A method for preparing des and its use in extract of paeonia lactiflora pall

Abstract

The application discloses a DES preparation method and application thereof in paeony extract, and relates to the technical field of chemical processes.The DES preparation method comprises the following steps: glycerol and betaine are configured in advance, the configured glycerol and betaine are placed in a container, and distilled water configured in advance is added into the container to be mixed with the glycerol and betaine; the container after mixing is placed in an oil bath to be heated, and the mixture in the container is stirred.The application ensures that the deep eutectic solvent has suitable chemical properties and dissolving capacity by accurately configuring the proportion of glycerol and betaine and adding an appropriate amount of distilled water, and creates conditions for efficient antioxidant component extraction.The DPPH free radical scavenging experiment on the DES can actually evaluate the free radical scavenging capacity of the DES.

Description

Technical Field

[0001] The present invention relates to the field of chemical process technology, and in particular to a method for preparing DES and application thereof in peony extract. Background Art

[0002] Deep eutectic solvent (DES) is a new type of green solvent. It is a low eutectic mixture formed by hydrogen bonding after hydrogen bond donors (such as alcohols, acids, amines, etc.) and hydrogen bond acceptors (such as halides, urea, thiourea, etc.) are mixed in a certain proportion. The melting point of a deep eutectic solvent is usually lower than the melting point of its components. This is because the intermolecular interactions in the mixture (such as hydrogen bonds) lead to a lower energy state. This low melting point property is particularly important because it allows DES to effectively dissolve and stabilize various organic compounds, including potential antioxidants, at lower temperatures. These properties make DES show excellent efficiency in extracting plant antioxidant components, such as bioactive substances in peony. For example, when using DES as a solvent for peony extraction, components with high antioxidant activity can be more effectively extracted under milder conditions, and these active components show efficient scavenging ability against DPPH free radicals.

[0003] In the existing technology, it is not easy to obtain images of deep eutectic solvents and identify their composition characteristics through advanced image processing and classification algorithms. Therefore, it is not easy to understand the complex composition of DES, and it is not easy to optimize and adjust their composition to obtain the best antioxidant performance by comparing different deep eutectic solvent images. At the same time, it is not easy to conduct in-depth analysis of the identified deep eutectic solvent composition characteristics, and therefore it is impossible to ensure that each batch of deep eutectic solvents meets high quality requirements, especially in their application as antioxidant solvents.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related art, the present invention proposes a method for preparing DES and its application in peony extract to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] According to one aspect of the present invention, a method for preparing DES is provided, comprising the following steps:

[0008] S1. Pre-prepare glycerol and betaine, place the prepared glycerol and betaine in a container, and add pre-prepared distilled water into the container to mix with the glycerol and betaine;

[0009] S2, placing the mixed container in an oil bath, heating it, and stirring the mixture in the container;

[0010] S3. After stirring is completed, observe the changes in the appearance of the mixture. If a uniform and transparent liquid is formed, the deep eutectic solvent is prepared. Samples are taken for free radical scavenging experiments to verify its effect.

[0011] S4. Acquire a deep eutectic solvent image, and preprocess the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image;

[0012] S5. Comparing the obtained deep eutectic solvent characteristic image with characteristic images of various deep eutectic solvents in a database through an image classification algorithm to identify the composition characteristics of the deep eutectic solvent;

[0013] S6. Analyze the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generate a deep eutectic solvent quality assessment report.

[0014] Furthermore, the molar ratio of glycerol to betaine is 1:3.

[0015] Furthermore, the heating temperature is eighty degrees Celsius.

[0016] Furthermore, the mixture in the container is stirred for two hours.

