. In recent years, with the development of science and technology, optical detection technology has gradually been applied to the quality control of traditional Chinese medicine preparations. Among them, refractive index technology has received widespread attention as a simple, fast and non-destructive detection method. The refractive index refers to the degree of deflection of light when it enters from one medium to another, which is directly related to the density of the medium. For liquids, their refractive index is closely related to the concentration of the solutes they contain, that is, the higher the concentration of the solutes in the solution, the greater its refractive index. This technology has the advantages of fast response, simplicity, non-destructiveness and high precision. At present, refractive index technology is widely used in many fields, including: in the food field, refractive index technology is used to measure the sugar content, concentration and content of other ingredients in foods such as juice, syrup, and dairy products to ensure the quality and safety of food; in the petrochemical field, refractive index technology is used to analyze the composition of oil products and control the chemical reaction process by monitoring the change of refractive index. In the field of environmental monitoring, the presence of pollutants is evaluated by measuring the refractive index in water samples. In view of the above advantages and applications in other fields, refractive index technology is expected to become an effective tool to replace traditional methods, thereby improving the automation and intelligence level of traditional Chinese medicine production.

[0004] The present invention realizes the rapid and accurate detection of the total solid content of Chinese medicine preparation intermediates by means of refractive index detection, which provides a strong guarantee for the quality control in the production process of Chinese medicine preparations. This not only improves production efficiency and reduces costs, but also provides solid technical support for the high-quality development of Chinese medicine preparations and helps the intelligent production of Chinese medicine preparations. Summary of the invention

[0005] The purpose of the present invention is to provide a method for detecting the total solid content of a Chinese medicine preparation intermediate with a reasonable design and high detection accuracy in view of the above problems.

[0006] Another object of the present invention is to provide a detection system for the total solid content of Chinese medicine preparation intermediates with good applicability in view of the above-mentioned problems.

[0007] To achieve the above object, the present invention adopts the following technical scheme: A method for detecting the total solid content of a Chinese medicine preparation intermediate comprises the following steps:

[0008] S1: Select intermediates in the production process of traditional Chinese medicine preparations;

[0009] S2: Determine the refractive index of different batches of intermediates;

[0010] S3: Determine the total solid content of different batches of intermediates;

[0011] S4: Taking the refractive index of the intermediate as input and the total solid content of the intermediate as output, a total solid content prediction model is established;

[0012] S5: Collect the refractive index of the intermediate of the Chinese medicine preparation to be tested, and calculate the total solid content of the intermediate of the Chinese medicine preparation to be tested according to the established total solid content prediction model.

[0013] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, the Chinese medicine preparation production process includes extraction, concentration and liquid preparation steps.

[0014] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, the Chinese medicine preparation intermediate includes a liquid obtained by extraction, a liquid obtained by concentration, and a liquid obtained by preparation.

[0015] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, step S2 comprises the following steps:

[0016] S21: Shake the sample bottle containing the intermediate to ensure that the intermediate sample is fully mixed;

[0017] S22: Calibrate the Abbe refractometer according to the instructions to ensure that the instrument is in normal working condition;

[0018] S23: Adjust the temperature of the Abbe refractometer to within the range of 20°C ± 0.5°C;

[0019] S24: After the temperature of the intermediate is stabilized within the range of 20℃±0.5℃, drop it on the auxiliary prism position of the Abbe refractometer, adjust the intersection point in the field of view to coincide with the light-dark dividing line, and read the indication as the refractive index.

[0020] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, step S3 comprises the following steps:

[0021] S31: weigh the fixed mass intermediate into a weighing bottle X0 with a constant mass, and weigh the mass X1;

[0022] S32: Place the weighing bottle containing the intermediate in an oven and dry it at 105°C to a constant mass. Weigh the mass X2. The solid content formula is as follows:

[0023] Solid content = (X2-X0) / (X1-X0).

[0024] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, step S4 comprises the following steps:

[0025] S41: performing regression analysis on the total solid content of the sample and the corresponding refractive index to establish a prediction model of refractive index-total solid content;

[0026] S42: Calculate the determination coefficient of the refractive index-total solid content prediction model. When the determination coefficient is greater than 0.8, it is determined that the refractive index X significantly predicts the total solid content Y.

