A method and system for optimizing the frying process of Chinese herbal medicine slices

Abstract

The present application relates to the technical field of Chinese herbal medicine slices, and provides a method and system for optimizing the frying process of Chinese herbal medicine slices. Based on the frying process database, P process parameter ranges of P kinds of frying process parameters of Chinese herbal medicine slices are obtained, P correlation information between the P kinds of frying process parameters and the quality of Chinese herbal medicine slices after frying is obtained, P adjustment range information for optimizing the P kinds of frying process parameters is obtained, and multiple adjustment methods are generated by random combination, and multiple adjustment methods are adopted based on the adjustment optimization constraint conditions to adjust the P kinds of frying process parameters in the frying process to optimize and obtain the optimal frying process. The technical problem that the control accuracy of the frying process of Chinese herbal medicine slices in the prior art is low, resulting in poor stability of the properties of the produced Chinese herbal medicine slices is solved, and the technical effect of improving the process control accuracy of the frying of Chinese herbal medicine slices, improving the stability of the properties of the produced Chinese herbal medicine slices, and reducing the loss of Chinese herbal medicine raw materials is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of Chinese herbal medicine slices, and in particular to an optimization method and system for the frying process of Chinese herbal medicine slices. Background Art

[0002] Chinese herbal medicine slices are an important form of Chinese medicine preparations, widely used in the field of clinical Chinese medicine and drug research and development. The quality and efficacy of Chinese herbal medicine slices are strictly controlled by the frying process. At present, the production of Chinese herbal medicine slices has been automated, but the key process control such as frying temperature and frying time still relies on manual labor, resulting in low frying precision control of Chinese herbal medicine slices, which affects the stability of the properties and consistency of efficacy of Chinese herbal medicine slices.

[0003] The frying process of Chinese herbal medicine slices is a complex process involving the combined effects of multiple factors. The traditional Chinese medicine frying process mainly relies on experience and manual control, lacking repeatability and precision. In order to solve this problem, modern Chinese herbal medicine slice production uses automated frying equipment. These devices can realize automatic control of key parameters such as frying temperature and frying time, improving the accuracy and stability of frying. However, in actual applications, these automated devices still need to be set and controlled manually, so there are still certain errors and uncertainties.

[0004] In summary, the existing technology has the technical problem that the frying precision of Chinese herbal medicine slices is low, resulting in poor stability of the properties of the produced Chinese herbal medicine slices. Summary of the invention

[0005] Based on this, it is necessary to provide an optimization method and system for the frying process of Chinese herbal medicine slices, which can improve the process control accuracy during the frying of Chinese herbal medicine slices, improve the stability of the properties of the produced Chinese herbal medicine slices, and reduce the loss of Chinese herbal raw materials in response to the above technical problems.

[0006] A method for optimizing a frying process for Chinese herbal medicine slices, the method comprising: obtaining a target Chinese medicine category for a target Chinese herbal medicine slice to be fried; inputting the target Chinese medicine category into a pre-constructed frying process database for selection, and obtaining a target frying process for the target Chinese herbal medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges; analyzing the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine slice after frying, and obtaining P pieces of correlation information; inputting the P pieces of correlation information into a process parameter adjustment amplitude standard, and obtaining P pieces of adjustment amplitude information for optimizing the P pieces of frying process parameters; randomly selecting and combining the P pieces of adjustment amplitude information, obtaining a plurality of adjustment methods, and obtaining constraint conditions for adjusting and optimizing the target frying process; based on the constraint conditions, using the plurality of adjustment methods to optimize the P kinds of frying process parameters in the target frying process, obtaining an optimal target frying process, and frying the target Chinese herbal medicine slice.

[0007] A system for optimizing the frying process of Chinese herbal medicine slices, the system comprising: a Chinese herbal medicine category acquisition module, used to acquire the target Chinese herbal medicine category of the target Chinese herbal medicine slice to be fried; a frying process acquisition module, used to input the target Chinese herbal medicine category into a pre-constructed frying process database for selection, and acquire the target frying process of the target Chinese herbal medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges; an information association analysis module, used to analyze the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine slice after frying, and obtain P pieces of correlation information; an optimization module, used to obtain the target Chinese herbal medicine category; a frying process acquisition module, used to input the target Chinese herbal medicine category into a pre-constructed frying process database for selection, and acquire the target frying process of the target Chinese herbal medicine slice; An adjustment execution module is used to input the P pieces of correlation information into the process parameter adjustment range standard, and obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters; a constraint condition acquisition module is used to randomly select and combine the P pieces of adjustment range information, obtain multiple adjustment methods, and obtain constraint conditions for adjusting and optimizing the target frying process; a Chinese herbal medicine frying module is used to adjust and optimize the P kinds of frying process parameters in the target frying process based on the constraint conditions and using the multiple adjustment methods to obtain the optimal target frying process and fry the target Chinese herbal medicine pieces.

[0008] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0009] Obtain the target Chinese medicine category of the target Chinese medicine pieces to be fried;

[0010] Input the target Chinese medicine category into a pre-built frying process database for selection, and obtain the target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges;

[0011] Analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying to obtain P pieces of correlation information;

[0012] Input the P pieces of correlation information into the process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters;

[0013] Randomly select and combine the P adjustment amplitude information to obtain multiple adjustment methods, and obtain constraint conditions for adjusting and optimizing the target frying process;

[0014] Based on the constraints, the multiple adjustment methods are used to adjust and optimize the P types of frying process parameters in the target frying process, obtain the optimal target frying process, and fry the target Chinese herbal medicine slices.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0016] Obtain the target Chinese medicine category of the target Chinese medicine pieces to be fried;

[0017] Input the target Chinese medicine category into a pre-built frying process database for selection, and obtain the target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges;

[0018] Analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying to obtain P pieces of correlation information;

[0019] Input the P pieces of correlation information into the process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters;

[0020] Randomly select and combine the P adjustment amplitude information to obtain multiple adjustment methods, and obtain constraint conditions for adjusting and optimizing the target frying process;

[0021] Based on the constraints, the multiple adjustment methods are used to adjust and optimize the P types of frying process parameters in the target frying process, obtain the optimal target frying process, and fry the target Chinese herbal medicine slices.