[0017] Furthermore, obtaining a deep eutectic solvent image and preprocessing the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image includes the following steps:

[0018] S41, removing noise from the acquired deep eutectic solvent image through a Gaussian filter;

[0019] S42, correcting brightness and color deviation of the deep eutectic solvent image after noise removal;

[0020] S43, processing the corrected deep eutectic solvent image using an image processing technique to obtain a deep eutectic solvent image with enhanced contrast and clarity;

[0021] S44, extracting an image sequence from the obtained deep eutectic solvent image with enhanced contrast and clarity, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image;

[0022] S45, using the Sobel operator to calculate the edge gradient of each pixel in the grayscale image;

[0023] S46, using a local gradient mean method to locally screen and enhance the edge gradient, and setting a threshold to filter the edge gradient to obtain a gradient image;

[0024] S47, representing the deep eutectic solvent image by calculating the ordered eigenvectors of the region areas by Euclidean distance;

[0025] S48, performing thinning and binarization processing on the gradient image, and taking pixels with gradient values ​​greater than a threshold as edge points;

[0026] S49. Connect adjacent edge points into a connected domain to obtain a final edge image as a characteristic image of the deep eutectic solvent.

[0027] Furthermore, comparing the obtained deep eutectic solvent characteristic image with various deep eutectic solvent characteristic images in the database by an image classification algorithm to identify the composition characteristics of the deep eutectic solvent includes the following steps:

[0028] S51, setting image classification algorithm parameters, and generating preliminary medical feature images and corresponding feature trend matrices according to the image classification algorithm parameters;

[0029] S52, calculating a fitness function value of a preliminary deep eutectic solvent characteristic image;

[0030] S53, calculating the population fitness variance of all deep eutectic solvent feature images. If the preset conditions are met, a mutation occurs and the process goes to step S55; otherwise, the process goes to step S54;

[0031] S54, updating the inertia weight point according to the formula for calculating the inertia weight, and updating the change trend and position of the deep eutectic solvent characteristic image according to the change trend update formula and position update formula of the deep eutectic solvent characteristic image respectively;

[0032] S55, check whether the end condition is met, if so, terminate the optimization process, if not, return to S52 to continue optimization;

[0033] S56, assigning the found optimal parameter vector to the classification model;

[0034] S57, inputting the processed deep eutectic solvent feature image into the classification model, and training the classification model to obtain a trained classification model;

[0035] S58. Determine the new deep eutectic solvent feature image using the trained classification model to obtain a final deep eutectic solvent component classification result, and stop the calculation;

[0036] S59. Identify the composition characteristics of the deep eutectic solvent through the final composition classification results.

[0037] Furthermore, the new deep eutectic solvent characteristic image is judged by the trained classification model to obtain the final deep eutectic solvent component classification result, and the calculation is stopped, which includes the following steps:

[0038] S581. Using the trained classification model, determine the new deep eutectic solvent feature image to obtain the probability that each feature image belongs to various deep eutectic solvent categories;

[0039] S582. Preset a confidence threshold, filter the probability of each deep eutectic solvent feature image belonging to each category below the confidence threshold, and determine the category label from the probability judgment of the classification model using the classification threshold;

[0040] S583. The determined category label is used as the final deep eutectic solvent composition classification result, and the calculation is stopped.

[0041] Furthermore, analyzing the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generating a deep eutectic solvent quality assessment report includes the following steps:

[0042] S61. Identify the key components that have the greatest impact on the quality of the deep eutectic solvent from its composition data using a mass analysis algorithm;

[0043] S62. Determine the indicators for analyzing the quality of deep eutectic solvents and set quality thresholds and improvement techniques;

[0044] S63. If the quality caused by the key component is lower than the threshold, the key component is adjusted using the set improvement technology;

[0045] S64. Establish a composition optimization model for optimizing the composition of the deep eutectic solvent, and determine the objective function and constraints of the composition optimization model;

[0046] S65. Apply the quality analysis algorithm to the optimization model to find the best solution that meets the constraints, which is used to determine and improve the key components that affect the quality of the deep eutectic solvent and generate a deep eutectic solvent quality assessment report.