[0027] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, step S41 comprises the following steps:

[0028] S411: performing data preprocessing on the total solid content of the intermediate and the corresponding refractive index to remove abnormal values ​​and erroneous data;

[0029] S412: Divide the intermediate samples of different batches into a training set and a test set, and ensure that the total solid content range of the training set samples can include the total solid content range of the test set samples;

[0030] S413: performing fuzzy clustering on the total solid content and relative density of all the test samples in the training set and the test set, dividing them into different categories, and calculating them using fuzzy membership functions respectively;

[0031] S414: clustering is performed according to the calculation results, and a prediction model is established for each cluster using a univariate linear regression algorithm to determine the relationship between the total solid content and the refractive index;

[0032] S415: According to the properties of the intermediates of the Chinese medicine preparations in the test set, the total solid content of the intermediates is predicted using a prediction model built using samples with similar properties to obtain a prediction result of the total solid content.

[0033] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, step S414 comprises the following steps:

[0034] S416: Select refractive index as input parameter and total solid content as output parameter;

[0035] S417: using a simple linear regression algorithm to establish a total solids regression prediction model for the input parameter refractive index and the output parameter total solids;

[0036] S418: training the training samples using a prediction model based on a simple linear regression algorithm, where the model can be expressed as: Y=aX+b, where Y is the total solid content of the intermediate, X is the refractive index of the intermediate, a is the regression coefficient of the model, and b is a constant term determined based on the intermediate data;

[0037] S419: Validate the prediction model.

[0038] In the above-mentioned method for detecting the total solid content of a Chinese medicine preparation intermediate, the method for verifying the prediction model in step S419 is to calculate the mean square error MSE, mean absolute error MAE and determination coefficient R2 of the intermediates in the test set, and verify the performance of the prediction model according to the evaluation rules; the method for verifying the performance of the prediction model can also be to compare the prediction results of other regression analysis models.

[0039] A detection system for the total solid content of a Chinese medicine preparation intermediate adopts the above-mentioned detection method for the total solid content of a Chinese medicine preparation intermediate.

[0040] Compared with the existing technology, the advantages of the present invention are: establishing a total solids prediction model, and based on the established total solids prediction model, quickly obtaining the total solids of the Chinese medicine preparation intermediate to be tested, thereby accelerating the production speed, reducing the production cost of the enterprise, and ensuring the stability and continuity of the production process; predicting the total solids of the intermediate through the model, and comparing it with the actual total solids of the intermediate, and combining the prediction relative error, verifying the accuracy of the total solids prediction formula in detecting the total solids; the established prediction model is trained for different Chinese medicine intermediates and has good applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the method of the present invention.

[0042] Figure 2 1 is a correlation diagram between the refractive index and the total solid content in Example 1 of the present invention.

[0043] Figure 3 3 is a correlation diagram between the refractive index and the total solid content of Example 2 of the present invention.

[0044] Figure 4 3 is a correlation diagram between the refractive index and the total solid content in Example 2 of the present invention. DETAILED DESCRIPTION

[0045] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] like Figure 1-4 As shown, a method for detecting the total solid content of a Chinese medicine preparation intermediate comprises the following steps:

[0047] S1: Select intermediates in the production process of traditional Chinese medicine preparations;

[0048] S2: Determine the refractive index of different batches of intermediates. Since the refractive index is usually linearly positively correlated with the organic content in the solution when the temperature is constant, but the refractive index decreases with increasing temperature, the measurement is performed at a constant temperature;

[0049] S3: Determine the total solid content of different batches of intermediates. This step adopts the conventional drying and weighing method;

[0050] S4: Taking the refractive index of the intermediate as input and the total solid content of the intermediate as output, a total solid content prediction model is established;

[0051] S5: Collect the refractive index of the intermediate of the Chinese medicine preparation to be tested, and calculate the total solid content of the intermediate of the Chinese medicine preparation to be tested according to the established total solid content prediction model.

[0052] Specifically, the production process of Chinese medicine preparations includes extraction, concentration and liquid preparation steps.

[0053] In depth, the intermediates of Chinese medicine preparations include liquid obtained by extraction, liquid obtained by concentration and liquid obtained by preparation.

[0054] Further, step S2 includes the following steps:

[0055] S21: Shake the sample bottle containing the intermediate to ensure that the intermediate sample is fully mixed;

[0056] S22: Calibrate the Abbe refractometer according to the instructions to ensure that the instrument is in normal working condition;

[0057] S33: After the temperature of the intermediate is stabilized within the range of 20℃±0.5℃, drop it on the auxiliary prism position of the Abbe refractometer, adjust the intersection point in the field of view to coincide with the light-dark dividing line, and read the indication as the refractive index.