[0022] The above-mentioned method and system for optimizing the frying process of Chinese herbal medicine slices solves the technical problem in the prior art that the frying precision control of Chinese herbal medicine slices is low, resulting in poor stability of the properties of the produced Chinese herbal medicine slices, and achieves the technical effect of improving the process control precision during the frying of Chinese herbal medicine slices, improving the stability of the properties of the produced Chinese herbal medicine slices, and reducing the loss of Chinese herbal raw materials.

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of an optimization method for a frying process of Chinese herbal medicine slices in one embodiment;

[0025] Figure 2 A schematic diagram of a process for obtaining a target frying process in a method for optimizing a frying process for Chinese herbal medicine pieces in one embodiment;

[0026] Figure 3 It is a structural block diagram of an optimization system for a frying process of Chinese herbal medicine slices in one embodiment;

[0027] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0028] Explanation of the accompanying drawings: Chinese medicine category acquisition module 1, frying process acquisition module 2, information association analysis module 3, optimization and adjustment execution module 4, constraint condition acquisition module 5, Chinese medicine decoction piece frying module 6. DETAILED DESCRIPTION

[0029] 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.

[0030] like Figure 1 As shown, the present application provides a method for optimizing the frying process of Chinese herbal medicine slices, the method comprising:

[0031] S100: Obtain the target Chinese medicine category of the target Chinese medicine pieces to be fried;

[0032] Specifically, it should be understood that the whole plant or its parts, tissues, secretions, metabolites, etc. of the medicinal plant are processed through picking, sun-drying and frying to complete the preparation of Chinese medicine slices. Compared with picking and drying, frying is an important step in processing medicinal plants into Chinese medicine slices, and the frying process determines the quality of the finished Chinese medicine slices.

[0033] In this embodiment, the target Chinese medicine slices are products directly used for preparation or formulation after the target Chinese medicine is subjected to a frying process. The target Chinese medicine category is the standard name of the target Chinese medicine in traditional Chinese medicine, which has a unique directionality. For example, the target Chinese medicine category is ginseng, astragalus, wolfberry, angelica, and chuanxiong. This embodiment provides a retrieval benchmark for subsequent acquisition of standard frying processes by obtaining the target Chinese medicine category.

[0034] S200: inputting the target Chinese medicine category into a pre-constructed frying process database for selection, and obtaining a target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges;

[0035] In one embodiment, Figure 2 As shown, the target Chinese medicine category is input into a pre-built frying process database for selection to obtain the target frying process of the target Chinese medicine slices. The method step S200 provided in the present application also includes:

[0036] S210: Obtain multiple sample Chinese medicine categories and multiple frying processes;

[0037] S220: constructing a plurality of index elements using the plurality of sample Chinese medicine categories as indexes;

[0038] S230: constructing a plurality of data elements using the plurality of frying processes as data, and combining the plurality of index elements to construct the frying process database;

[0039] S240: Input the target Chinese medicine category into the frying process database for indexing to obtain the target frying process.

[0040] Specifically, in this embodiment, the target frying process is a set of frying process control parameters for frying the medicinal plants of the target Chinese medicine category into Chinese medicine pieces whose properties meet the requirements of the "Chinese Medicine Piece Processing Specifications" issued and implemented, and the target frying process includes P frying process parameters (where P is a positive integer greater than 2). Each of the P frying process parameters is a value range, so the P frying process parameters correspond to P process parameter ranges.

[0041] Exemplarily, the target frying process P is 3, and the P frying process parameters are respectively frying time parameter, the process parameter range is 27±3min; frying temperature parameter, the process parameter range is [160,180]℃; frying auxiliary material type-dosage parameter, the process parameter range is [0.08,0.12]kg of bran per 1kg of clean medicinal material.

[0042] When frying the target Chinese herbal medicine slices based on the clean medicinal materials of the target Chinese herbal medicine category, the frying parameters are controlled to be within the range of each frying process parameter in the target frying process, which can theoretically ensure that the target Chinese herbal medicine slices obtained by frying are qualified products.

[0043] In order to ensure the credibility of the target frying process obtained, this embodiment constructs the frying process database based on the frying process database and the target frying process of the target Chinese herbal medicine slices. The construction method of the frying process database is as follows:

[0044] It should be understood that when different types of Chinese medicine raw materials are fried and processed to produce Chinese medicine slices, there are differences in the frying time, frying temperature and added frying auxiliary materials (stove core soil, loess, red ochre), that is, the parameters of the frying process are different.

[0045] Therefore, in this embodiment, any one sample Chinese medicine category is randomly selected from a plurality of sample Chinese medicine categories as the first sample Chinese medicine category. Referring to the currently issued and implemented "Specifications for the Preparation of Chinese Medicine Pieces", the first frying qualified property requirements of the sample Chinese medicine pieces produced by frying of the first sample Chinese medicine category are obtained, and based on the first frying qualified property requirements, multiple rounds of frying tests of the Chinese medicine pieces of the first sample pharmaceutical category are performed to obtain the maximum and minimum values ​​of the frying time when the qualified property requirements are produced, the maximum and minimum values ​​of the frying temperature, the frying auxiliary material type, and the maximum and minimum values ​​of the amount of net medicinal material auxiliary materials added per unit mass of the first sample Chinese medicine category.

[0046] The frying time process parameter range is constructed based on the maximum and minimum values ​​of the frying time, the frying temperature process parameter range is constructed based on the maximum and minimum values ​​of the frying temperature, and the frying auxiliary material process parameter range is constructed based on the frying auxiliary material type and the maximum and minimum values ​​of the net medicinal material auxiliary material addition amount per unit mass of the first sample Chinese medicine category. The frying time process parameter range, the frying temperature process parameter range, and the frying auxiliary material process parameter range are combined to generate the frying process of the first sample Chinese medicine category.