[0047] Furthermore, applying the quality analysis algorithm to the optimization model to find the best solution that meets the constraints is used to determine and improve the key components that affect the quality of the deep eutectic solvent. Generating a deep eutectic solvent quality assessment report includes the following steps:

[0048] S651. Processing the identified key components that affect the quality of the deep eutectic solvent to meet preset quality standards, and obtaining processed key component data;

[0049] S652. Initializing parameters of the quality analysis algorithm and setting an initial improved technique for deep eutectic solvent quality optimization;

[0050] S653. Evaluate the specific impact of each improvement technology on the quality of the deep eutectic solvent through the established objective function, and update the optimization status based on the results;

[0051] S654. Optimize, evaluate, and adjust the improvement technologies for key components that affect the quality of deep eutectic solvents, and continuously update the optimization status based on preset conditions;

[0052] S655. If the quality analysis reaches a preset quality threshold, then determine the best improvement technology to generate a deep eutectic solvent quality assessment report; if the quality does not reach the preset threshold, then continue to optimize and adjust the improvement technology.

[0053] According to another aspect of the present invention, the use of a deep eutectic solvent in a peony extract is also provided.

[0054] The beneficial effects of the present invention are:

[0055] 1. The present invention creates a specific deep eutectic solvent by precisely formulating the ratio of glycerol and betaine and adding an appropriate amount of distilled water. This ensures that the deep eutectic solvent has suitable chemical properties and solubility, creating conditions for the efficient extraction of antioxidant components. By conducting DPPH free radical scavenging experiments on DES, its free radical scavenging ability can be effectively evaluated, which is a key indicator for measuring its potential application value. By acquiring images of the deep eutectic solvent and identifying its component characteristics through advanced image processing and classification algorithms, it is not only helpful to understand the complex composition of DES, but also to optimize and adjust its composition for optimal antioxidant performance by comparing different deep eutectic solvent images. Utilizing quality analysis algorithms to conduct in-depth analysis of the identified component characteristics ensures that each batch of deep eutectic solvent meets high quality standards.

[0056] 2. The present invention sets image classification algorithm parameters and trains classification models to more accurately identify and classify the components in deep eutectic solvents, helping to accurately determine which components have the best DPPH free radical scavenging effect, thereby optimizing the preparation formula of DES. By calculating the fitness function and fitness variance, the component characteristics of DES are continuously adjusted and optimized to ensure that the prepared deep eutectic solvent achieves optimal antioxidant performance in practical applications. By using the trained classification model to quickly and accurately determine the characteristic images of new deep eutectic solvents, the evaluation process of the new deep eutectic solvent components is accelerated, significantly improving the efficiency of research and development and production.

[0057] 3. The present invention uses a mass analysis algorithm to identify and determine the key components and quality indicators that affect the quality of DES, thereby not only helping to ensure the consistency of each batch of DES, but also ensuring that it meets the strict standards for high-efficiency DPPH clearance experiments. Key components below the quality threshold are adjusted, and a component optimization model is established to make the DES preparation process more precise and optimize the components to improve its overall effectiveness. By applying the mass analysis algorithm to the component optimization model, the optimal solution that meets the constraints is found, effectively guiding key decisions in the preparation process to ensure the quality and effectiveness of the final product. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 4 is a flow chart of a method for preparing DES according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0061] According to an embodiment of the present invention, a method for preparing DES and its application in peony extract are provided.

[0062] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the DES preparation method of an embodiment of the present invention, the DES preparation method comprises the following steps:

[0063] S1. Pre-prepare glycerol and betaine, place the prepared glycerol and betaine in a container, and add pre-prepared distilled water into the container to mix with the glycerol and betaine;

[0064] S2, placing the mixed container in an oil bath, heating it, and stirring the mixture in the container;

[0065] S3. After stirring is completed, observe the changes in the appearance of the mixture. If a uniform and transparent liquid is formed, the deep eutectic solvent is prepared. Samples are taken for free radical scavenging experiments to verify its effect.

[0066] S4. Acquire a deep eutectic solvent image, and preprocess the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image;

[0067] S5. Comparing the obtained deep eutectic solvent characteristic image with characteristic images of various deep eutectic solvents in a database through an image classification algorithm to identify the composition characteristics of the deep eutectic solvent;

[0068] S6. Analyze the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generate a deep eutectic solvent quality assessment report.