[0058] Furthermore, step S3 includes the following steps:

[0059] S31: weigh the fixed mass intermediate into a weighing bottle X0 with a constant mass, and weigh the mass X1;

[0060] S32: Place the weighing bottle containing the intermediate in an oven and dry it at 105°C to a constant mass. Weigh the mass X2. The total solid content is calculated as follows:

[0061] Total solids = (X2-X0) / (X1-X0).

[0062] In addition, step S4 includes the following steps:

[0063] S41: performing regression analysis on the total solid content of the sample and the corresponding refractive index to establish a prediction model of refractive index-total solid content;

[0064] S42: Calculate the determination coefficient of the refractive index-total solid content prediction model. When the determination coefficient is greater than 0.8, it is determined that the refractive index X significantly predicts the total solid content Y.

[0065] Meanwhile, step S41 includes the following steps:

[0066] S411: performing data preprocessing on the total solid content and the corresponding refractive index of the sample to remove abnormal values ​​and erroneous data;

[0067] S412: Divide the intermediate samples of different batches into training sets and test sets, and ensure that the total solid content range of the training set samples can include the total solid content range of the test set samples;

[0068] S413: Perform fuzzy clustering on the total solid content and refractive index of all the test samples in the training set and the test set, divide them into different categories, and use fuzzy membership functions to calculate them respectively. Specifically, all sample records R = {r1, r2, ..., r n}; Initial cluster center C = {c1, c2, ..., c k}; number of clusters K; fuzzy index m; iteration threshold ε; finally output K clusters and sample fuzzy membership matrix;

[0069] First calculate the initial fuzzy membership:

[0070]

[0071] Then calculate the cluster centers and update the fuzzy membership matrix:

[0072]

[0073] Finally, calculate the objective function:

[0074]

[0075] Until |J i -J i-1 |<ε terminate;

[0076] S414: clustering is performed according to the calculation results, and a prediction model is established for each cluster using a simple linear regression algorithm to determine the relationship between the total solid content and the refractive index;

[0077] S415: According to the properties of the intermediates of the Chinese medicine preparations in the test set, a prediction model constructed by samples with similar properties is used to predict the total solid content of the intermediates to obtain a prediction result of the total solid content.

[0078] It can be seen that step S414 includes the following steps:

[0079] S416: Select refractive index as input parameter and total solid content as output parameter;

[0080] S417: using a simple linear regression algorithm to establish a total solids regression prediction model for the input parameter refractive index and the output parameter total solids;

[0081] S418: Using a prediction model based on a simple linear regression algorithm to train the training samples, the model can be expressed as: Y = aX + b, where Y is the total solid content of the intermediate, X is the refractive index of the intermediate, a is the regression coefficient of the model, and b is a constant term determined based on the intermediate data; according to the data set {y i , x i1 , x i2 , …, x im} Find the variable y i and variable x ij The regression coefficient a and constant term b are calculated for each cluster.

[0082] First, calculate the regression coefficient a:

[0083]

[0084] Next, calculate the constant term b:

[0085]

[0086] Finally, a regression prediction model is established:

[0087] Y=a·X+b

[0088] S419: Validate the prediction model.

[0089] Regression analysis uses mean square error (MSE), mean absolute error (MAE) and determination coefficient (R2) to evaluate the model:

[0090]

[0091]

[0092] Among them, the smaller the mean square error (MSE) and the mean absolute error (MAE), the higher the prediction accuracy of the model; the closer the determination coefficient (R2) is to 1, the higher the fit of the regression equation.

[0093] Obviously, the verification method of the prediction model in step S419 is to calculate the mean square error MSE, mean absolute error MAE and determination coefficient R2 of the intermediate of the test set, and verify the performance of the prediction model according to the evaluation rules; the method for verifying the performance of the prediction model can also be to compare the prediction results of other regression analysis models, and other regression analysis models include ridge regression, least squares method, weighted least squares method and other methods.

[0094] A detection system for the total solid content of a Chinese medicine preparation intermediate adopts the above-mentioned detection method for the total solid content of a Chinese medicine preparation intermediate.

[0095] Embodiment 1

[0096] This example is a study on the detection of the total solid content of the honeysuckle concentrate of Reduning Injection based on the refractive index.

[0097] This implementation case collects the refractive index and total solid content of 64 samples of Reduning Injection Honeysuckle Concentrate, establishes a total solid content prediction formula based on the refractive index, and realizes quantitative prediction of the total solid content of the concentrate. The specific steps are as follows:

[0098] 1. Sample Collection

[0099] In the production process of honeysuckle concentration for Reduning Injection, samples were taken every 15 minutes from the beginning to the end of the concentration of the extract until the concentration was completed. A total of 64 samples from 4 batches were collected in this study.