[0047] The same method as the frying process of the first sample Chinese medicine category is adopted to obtain multiple sample Chinese medicine categories and multiple frying processes. The multiple sample Chinese medicine categories are used as indexes to construct multiple index elements, and the multiple index elements correspond to the multiple sample Chinese medicine categories; the multiple frying processes are used as data to construct multiple data elements, and the multiple data elements correspond to the multiple frying processes.

[0048] The frying process database is constructed by connecting multiple index elements and multiple data elements, wherein the frying process database has multiple index element-data elements. The target Chinese medicine category is input into the frying process database for indexing, an index of a sample Chinese medicine category corresponding to the target Chinese medicine category is obtained, and the data element of the sample Chinese medicine category index is called to obtain a corresponding frying process as the target frying process.

[0049] This embodiment constructs a frying process database, so that when the target Chinese medicine category is known, the range of frying process parameter values ​​for producing Chinese herbal medicine slices with qualified properties of the target Chinese medicine category can be obtained, so as to determine the optimal target frying process for subsequent optimization, narrow the optimization range of process parameters, and indirectly achieve the technical effect of improving the optimization efficiency of obtaining the optimal target frying process.

[0050] S300: Analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying, and obtain P pieces of correlation information;

[0051] In one embodiment, the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying is analyzed to obtain P pieces of correlation information. The method step S300 provided in the present application also includes:

[0052] S310: According to the process parameters and frying results of frying the target Chinese herbal medicine slices using the target frying process in the past, a plurality of historical process parameter sets, a plurality of frying smell results, a plurality of slice images and a plurality of effective component content information are obtained;

[0053] S320: inputting the multiple frying smell results, the multiple slice images and the multiple active ingredient content information into the frying quality analysis model of the target Chinese herbal slices to obtain multiple frying quality analysis results;

[0054] S330: Dividing the plurality of historical process parameter sets according to the P types of frying process parameters to obtain P process parameter sets;

[0055] S340: According to the P process parameter sets and the multiple frying quality analysis results, analyze the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine pieces after frying, and obtain P pieces of correlation information.

[0056] In one embodiment, according to the P process parameter sets and the multiple frying quality analysis results, the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine pieces after frying is analyzed to obtain P pieces of correlation information. The method step S340 provided in the present application also includes:

[0057] S341: Arrange the P process parameter sets and the multiple frying quality analysis results, and normalize the data in the arrangement to obtain P process parameter sequences and frying quality sequences;

[0058] S342: Calculate the correlation coefficients of the P process parameter sequences and the frying quality sequences to obtain P sets of correlation coefficients, using the following formula:

[0059]

[0060]

[0061]

[0062] in, is the influence correlation coefficient of the jth data in the i-th process parameter sequence and the frying quality sequence, ρ is the adjustable calculation coefficient, is the absolute difference between the jth data in the i-th process parameter sequence and the frying quality sequence, is the minimum difference between the absolute difference of the jth data in the ith process parameter sequence and the frying quality sequence. is the maximum difference between the absolute difference of the jth data in the i-th process parameter sequence and the frying quality sequence;

[0063] S343: Calculate and obtain the P pieces of association degree information based on the P sets of association coefficients.

[0064] In one embodiment, the multiple frying smell results, multiple slice images and multiple active ingredient content information are input into the frying quality analysis model of the target Chinese herbal slices to obtain multiple frying quality analysis results. The method step S320 provided in the present application also includes:

[0065] S321: Obtaining a sample stir-frying smell result set, a sample slice image set, and a sample active ingredient content information set of the target Chinese herbal medicine slices;

[0066] S322: constructing a scoring standard for the frying smell based on the sample frying smell result set, and constructing a scoring standard for the effective ingredient content based on the sample effective ingredient content information set;

[0067] S323: According to the sample decoction piece image set, score the decoction piece images to obtain a sample image score set, and use the sample decoction piece image set as construction data to construct a stir-frying image quality analysis unit based on a convolutional neural network;

[0068] S324: Combining the frying smell scoring standard, the frying image quality analysis unit and the effective ingredient content scoring standard, obtaining the frying quality analysis model;

[0069] S325: Input the multiple frying smell results, multiple medicinal material images and multiple effective ingredient content information into the frying quality analysis model respectively, obtain multiple frying smell scores, multiple image scores and multiple effective ingredient content scores, and combine and add them respectively to obtain multiple comprehensive scores as the multiple frying quality analysis results.

[0070] Specifically, in this embodiment, the Chinese herbal medicine processing factory sets multiple historical process parameter sets based on the subjective judgment and experience of the staff during historical time to perform frying processing of the target Chinese herbal medicine.

[0071] Based on the quality control inspection data and production logs of Chinese herbal medicines in the Chinese herbal medicine processing factory, multiple groups of frying time, temperature, and auxiliary material addition amount set by multiple historical process parameter sets in the past period are obtained, and the process parameters and frying results of the target Chinese herbal medicines are fried, and multiple historical process parameter sets with mapping relationships, multiple frying odor results, multiple herbal medicine images and multiple effective ingredient content information are obtained.

[0072] Each of the historical process parameter sets includes P process parameter values, and the multiple historical process parameter sets are non-repetitive. The multiple pieces of medicine images are target Chinese herbal medicine pieces product images obtained by image acquisition under the same ambient light after the target Chinese herbal medicine pieces are processed using multiple historical process parameter sets.

[0073] Obtain the effective ingredient composition standard of the target Chinese herbal medicine slices, for example, the effective ingredients of the standard Angelica dahurica Chinese herbal medicine slices include furanocoumarins, white angelicae, and angelica ether. After the target Chinese herbal medicine slices are processed using multiple historical process parameter sets, the effective ingredient content is detected according to the effective ingredient composition of the qualified target Chinese herbal medicine slices to obtain the multiple effective ingredient content information, each of which consists of multiple effective ingredients and their content data.

[0074] The frying smell result is composed of the burnt aroma level and the inherent aroma level of the target Chinese medicine. The method for determining the aroma level in this embodiment is to draw four concentric circles with radii of 10cm, 50cm, 100cm, and 200cm with the target medicinal material as the center. The four concentric circles correspond to four aroma levels, and the closer the concentric circles are to the center, the lower the aroma level.