[0069] Preferably, the molar ratio of glycerol to betaine is 1:3.

[0070] Preferably, the heating temperature is eighty degrees Celsius.

[0071] Preferably, the mixture in the container is stirred for two hours.

[0072] Preferably, acquiring a deep eutectic solvent image and preprocessing the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image comprises the following steps:

[0073] S41, removing noise from the acquired deep eutectic solvent image through a Gaussian filter;

[0074] Specifically, a Gaussian filter is a commonly used image filter that can remove noise by smoothing an image. It performs a weighted average on each pixel in the image based on the weight of the Gaussian function, thereby reducing the noise in the image.

[0075] S42, correcting brightness and color deviation of the deep eutectic solvent image after noise removal;

[0076] Specifically, brightness and color deviation correction is to make the brightness and color of the image more accurate and consistent. By performing grayscale correction and white balance correction on the image, the brightness and color of the image can be adjusted to make it more consistent with the real scene.

[0077] S43, processing the corrected deep eutectic solvent image using an image processing technique to obtain a deep eutectic solvent image with enhanced contrast and clarity;

[0078] Specifically, the image processing technology is the histogram equalization method, the basic idea of ​​which is to adjust the grayscale distribution of the image so that the pixel values ​​of each grayscale level in the image are distributed more evenly, thereby enhancing the details and contrast of the image.

[0079] S44, extracting an image sequence from the obtained deep eutectic solvent image with enhanced contrast and clarity, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image;

[0080] S45, using the Sobel operator to calculate the edge gradient of each pixel in the grayscale image;

[0081] Specifically, the Sobel operator is a classic image edge detection operator used to detect edges and contours in images. Based on discrete differential operations, it calculates the horizontal and vertical gradient values ​​for each pixel in the image, thereby highlighting areas with large grayscale changes in the image, namely edges or contours.

[0082] S46, using a local gradient mean method to locally screen and enhance the edge gradient, and setting a threshold to filter the edge gradient to obtain a gradient image;

[0083] Specifically, the local mean gradient method is an image processing method used to enhance image edges or details while reducing the effects of noise. It filters and enhances edge features by calculating the mean gradient of pixels within a local area of ​​the image.

[0084] S47, representing the deep eutectic solvent image by calculating the ordered eigenvectors of the region areas by Euclidean distance;

[0085] Specifically, Euclidean distance is a commonly used distance metric used to calculate the distance between two vectors. In image processing and pattern recognition, Euclidean distance is often used to compare the similarity or difference between two vectors or features.

[0086] S48, performing thinning and binarization processing on the gradient image, and taking pixels with gradient values ​​greater than a threshold as edge points;

[0087] Specifically, thinning is an image processing technique that aims to make edge lines thinner and longer, and is often used to extract detailed features in images. Thinning can reduce the width of edge lines through a series of algorithms, such as the Zhang-Suen algorithm and the Guo-Hall algorithm, to make them more consistent with the actual edge structure.

[0088] Specifically, binarization is the process of converting the grayscale values ​​of an image into two values. This usually involves dividing the image into two regions, one with a pixel value of 0 (usually representing black) and the other with a pixel value of 255 (usually representing white). This process helps to highlight objects or specific areas in the image.

[0089] S49. Connect adjacent edge points into a connected domain to obtain a final edge image as a characteristic image of the deep eutectic solvent.