[0100] 2. Total solid content and refractive index determination

[0101] Using the weight method, accurately weigh 5.0g of the sample to be tested into a weighing bottle X0 with a constant mass, weigh the mass X1, place it in an oven, dry it at 105°C to a constant mass, and weigh the mass X2. The total solid content is calculated according to the formula:

[0102] Total solids = (X2-X0) / (X1-X0).

[0103] Stabilize the sample temperature at about 20°C, calibrate the instrument with purified water, then drop 3 drops of the sample to be tested at the measuring position, adjust the intersection point in the field of view to coincide with the light-dark dividing line, and read the indication as the refractive index.

[0104] 3. Refractive index model establishment

[0105] The total solid content and the corresponding refractive index of 50 batches of samples were regressed and the regression equation of refractive index-total solid content was established. The results are shown in Table 1 and Figure 2 From the results, we can see that equation R 2 All of them are greater than 0.9, and the fitting degree is high, which shows that there is a good correlation between the refractive index and the solid content, suggesting that the refractive index can be used to predict the total solid content.

[0106] Table 1 Regression equation of refractive index and total solid content

[0107]

[0108] 4. Model Validation

[0109] 14 batches of samples to be tested were introduced into the refractive index-total solid content prediction formula to predict the total solid content of the 14 batches of samples to be tested, and the predicted values ​​were compared with the reference values. As a result, the average relative prediction errors of the total solid content of the 14 batches of samples were 1.57%, which was less than 5%, indicating that the refractive index model can predict the total solid content of the samples with high prediction accuracy.

[0110] Embodiment 2

[0111] The present embodiment is based on the refractive index of the reduning injection honeysuckle extract total solid content of the research

[0112] This implementation case collects the refractive index and total solid content of 82 samples of Reduning Injection Honeysuckle Extract, establishes a correlation model between the refractive index and the total solid content, and realizes quantitative prediction of the total solid content of the extract. The specific steps are as follows:

[0113] 1. Sample Collection

[0114] In the production process of honeysuckle extraction for Reduning Injection, samples were taken every 3 minutes from the beginning to the end of the extraction of medicinal materials. A total of 82 samples from 3 batches were collected in this study.

[0115] 2. Total solid content and refractive index determination

[0116] 3. Refractive index model establishment

[0117] The total solid content of 65 batches of samples was regressed against the corresponding refractive index to establish a regression equation for refractive index-total solid content. The results are shown in Table 2 and Figure 3 From the results, we can see that equation R 2 It is greater than 0.9, and the fitting degree is high, which shows that the refractive index and solid content have a good correlation, suggesting that the refractive index can be used to predict the total solid content.

[0118] Table 2 Regression equation of refractive index and total solid content

[0119]

[0120] 4. Model Validation

[0121] 17 batches of samples to be tested were introduced into the total solid content prediction formula to predict the total solid content of the samples, and the predicted values ​​were compared with the reference values. The results showed that the average relative prediction error of the 17 batches of samples was 8.24%, which was less than 10%, indicating that the refractive index method can predict the total solid content of the samples with high prediction accuracy.

[0122] Embodiment 3

[0123] This example is based on the refractive index of the detection of the total solid content of the intermediates in the preparation process of Jinzhen oral liquid

[0124] This implementation case collects the refractive index and total solid content of 35 samples of intermediates in the preparation process of Jinzhen oral liquid, establishes a correlation model between the refractive index and the total solid content, and realizes quantitative prediction of the total solid content of the intermediates in the preparation process. The specific steps are as follows:

[0125] 1. Sample Collection

[0126] 35 batches of samples from the Jinzhen oral liquid preparation process were collected.

[0127] 2. Total solid content and refractive index determination

[0128] 3. Refractive index model establishment

[0129] The total solid content of 27 batches of samples was regressed against the corresponding refractive index to establish a regression equation for refractive index-total solid content. The results are shown in Table 3 and Figure 4 From the results, we can see that equation R 2 It is greater than 0.9, and the fitting degree is high, which shows that the refractive index and solid content have a good correlation, suggesting that the refractive index can be used to predict the total solid content.

[0130] Table 2 Regression equation of refractive index and total solid content

[0131]

[0132]

[0133] 4. Model Validation

[0134] Eight batches of samples to be tested were introduced into the refractive index-total solid content prediction formula to predict the total solid content of the samples, and the predicted values ​​were compared with the reference values. The results showed that the average relative error of the eight batches of samples was 3.20%, which was less than 5%, indicating that the refractive index method can predict the total solid content of the samples with high prediction accuracy.