[0075] When the target Chinese herbal medicine slices are fried and cooled, they are placed at the center of the circle. If the Chinese herbal medicine slice quality inspector has normal sense of smell and has not experienced olfactory adaptation, he can smell the burnt aroma of the target Chinese herbal medicine slices in the 70cm concentric circle and the inherent aroma of the target Chinese herbal medicine slices in the 30cm concentric circle, then the frying odor result is burnt aroma level 4 and the target Chinese herbal medicine inherent aroma level 2. The above-mentioned aroma level determination method is used to obtain multiple frying odor results of multiple target Chinese herbal medicine slices after the target Chinese herbal medicine slices are processed using multiple historical process parameter sets.

[0076] Construct the stir-frying quality analysis model for scoring the stir-frying quality of target Chinese herbal medicine slices, specifically,

[0077] A sample stir-fry smell result set, a sample slice image set, and a sample effective component content information set of the target Chinese herbal medicine slices are obtained, and multiple sets of sample stir-fry smell results-sample slice images-sample effective component content information corresponding to multiple sample Chinese herbal medicine slices can be extracted based on the sample stir-fry smell result set, the sample slice image set, and the sample effective component content information set. It should be noted that the multiple sample Chinese herbal medicine slices here are samples of the target Chinese herbal medicine slices, and the sample stir-fry smell result and the stir-fry smell result have the same meaning.

[0078] Based on the pharmacopoeia, the burnt aroma and inherent aroma of high-quality target Chinese herbal medicines are obtained, and the aroma grade determination method of this embodiment is used to obtain the burnt aroma grade and inherent aroma grade of high-quality target Chinese herbal medicines. Calculate the deviation percentage between the burnt aroma grade of the sample frying odor result and the burnt aroma grade of the high-quality target Chinese herbal medicines, calculate the deviation percentage between the inherent aroma grade of the sample frying odor result and the inherent aroma grade of the high-quality target Chinese herbal medicines, add the two deviation percentages as the subtrahend, and use 1 as the minuend to calculate the sample frying odor score of the sample frying odor result. The above content is the frying odor scoring standard.

[0079] Based on the pharmacopoeia, the content information of multiple active ingredients of high-quality target Chinese herbal medicines is obtained, and the multiple deviation percentages of the multiple active ingredient contents in the sample active ingredient content information and the multiple active ingredient contents of high-quality target Chinese herbal medicines are calculated one by one, and the multiple deviation percentages are added as the subtrahend, and 1 is used as the minuend to calculate the sample active ingredient score. The above is the active ingredient content scoring standard;

[0080] Based on the fact that multiple experts in the field of traditional Chinese medicine perform a herbal medicine image scoring on each sample herbal medicine image in the sample herbal medicine image set, the image score value range is [0,1], and multiple scoring results for each sample herbal medicine image are obtained and further average calculation is performed to eliminate the influence of expert subjective factors on the objectivity of the scoring, and the average score of each sample herbal medicine image is obtained to form the sample image scoring set, and the sample image scoring set is composed of multiple sample herbal medicine images-sample image scores.

[0081] A stir-fried image quality analysis unit is constructed based on a convolutional neural network, wherein the input data of the stir-fried image quality analysis unit is a stir-fried herbal slice image, and the output result is a stir-fried herbal slice image score. The sample image score set is divided into a training set, a test set, and a validation set, and the stir-fried image quality analysis unit is trained and tested based on the training set and the test set, and the stir-fried image quality analysis unit output accuracy is verified based on the validation set. When the stir-fried image quality analysis unit output accuracy is higher than 97%, the training of the stir-fried image quality analysis unit is stopped.

[0082] An odor scoring calculation unit is constructed based on the stir-frying odor scoring standard, and an effective ingredient scoring calculation unit is constructed based on the effective ingredient content scoring standard. Combined with the stir-frying image quality analysis unit, the construction of the stir-frying quality analysis model is completed. The stir-frying quality analysis model includes an input layer, a data processing layer, and an output layer. In the data processing layer, the effective ingredient scoring calculation unit, the odor scoring calculation unit, and the stir-frying image quality analysis unit are set in parallel.

[0083] The multiple stir-frying smell results, multiple medicinal slice images and multiple effective ingredient content information are input into the stir-frying quality analysis model to obtain multiple stir-frying smell scores, multiple image scores and multiple effective ingredient content scores, and according to the mapping relationship between multiple historical process parameter sets, multiple stir-frying smell results, multiple medicinal slice images and multiple effective ingredient content information, they are combined and added respectively to obtain multiple comprehensive scores as the multiple stir-frying quality analysis results of multiple target Chinese medicinal slices obtained based on multiple historical process parameter sets.

[0084] Furthermore, in the present embodiment, each of the historical process parameter sets includes P process parameter values ​​(for example, the P process parameter values ​​are: historical frying time process parameters, historical frying temperature process parameters, and historical frying auxiliary material process parameters), and thus the multiple historical process parameter sets are divided according to the P types of frying process parameters to obtain P process parameter sets. Exemplarily, the P process parameter sets may be composed of a historical frying time process parameter set, a historical frying temperature process parameter set, and a frying auxiliary material process parameter set, and the data indicators in each process parameter set are consistent.

[0085] According to the correspondence between the plurality of historical process parameter sets and the plurality of stir-fry quality analysis results, and the data recording time of the plurality of historical process parameter sets, the P process parameter sets and the plurality of stir-fry quality analysis results are arranged, and in the obtained P+1 sequences, the data of the same sequence in each sequence corresponds to a set of historical process parameter sets and stir-fry quality analysis results. Unit normalization processing is performed on the data in each sequence of the arrangement result, and the data unit is removed to obtain P process parameter sequences and stir-fry quality sequences.