[0090] Preferably, comparing the obtained deep eutectic solvent characteristic image with various deep eutectic solvent characteristic images in a database by an image classification algorithm to identify the composition characteristics of the deep eutectic solvent comprises the following steps:

[0091] S51, setting image classification algorithm parameters, and generating preliminary medical feature images and corresponding feature trend matrices according to the image classification algorithm parameters;

[0092] S52, calculating a fitness function value of a preliminary deep eutectic solvent characteristic image;

[0093] S53, calculating the population fitness variance of all deep eutectic solvent feature images. If the preset conditions are met, a mutation occurs and the process goes to step S55; otherwise, the process goes to step S54;

[0094] S54, updating the inertia weight point according to the formula for calculating the inertia weight, and updating the change trend and position of the deep eutectic solvent characteristic image according to the change trend update formula and position update formula of the deep eutectic solvent characteristic image respectively;

[0095] S55, check whether the end condition is met, if so, terminate the optimization process, if not, return to S52 to continue optimization;

[0096] S56, assigning the found optimal parameter vector to the classification model (i.e., support vector machine model);

[0097] S57, inputting the processed deep eutectic solvent feature image into the classification model, and training the classification model to obtain a trained classification model;

[0098] S58. Determine the new deep eutectic solvent feature image using the trained classification model to obtain a final deep eutectic solvent component classification result, and stop the calculation;

[0099] S59. Identify the composition characteristics of the deep eutectic solvent through the final composition classification results.

[0100] Specifically, the image classification algorithm is an adaptive particle swarm optimization (PSO) support vector machine (SVM) algorithm. This algorithm combines PSO with SVM to optimize the parameters of the SVM model. The adaptive particle swarm optimization (PSO) SVM algorithm continuously updates the positions and velocities of particles and leverages the search capabilities of the PSO algorithm to find the optimal combination of SVM parameters, thereby improving the model's performance and generalization capabilities.

[0101] Preferably, determining the new deep eutectic solvent characteristic image by a trained classification model to obtain the final deep eutectic solvent component classification result and stopping the calculation includes the following steps:

[0102] S581. Using the trained classification model, determine the new deep eutectic solvent feature image to obtain the probability that each feature image belongs to various deep eutectic solvent categories;

[0103] S582. Preset a confidence threshold, filter the probability of each deep eutectic solvent feature image belonging to each category below the confidence threshold, and determine the category label from the probability judgment of the classification model using the classification threshold;

[0104] S583. The determined category label is used as the final deep eutectic solvent composition classification result, and the calculation is stopped.

[0105] Preferably, analyzing the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generating a deep eutectic solvent quality assessment report includes the following steps:

[0106] S61. Identify the key components that have the greatest impact on the quality of the deep eutectic solvent from its composition data using a mass analysis algorithm;

[0107] S62. Determine the indicators for analyzing the quality of deep eutectic solvents and set quality thresholds and improvement techniques;

[0108] S63. If the quality caused by the key component is lower than the threshold, the key component is adjusted using the set improvement technology;

[0109] S64. Establish a composition optimization model for optimizing the composition of the deep eutectic solvent, and determine the objective function and constraints of the composition optimization model;

[0110] S65. Apply the quality analysis algorithm to the optimization model to find the best solution that meets the constraints, which is used to determine and improve the key components that affect the quality of the deep eutectic solvent and generate a deep eutectic solvent quality assessment report.

[0111] Specifically, the quality analysis algorithm is the fish school algorithm, which is an optimization algorithm based on swarm intelligence. It is inspired by the foraging, clustering and following behaviors of fish in nature. The algorithm imitates the collective behavior of fish in finding food and avoiding danger.

[0112] Preferably, applying a quality analysis algorithm to an optimization model to find an optimal solution that satisfies the constraints, thereby determining and improving key components that affect the quality of the deep eutectic solvent, and generating a deep eutectic solvent quality assessment report comprises the following steps:

[0113] S651. Processing (i.e., whitening) the identified key components that affect the quality of the deep eutectic solvent to meet preset quality standards, and obtaining processed key component data;

[0114] Specifically, whitening is a signal processing technique used to eliminate redundant information in data and reduce the correlation between features. In the present invention, the purpose of whitening is to prepare key component data so that it meets the input requirements of the comparison algorithm.