[0135] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

[0136] Although the terms such as total solids and refractive index are used more frequently in this article, the possibility of using other terms is not excluded. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional restrictions is contrary to the spirit of the present invention.

Claims

1. A method for detecting the total solid content of a Chinese medicine preparation intermediate, characterized in that: The steps include: S1: Select intermediates in the production process of traditional Chinese medicine preparations; S2: Determine the refractive index of different batches of intermediates; S3: Determine the total solid content of different batches of intermediates; S4: Taking the refractive index of the intermediate as input and the total solid content of the intermediate as output, a total solid content prediction model is established; S5: Collect the refractive index of the intermediate of the Chinese medicine preparation to be tested, and calculate the total solid content of the intermediate of the Chinese medicine preparation to be tested according to the established total solid content prediction model.

2. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 1, characterized in that: The production process of the traditional Chinese medicine preparation includes extraction, concentration and liquid preparation processes.

3. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 1, characterized in that: The intermediate of the traditional Chinese medicine preparation includes the liquid obtained by extraction, the liquid obtained by concentration and the liquid obtained by preparation.

4. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 1, characterized in that: The step S2 comprises the following steps: S21: Shake the sample bottle containing the intermediate to ensure that the intermediate sample is fully mixed; S22: Calibrate the Abbe refractometer according to the instructions to ensure that the instrument is in normal working condition; S23: Adjust the temperature of the Abbe refractometer to within the range of 20°C ± 0.5°C; S24: After the temperature of the intermediate is stabilized within the range of 20℃±0.5℃, drop it on the auxiliary prism position of the Abbe refractometer, adjust the intersection point in the field of view to coincide with the light-dark dividing line, and read the indication as the refractive index.

5. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 4, characterized in that: The step S3 comprises the following steps: S31: weigh the fixed mass intermediate into a weighing bottle X0 with a constant mass, and weigh the mass X1; S32: Place the weighing bottle containing the intermediate in an oven and dry it at 105°C to a constant mass. Weigh the mass X2. The total solid content is calculated as follows: Total solids = (X2-X0) / (X1-X0).

6. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 5, characterized in that: The step S4 comprises the following steps: S41: performing regression analysis on the total solid content of the sample and the corresponding refractive index to establish a prediction model of refractive index-total solid content; S42: Calculate the determination coefficient of the refractive index-total solid content prediction model. When the determination coefficient is greater than 0.8, it is determined that the refractive index X significantly predicts the total solid content Y.

7. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 6, characterized in that: The step S41 comprises the following steps: S411: performing data preprocessing on the total solid content and the corresponding refractive index of the sample to remove abnormal values ​​and erroneous data; S412: Divide the intermediate samples of different batches into a training set and a test set, and ensure that the total solid content range of the training set samples can include the total solid content range of the test set samples; S413: performing fuzzy clustering on the total solid content and refractive index of all the test samples in the training set and the test set, dividing them into different categories, and performing calculations using fuzzy membership functions respectively; S414: clustering is performed according to the calculation results, and a prediction model is established for each cluster using a simple linear regression algorithm to determine the relationship between the total solid content and the refractive index; S415: According to the properties of the intermediates of the Chinese medicine preparations in the test set, the total solid content of the intermediates is predicted using a prediction model built using samples with similar properties to obtain a prediction result of the total solid content.

8. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 7, characterized in that: The step S414 includes the following steps: S416: Select refractive index as input parameter and total solid content as output parameter; S417: using a simple linear regression algorithm to establish a total solids regression prediction model for the input parameter refractive index and the output parameter total solids; S418: using a total solid content prediction model based on a simple linear regression algorithm to train the training samples, the model can be expressed as: Y = aX + b, where Y is the total solid content of the intermediate, X is the refractive index of the intermediate, a is the regression coefficient of the model, and b is a constant term determined based on the intermediate data; S419: Validate the prediction model.

9. The method for detecting the total solid content of a Chinese medicine preparation intermediate according to claim 8, characterized in that: The method for verifying the prediction model in step S419 is to calculate the mean square error MSE, mean absolute error MAE and determination coefficient R2 of the test set intermediate, and verify the performance of the prediction model according to the evaluation rules; the method for verifying the performance of the prediction model can also be to compare the prediction results of other regression analysis models.

10. A detection system for the total solid content of a Chinese medicine preparation intermediate, characterized in that: The method for detecting the total solid content of the Chinese medicine preparation intermediate described in any one of claims 1 to 9 is adopted.

Images