[0086] Based on the grey correlation analysis method, a correlation coefficient calculation formula is constructed, and the correlation coefficients of the P process parameter sequences and the frying quality sequence are calculated by the following calculation formula:

[0087]

[0088]

[0089]

[0090] In the correlation coefficient calculation formula, is the influence correlation coefficient between the ith process parameter sequence and the jth data in the frying quality sequence in P process parameter sequences, and there are a total of P process parameter sequences. ρ is an adjustable calculation coefficient. In this embodiment, ρ is preferably 0.5.

[0091] is the absolute difference between the jth data in the i-th process parameter sequence and the frying quality sequence, is the minimum difference between the absolute difference of the jth data in the ith process parameter sequence and the frying quality sequence. It is the maximum difference between the absolute difference of the jth data in the i-th process parameter sequence and the frying quality sequence.

[0092] The data at the same sequence position in the P process parameter sequences and the frying quality sequence are substituted into the correlation coefficient calculation formula one by one, and P correlation coefficient sets corresponding to the P process parameter sequences are obtained by calculation.

[0093] The mean value of the correlation coefficient is calculated for each of the P correlation coefficient sets to obtain P correlation degree means as the P correlation degree information.

[0094] The P correlation information represent the correlation between the P process parameters and the target Chinese herbal medicine frying quality analysis results. The larger the correlation information value is, the greater the impact of the corresponding process parameters on the frying quality of the target Chinese herbal medicine when the target Chinese herbal medicine is frying.

[0095] This embodiment achieves the technical effect of scientifically and accurately knowing the influence of P process parameters on the frying quality of target Chinese herbal medicine slices by obtaining P correlation information of P process parameters in the frying process steps. At the same time, it provides a reference for subsequent optimization to determine the optimal target frying process and set the adjustment range of the optimization parameters, thereby indirectly achieving the technical effect of improving the optimization efficiency of obtaining the optimal target frying process.

[0096] S400: inputting the P pieces of correlation information into a process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters;

[0097] In one embodiment, the P pieces of correlation information are input into the process parameter adjustment range standard, and the method step S400 provided in the present application further includes:

[0098] S410: Obtaining a sample association information set;

[0099] S420: constructing a plurality of adjustment range information according to the sample association degree information set, and constructing and obtaining the process parameter adjustment range standard;

[0100] S430: Input the P pieces of correlation information into the process parameter adjustment range standard to obtain the P pieces of adjustment range information.

[0101] Specifically, in this embodiment, a plurality of different types of Chinese herbal medicines are randomly selected as multiple sample Chinese herbal medicines, and the same method of obtaining P pieces of correlation information of the target Chinese herbal medicines is adopted to obtain multiple sample correlation information of the frying process parameters of the multiple sample Chinese herbal medicines to constitute the sample correlation information set.

[0102] According to the multiple sample correlation information in the sample correlation information set, based on the work experience of the Chinese medicine preparation production staff, the adjustment ranges of the process parameters corresponding to the multiple sample correlation information are set one by one, and the multiple adjustment range information is constructed and obtained. The adjustment range is the parameter value change range when the process parameter is adjusted, for example, the adjustment range of the frying time process parameter is 5%. Among them, the larger the correlation information, the greater the influence of the process parameter on the frying quality of Chinese medicine pieces, and the smaller the corresponding adjustment range information, so as to accurately adjust the process parameter and improve the frying quality, and vice versa.

[0103] Based on the multiple sample correlation information and the corresponding multiple adjustment amplitude information in the sample correlation information set, a process parameter adjustment amplitude standard is constructed, wherein the process parameter adjustment amplitude standard includes a mapping relationship between correlation information of different sizes and different adjustment amplitude information.

[0104] The P pieces of correlation information are input into the process parameter adjustment range standard, and the closest or identical P pieces of sample correlation information within the process parameter adjustment range standard are obtained, and then the corresponding P pieces of adjustment range information are obtained. The P pieces of adjustment range information are references for adjusting the parameter values ​​of the P process control parameters when optimizing the target Chinese herbal medicine slices in this embodiment. This embodiment obtains the P pieces of adjustment range information, reduces the adjustment range for the frying process parameters with a large correlation, thereby performing fine adjustments and improving the frying quality, and increases the adjustment range for the frying process parameters with a small correlation, reducing unnecessary adjustment costs, thereby reducing the difficulty of optimizing the value changes in optimizing the optimal target frying process, thereby improving the optimization efficiency of optimizing the optimal target frying process.

[0105] S500: randomly selecting and combining the P pieces of adjustment amplitude information to obtain multiple adjustment methods, and obtaining constraint conditions for adjusting and optimizing the target frying process;

[0106] Specifically, in this embodiment, the P adjustment amplitude information are randomly selected and combined, for example, one adjustment amplitude information is randomly selected, and the remaining process control parameters are unchanged as one adjustment method, and P adjustment methods are obtained; two adjustment amplitude information combinations are randomly selected, and the remaining process control parameters are unchanged as one adjustment method, and P (P-1) / 2 adjustment methods are obtained. And so on, different numbers and different adjustment amplitude information are randomly selected to form the multiple adjustment methods.

[0107] The constraint condition is a preset number of iterations constraint for stopping the optimization for adjusting and optimizing the target frying process in advance.

[0108] S600: Based on the constraints, the multiple adjustment methods are used to adjust and optimize the P types of frying process parameters in the target frying process, obtain the optimal target frying process, and fry the target Chinese herbal medicine slices.

[0109] In one embodiment, the constraint condition includes adjusting within the range of the P process parameters. Based on the constraint condition, the P kinds of frying process parameters in the target frying process are adjusted and optimized by using the multiple adjustment methods. The method step S600 provided in the present application also includes:

[0110] S610: taking the current P kinds of frying process parameters in the target frying process as a first process parameter set;

[0111] S620: trial frying the target Chinese herbal medicine slices using the first process parameter set, and obtaining a first frying quality analysis result through the frying quality analysis model;

[0112] S630: Using the multiple adjustment methods, adjust the first process parameter set to obtain multiple adjusted process parameter sets;

[0113] S640: Obtaining a plurality of adjusted frying quality analysis results of the plurality of adjusted process parameter sets through the frying quality analysis model;

[0114] S650: taking the maximum value among the plurality of adjusted frying quality analysis results as the second adjusted frying quality analysis result, taking the corresponding adjusted process parameter set as the second process parameter set, and adding the adjustment method for obtaining the second process parameter set into the taboo table, which cannot be used in the taboo iteration number;

[0115] S660: Use a non-prohibited adjustment method to adjust the second process parameter set, perform iterative optimization, and until a preset number of iterations is reached, output the process parameter set with the maximum frying quality analysis result in the optimization process to obtain the optimal target frying process.