[0115] S652, initializing the parameters of the quality analysis algorithm (i.e., initializing the fish school algorithm parameters), and setting the initial improved technology for deep eutectic solvent quality optimization (i.e., artificial fish);

[0116] S653. Evaluate the specific impact of each improvement technology on the quality of the deep eutectic solvent through the established objective function, and update the optimization status based on the results;

[0117] S654. Optimize (i.e., foraging behavior in the fish school algorithm), evaluate, and adjust (i.e., clustering behavior in the fish school algorithm) the improvement technology for key components that affect the quality of deep eutectic solvents, and continuously update the optimization status according to preset conditions (i.e., tailing behavior in the fish school algorithm);

[0118] S655. If the quality analysis reaches a preset quality threshold, determine the best improvement technology to generate a deep eutectic solvent quality assessment report; if the quality does not reach the preset threshold, continue to optimize and adjust the improvement technology (i.e., improvement strategy or improvement measures).

[0119] According to another embodiment of the present invention, the use of a deep eutectic solvent in a peony extract is also provided.

[0120] It should be explained that the process of extracting white peony root components using the deep eutectic solvent (DES) prepared by the present invention as a medium under specific conditions includes:

[0121] 1) Weighing and mixing: First, accurately weigh 1 g of white peony root powder, 0.8 g of cellulase, and 1.2 g of pectinase, and dissolve these ingredients in 200 ml of the prepared deep eutectic solvent (DES).

[0122] 2) Adjust pH and temperature: The pH of the solution was then adjusted to 5.5 and stirred at 55 degrees Celsius for 2.5 hours. This helps optimize the efficiency and stability of the enzyme.

[0123] 3) Centrifugation and collection of supernatant: Finally, the mixture was centrifuged at 10,000 rpm for 10 minutes, and then the supernatant was collected. This liquid contained the active ingredients extracted from the white peony root.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for preparing DES, characterized in that: The DES preparation method comprises the following steps: S1. Pre-prepare glycerol and betaine, place the prepared glycerol and betaine in a container, and add pre-prepared distilled water into the container to mix with the glycerol and betaine; S2, placing the mixed container in an oil bath, heating it, and stirring the mixture in the container; S3. After stirring is completed, observe the changes in the appearance of the mixture. If a uniform and transparent liquid is formed, the deep eutectic solvent is prepared. Samples are taken for free radical scavenging experiments to verify its effect. S4. Acquire a deep eutectic solvent image, and preprocess the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image; S5. Comparing the obtained deep eutectic solvent characteristic image with characteristic images of various deep eutectic solvents in a database through an image classification algorithm to identify the composition characteristics of the deep eutectic solvent; S6. Analyzing the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generating a deep eutectic solvent quality assessment report; The step of acquiring a deep eutectic solvent image and preprocessing the deep eutectic solvent image to obtain a deep eutectic solvent characteristic image comprises the following steps: S41, removing noise from the acquired deep eutectic solvent image through a Gaussian filter; S42, correcting brightness and color deviation of the deep eutectic solvent image after noise removal; S43, processing the corrected deep eutectic solvent image using an image processing technique to obtain a deep eutectic solvent image with enhanced contrast and clarity; S44, extracting an image sequence from the obtained deep eutectic solvent image with enhanced contrast and clarity, and performing grayscale processing on each frame of the image sequence to obtain a grayscale image; S45, using the Sobel operator to calculate the edge gradient of each pixel in the grayscale image; S46, using a local gradient mean method to locally screen and enhance the edge gradient, and setting a threshold to filter the edge gradient to obtain a gradient image; S47, representing the deep eutectic solvent image by calculating the ordered eigenvectors of the region areas by Euclidean distance; S48, performing thinning and binarization processing on the gradient image, and taking pixels with gradient values ​​greater than a threshold as edge points; S49. Connect adjacent edge points into a connected domain to obtain a final edge image as a characteristic image of the deep eutectic solvent.

2. A DES preparation method according to claim 1, characterized in that: The molar ratio of the glycerol to the betaine is 1:

3.

3. A DES preparation method according to claim 1, characterized in that: The heating temperature is eighty degrees Celsius.

4. A method for preparing DES according to claim 1, characterized in that: The time for stirring the mixture in the container is two hours.