[0116] Specifically, based on step S200, it can be known that in this embodiment, the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges.

[0117] The current P frying process parameters in the target frying process are used as the first process parameter set; the target Chinese herbal medicine slices are trial-fried using the first process parameter set, and the first frying quality analysis result is obtained through the frying quality analysis model in the aforementioned content.

[0118] The first process parameter set is adjusted using several adjustment methods among the multiple adjustment methods to obtain multiple adjustment process parameter sets, and the multiple adjustment process parameter sets are traversed based on the P process parameter ranges, and the adjustment process parameter sets whose process parameters do not satisfy the P process parameter ranges are eliminated.

[0119] Through the stir-fry quality analysis model, multiple adjusted stir-fry quality analysis results of the multiple adjusted process parameter sets are obtained. The maximum value among the multiple adjusted stir-fry quality analysis results is used as the second adjusted stir-fry quality analysis result, and the corresponding adjusted process parameter set is used as the second process parameter set, and the adjustment method for adjusting the second process parameter set is added to the taboo table. The adjustment method cannot be used in the taboo iteration number to avoid falling into the local optimum. After the iterative optimization reaches the taboo iteration number, the adjustment method is deleted from the taboo table. Exemplarily, the taboo iteration number can be 3 or 5 times.

[0120] The second process parameter set is adjusted using a non-prohibited adjustment method to obtain multiple adjustment process parameter sets, and the multiple adjustment process parameter sets are traversed based on the P process parameter ranges to eliminate the adjustment process parameter sets whose process parameters do not satisfy the P process parameter ranges.

[0121] Through the frying quality analysis model, a plurality of adjusted frying quality analysis results of the plurality of adjusted process parameter sets are obtained. The maximum value among the plurality of adjusted frying quality analysis results is used as a third adjusted frying quality analysis result, and the corresponding adjusted process parameter set is used as a third process parameter set, and the adjustment method for obtaining the third process parameter set is added to a taboo table.

[0122] The third process parameter set is adjusted by using an adjustment method that is not prohibited, and the above process is repeatedly generated to perform iterative optimization. Based on step S500, a preset number of iterations constraint for stopping optimization is obtained in the constraint condition. It is determined whether the current iteration reaches the preset number of iterations. If so, the optimization iteration is stopped, and multiple frying quality analysis results obtained by multiple rounds of optimization are sorted to obtain a process parameter set output corresponding to the maximum frying quality analysis result in the optimization process, and the P process parameters of the process parameter set are used as the optimal target frying process.

[0123] This embodiment achieves the technical effects of improving the process control accuracy and scientificity of the control during the frying of Chinese herbal medicine slices, improving the stability of the properties of the produced Chinese herbal medicine slices, and reducing the loss of Chinese herbal medicine raw materials.

[0124] In one embodiment, Figure 3 As shown, a system for optimizing the frying process of Chinese herbal medicine pieces is provided, comprising: a Chinese herbal medicine category acquisition module 1, a frying process acquisition module 2, an information association analysis module 3, an optimization adjustment execution module 4, a constraint condition acquisition module 5, and a Chinese herbal medicine piece frying module 6, wherein:

[0125] The Chinese medicine category acquisition module 1 is used to acquire the target Chinese medicine category of the target Chinese medicine pieces to be fried;

[0126] A frying process acquisition module 2 is used to input the target Chinese medicine category into a pre-built frying process database for selection, and obtain a target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges;

[0127] The information association analysis module 3 is used to analyze the association between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying, and obtain P pieces of association information;

[0128] The optimization and adjustment execution module 4 is used to input the P pieces of correlation information into the process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters;

[0129] A constraint condition acquisition module 5 is used to randomly select and combine the P adjustment range information to obtain multiple adjustment methods and obtain constraint conditions for adjusting and optimizing the target frying process;

[0130] The Chinese herbal medicine slice frying module 6 is used to adjust and optimize the P frying process parameters in the target frying process based on the constraint conditions and adopt the multiple adjustment methods to obtain the optimal target frying process and fry the target Chinese herbal medicine slices.

[0131] In one embodiment, the system further comprises:

[0132] A sample information acquisition unit is used to acquire multiple sample Chinese medicine categories and multiple frying processes;

[0133] An index element construction unit, used to construct a plurality of index elements using the plurality of sample Chinese medicine categories as indexes;

[0134] A database construction unit, used to construct a plurality of data elements using the plurality of frying processes as data, and to construct the frying process database in combination with the plurality of index elements;

[0135] The frying process indexing unit is used to input the target Chinese medicine category into the frying process database for indexing to obtain the target frying process.

[0136] In one embodiment, the system further comprises:

[0137] A historical data acquisition unit, for obtaining a plurality of historical process parameter sets, a plurality of frying odor results, a plurality of slice images and a plurality of effective component content information according to the process parameters and frying results of frying the target Chinese herbal medicine slices using the target frying process in the past time;

[0138] A frying quality analysis unit, used for inputting the plurality of frying smell results, the plurality of slice images and the plurality of effective component content information into the frying quality analysis model of the target Chinese herbal slices to obtain a plurality of frying quality analysis results;

[0139] A process parameter division unit, configured to divide the plurality of historical process parameter sets according to the P types of frying process parameters to obtain P process parameter sets;

[0140] The correlation obtaining unit is used to analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying according to the P process parameter sets and the multiple frying quality analysis results, and obtain P pieces of correlation information.

[0141] In one embodiment, the system further comprises:

[0142] An analysis result arrangement unit, used for arranging the P process parameter sets and the multiple frying quality analysis results, and normalizing the data in the arrangement to obtain P process parameter sequences and a frying quality sequence;

[0143] The correlation coefficient calculation unit is used to calculate the correlation coefficients of the P process parameter sequences and the frying quality sequence, and obtain P sets of correlation coefficients, through the following formula:

[0144]

[0145]

[0146]

[0147] in, is the influence correlation coefficient of the jth data in the i-th process parameter sequence and the frying quality sequence, ρ is the adjustable calculation coefficient, is the absolute difference between the jth data in the i-th process parameter sequence and the frying quality sequence, is the minimum difference between the absolute difference of the jth data in the ith process parameter sequence and the frying quality sequence. is the maximum difference between the absolute difference of the jth data in the i-th process parameter sequence and the frying quality sequence;

[0148] The association degree obtaining unit is used to calculate and obtain the P association degree information according to the P association coefficient sets.

[0149] In one embodiment, the system further comprises:

[0150] A sample set acquisition unit, used to acquire a sample stir-frying smell result set, a sample piece image set and a sample effective ingredient content information set of the target Chinese herbal medicine pieces;

[0151] A scoring standard construction unit, used to construct a scoring standard for the frying smell based on the sample frying smell result set, and to construct a scoring standard for the effective ingredient content based on the sample effective ingredient content information set;

[0152] A decoction piece image analysis unit is used to score the decoction piece images according to the sample decoction piece image set, obtain a sample image score set, and construct a stir-frying image quality analysis unit based on a convolutional neural network in combination with the sample decoction piece image set as construction data;

[0153] An analysis model building unit, used to obtain the stir-fry quality analysis model by combining the stir-fry smell scoring standard, the stir-fry image quality analysis unit and the effective ingredient content scoring standard;

[0154] The analysis result obtaining unit is used to input the multiple stir-frying odor results, multiple medicinal material images and multiple effective ingredient content information into the stir-frying quality analysis model respectively, obtain multiple stir-frying odor scores, multiple image scores and multiple effective ingredient content scores, and combine and add them respectively to obtain multiple comprehensive scores as the multiple stir-frying quality analysis results.

[0155] In one embodiment, the system further comprises:

[0156] A sample correlation obtaining unit, used to obtain a sample correlation information set;

[0157] An adjustment standard construction unit, used to construct a plurality of adjustment range information according to the sample correlation information set, and to construct and obtain the process parameter adjustment range standard;

[0158] The adjustment range obtaining unit is used to input the P pieces of correlation degree information into the process parameter adjustment range standard to obtain the P pieces of adjustment range information.

[0159] In one embodiment, the system further comprises:

[0160] A process parameter setting unit, configured to use the current P types of frying process parameters in the target frying process as a first process parameter set;

[0161] An analysis result output unit, used to test-fry the target Chinese herbal medicine slices using the first process parameter set, and obtain a first frying quality analysis result through the frying quality analysis model;

[0162] A process parameter adjustment unit, configured to adjust the first process parameter set by using the multiple adjustment methods to obtain multiple adjusted process parameter sets;

[0163] An analysis result generating unit, used for obtaining a plurality of adjusted frying quality analysis results of the plurality of adjusted process parameter sets through the frying quality analysis model;

[0164] a taboo iteration execution unit, configured to use the maximum value among the plurality of adjusted frying quality analysis results as the second adjusted frying quality analysis result, use the corresponding adjusted process parameter set as the second process parameter set, and add the adjustment method for obtaining the second process parameter set into a taboo table, which cannot be used in the taboo iteration number;

[0165] The target process output unit is used to adjust the second process parameter set by adopting a non-prohibited adjustment method, perform iterative optimization, and output the process parameter set with the maximum frying quality analysis result in the optimization process to obtain the optimal target frying process.

[0166] For a specific embodiment of an optimization system for a frying process of Chinese herbal medicine slices, please refer to the embodiment of an optimization method for a frying process of Chinese herbal medicine slices mentioned above, which will not be repeated here. Each module in the above-mentioned optimization system for a frying process of Chinese herbal medicine slices can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0167] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time decay factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for optimizing the frying process of Chinese herbal medicine slices is implemented.

[0168] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0169] In one embodiment, a computer-readable storage medium is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining a target Chinese medicine category of a target Chinese medicine piece to be fried; inputting the target Chinese medicine category into a pre-constructed frying process database for selection, and obtaining a target frying process of the target Chinese medicine piece, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges; analyzing the P frying process parameters and the frying process of the target Chinese medicine piece; The correlation degree of the post-processing quality is obtained to obtain P pieces of correlation degree information; the P pieces of correlation degree information are input into the process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters; the P pieces of adjustment range information are randomly selected and combined to obtain a variety of adjustment methods, and the constraint conditions for adjusting and optimizing the target frying process are obtained; based on the constraint conditions, the multiple adjustment methods are adopted to optimize the P kinds of frying process parameters in the target frying process, the optimal target frying process is obtained, and the target Chinese herbal medicine is fried.