5. The method for preparing DES according to claim 1, wherein: The step of comparing the obtained deep eutectic solvent characteristic image with various deep eutectic solvent characteristic images in a database by an image classification algorithm to identify the composition characteristics of the deep eutectic solvent comprises the following steps: S51, setting image classification algorithm parameters, and generating preliminary medical feature images and corresponding feature trend matrices according to the image classification algorithm parameters; S52, calculating a fitness function value of a preliminary deep eutectic solvent characteristic image; S53, calculating the population fitness variance of all deep eutectic solvent feature images. If the preset conditions are met, a mutation occurs and the process goes to step S55; otherwise, the process goes to step S54; S54, updating the inertia weight point according to the formula for calculating the inertia weight, and updating the change trend and position of the deep eutectic solvent characteristic image according to the change trend update formula and position update formula of the deep eutectic solvent characteristic image respectively; S55, check whether the end condition is met, if so, terminate the optimization process, if not, return to S52 to continue optimization; S56, assigning the found optimal parameter vector to the classification model; S57, inputting the processed deep eutectic solvent feature image into the classification model, and training the classification model to obtain a trained classification model; S58. Determine the new deep eutectic solvent feature image using the trained classification model to obtain a final deep eutectic solvent component classification result, and stop the calculation; S59. Identify the composition characteristics of the deep eutectic solvent through the final composition classification results.

6. A method for preparing DES according to claim 5, characterized in that: The method of determining the new deep eutectic solvent characteristic image by using the trained classification model to obtain the final deep eutectic solvent component classification result and stopping the calculation includes the following steps: S581. Using the trained classification model, determine the new deep eutectic solvent feature image to obtain the probability that each feature image belongs to various deep eutectic solvent categories; S582. Preset a confidence threshold, filter the probability of each deep eutectic solvent feature image belonging to each category below the confidence threshold, and determine the category label from the probability judgment of the classification model using the classification threshold; S583. The determined category label is used as the final deep eutectic solvent composition classification result, and the calculation is stopped.

7. The method for preparing DES according to claim 1, wherein: The method of analyzing the composition characteristics of the identified deep eutectic solvent using a quality analysis algorithm and generating a deep eutectic solvent quality assessment report includes the following steps: S61. Identify the key components that have the greatest impact on the quality of the deep eutectic solvent from its composition data using a mass analysis algorithm; S62. Determine the indicators for analyzing the quality of deep eutectic solvents and set quality thresholds and improvement techniques; S63. If the quality caused by the key component is lower than the threshold, the key component is adjusted using the set improvement technology; S64. Establish a composition optimization model for optimizing the composition of the deep eutectic solvent, and determine the objective function and constraints of the composition optimization model; S65. Apply the quality analysis algorithm to the optimization model to find the best solution that meets the constraints, which is used to determine and improve the key components that affect the quality of the deep eutectic solvent and generate a deep eutectic solvent quality assessment report.

8. A method for preparing DES according to claim 7, characterized in that: Applying the quality analysis algorithm to the optimization model to find the best solution that meets the constraints, identify and improve the key components that affect the quality of the deep eutectic solvent, and generate a deep eutectic solvent quality assessment report includes the following steps: S651. Processing the identified key components that affect the quality of the deep eutectic solvent to meet preset quality standards, and obtaining processed key component data; S652. Initializing parameters of the quality analysis algorithm and setting an initial improved technique for deep eutectic solvent quality optimization; S653. Evaluate the specific impact of each improvement technology on the quality of the deep eutectic solvent through the established objective function, and update the optimization status based on the results; S654. Optimize, evaluate, and adjust the improvement technologies for key components that affect the quality of deep eutectic solvents, and continuously update the optimization status based on preset conditions; S655. If the quality analysis reaches a preset quality threshold, then determine the best improvement technology to generate a deep eutectic solvent quality assessment report; if the quality does not reach the preset threshold, then continue to optimize and adjust the improvement technology.

9. Use of the deep eutectic solvent prepared by the DES preparation method according to claim 1 in peony extract.

Images