[0170] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0171] The above-mentioned 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 invention patent. 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 of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing the frying process of Chinese herbal medicine slices, characterized in that: The method comprises: Obtain the target Chinese medicine category of the target Chinese medicine pieces to be fried; Input the target Chinese medicine category into a pre-built frying process database for selection, and obtain the target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges; Analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying to obtain P pieces of correlation information; Input the P pieces of correlation information into the process parameter adjustment range standard to obtain P pieces of adjustment range information for optimizing the P kinds of frying process parameters; Randomly select and combine the P adjustment amplitude information to obtain multiple adjustment methods, and obtain constraint conditions for adjusting and optimizing the target frying process; Based on the constraint conditions, the P kinds of frying process parameters in the target frying process are adjusted and optimized by using the multiple adjustment methods to obtain the optimal target frying process, and the target Chinese herbal medicine pieces are fried; Analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying, and obtain P pieces of correlation information, including: According to the process parameters and frying results of frying the target Chinese herbal medicine slices using the target frying process in the past, multiple historical process parameter sets, multiple frying odor results, multiple slice images and multiple active ingredient content information are obtained; Inputting the plurality of stir-frying smell results, the plurality of slice images and the plurality of effective component content information into the stir-frying quality analysis model of the target Chinese herbal slices to obtain a plurality of stir-frying quality analysis results; According to the P kinds of frying process parameters, the multiple historical process parameter sets are divided to obtain P process parameter sets; According to the P process parameter sets and the multiple frying quality analysis results, analyzing the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine slices after frying, and obtaining P pieces of correlation information; According to the P process parameter sets and the multiple frying quality analysis results, the correlation between the P frying process parameters and the quality of the target Chinese herbal medicine slices after frying is analyzed to obtain P pieces of correlation information, including: Arranging the P process parameter sets and the multiple frying quality analysis results, and normalizing the data in the arrangement to obtain P process parameter sequences and a frying quality sequence; Calculate the correlation coefficients of the P process parameter sequences and the frying quality sequence to obtain P sets of correlation coefficients, using the following formula: M=min min|x i (j)-y(j)| N max max|x i (j)-y(j)| Among them, K i (j) is the influence correlation coefficient of the jth data in the i-th process parameter sequence and the frying quality sequence, ρ is the adjustable calculation coefficient, |x i (j)-y(j)| is the absolute difference between the jth data in the i-th process parameter sequence and the frying quality sequence, min min|x i (j)-y(j)| is the minimum difference between the absolute difference of the jth data in the i-th process parameter sequence and the frying quality sequence, max max|x i (j)-y(j)| is the maximum difference between the absolute difference of the jth data in the i-th process parameter sequence and the frying quality sequence; Calculating and obtaining the P pieces of association degree information according to the P association coefficient sets; The multiple frying smell results, multiple pieces of decoction images and multiple pieces of effective ingredient content information are input into the frying quality analysis model of the target Chinese herbal medicine pieces to obtain multiple frying quality analysis results, including: Obtaining a sample stir-frying smell result set, a sample slice image set, and a sample effective ingredient content information set of the target Chinese herbal medicine slices; Based on the sample stir-frying smell result set, a stir-frying smell scoring standard is constructed, and based on the sample effective ingredient content information set, an effective ingredient content scoring standard is constructed; According to the sample decoction piece image set, the decoction piece image is scored to obtain a sample image scoring set, and the sample decoction piece image set is used as construction data to construct a stir-frying image quality analysis unit based on a convolutional neural network; The stir-frying quality analysis model is obtained by combining the stir-frying smell scoring standard, the stir-frying image quality analysis unit and the effective ingredient content scoring standard; Inputting the multiple stir-frying smell results, multiple slice images and multiple effective ingredient content information into the stir-frying quality analysis model respectively, obtaining multiple stir-frying smell scores, multiple image scores and multiple effective ingredient content scores, and combining and adding them respectively to obtain multiple comprehensive scores as the multiple stir-frying quality analysis results; The constraint condition includes adjusting within the range of the P process parameters. Based on the constraint condition, the P kinds of frying process parameters in the target frying process are adjusted and optimized by using the multiple adjustment methods, including: Using the current P kinds of frying process parameters in the target frying process as a first process parameter set; Using the first process parameter set to test-fry the target Chinese herbal medicine slices, and obtaining a first frying quality analysis result through the frying quality analysis model; Using the multiple adjustment methods, adjusting the first process parameter set to obtain multiple adjusted process parameter sets; Obtaining a plurality of adjusted frying quality analysis results of the plurality of adjusted process parameter sets through the frying quality analysis model; The maximum value among the plurality of adjusted frying quality analysis results is used as the second adjusted frying quality analysis result, and the corresponding adjusted process parameter set is used as the second process parameter set, and the adjustment method for obtaining the second process parameter set is added to the taboo table, which cannot be used in the taboo iteration number; The second process parameter set is adjusted by an unprohibited adjustment method, and iterative optimization is performed until a preset number of iterations is reached. The process parameter set with the maximum frying quality analysis result in the optimization process is output to obtain the optimal target frying process.

2. The method according to claim 1, characterized in that Inputting the target Chinese medicine category into a pre-built frying process database for selection, and obtaining the target frying process of the target Chinese medicine slices, including: Obtain multiple sample categories of Chinese medicine and a variety of frying techniques; Using the multiple sample Chinese medicine categories as indexes, constructing multiple index elements; Taking the multiple frying processes as data, constructing multiple data elements, and combining the multiple index elements to construct the frying process database; The target Chinese medicine category is input into the frying process database for indexing to obtain the target frying process.

3. The method according to claim 1, characterized in that Inputting the P pieces of correlation information into the process parameter adjustment range standard includes: Get sample correlation information set; Constructing a plurality of adjustment range information according to the sample correlation information set, and constructing a process parameter adjustment range standard; The P pieces of correlation information are input into the process parameter adjustment range standard to obtain the P pieces of adjustment range information.

4. A system for optimizing the frying process of Chinese herbal medicine slices, characterized in that: The system is used to execute the method according to any one of claims 1 to 3, and the system comprises: A Chinese medicine category acquisition module is used to acquire the target Chinese medicine category of the target Chinese medicine pieces to be fried; A frying process acquisition module is used to input the target Chinese medicine category into a pre-built frying process database for selection, and obtain a target frying process of the target Chinese medicine slice, wherein the target frying process includes P frying process parameters, and the P frying process parameters include P process parameter ranges; An information correlation analysis module is used to analyze the correlation between the P kinds of frying process parameters and the quality of the target Chinese herbal medicine slices after frying, and obtain P pieces of correlation information; An optimization and adjustment execution module, used for inputting the P pieces of correlation information into a process parameter adjustment range standard, and obtaining P pieces of adjustment range information for optimizing the P kinds of frying process parameters; A constraint condition acquisition module, used to randomly select and combine the P adjustment range information to obtain multiple adjustment methods and obtain constraint conditions for adjusting and optimizing the target frying process; The Chinese herbal medicine slice frying module is used to adjust and optimize the P frying process parameters in the target frying process based on the constraints and adopt the multiple adjustment methods to obtain the optimal target frying process and fry the target Chinese herbal medicine slices.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images