A method and system for component production optimization of a target composition

Abstract

The application relates to the technical field of composition production, in particular to a component production optimization method and system for a target composition. The method comprises the following steps: acquiring an image set of each target composition sample in a target composition sample set; acquiring a wrinkle change amount in a corresponding image of each target composition sample; acquiring a mapping relationship between a mass percentage of a component in the target composition and the wrinkle change amount in the image; acquiring a priority value corresponding to each candidate density in a candidate density set of the target composition according to the mapping relationship; determining a candidate density with the maximum priority value in the candidate density set as a target density; and determining a target mass percentage of the component in the target composition as a target mass percentage of the component in the target composition, wherein the target density is the target density and the wrinkle change amount in the corresponding image is the minimum. The application can improve the efficiency of composition research and development and production and the accuracy of composition evaluation.

Description

Technical Field

[0001] This invention relates to the field of composition production technology, and in particular to a method and system for optimizing the production of components of a target composition. Background Technology

[0002] In the field of composition research and development, ingredients such as AKG (α-ketoglutarate), SOD (superoxide dismutase), and niacinamide are often used in combination. Compositions containing AKG, SOD, and niacinamide have important applications in anti-wrinkle and other aspects. Currently, the traditional methods for optimizing the production of such compositions often rely on manual experiments and subjective evaluation. Traditional methods relying on manual experiments refer to conducting numerous experiments with different component mass percentages to obtain the anti-wrinkle effect of each different component mass percentage, which consumes considerable experimental time and costs. Traditional methods relying on subjective evaluation refer to judging the anti-wrinkle effect by manually observing changes in the skin of experimental subjects. Due to the strong subjectivity of manual observation, it is difficult to accurately quantify the changes in wrinkles before and after the use of the composition. The aforementioned methods of manual experiments and subjective evaluation affect the efficiency of composition research and development and also affect the accuracy of composition evaluation. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for optimizing the production of components of a target composition, so as to improve the efficiency of composition research and development and the accuracy of composition evaluation.

[0004] According to a first aspect of the present invention, a method for optimizing the production of components of a target composition is provided, the method comprising the following steps:

[0005] Obtain an image set for each target composition sample in the target composition sample set; the target composition sample set includes several target composition samples, and the components of any target composition sample include AKG, SOD and nicotinamide, and the mass percentage of the components in different target composition samples is different; the image set of any target composition sample includes several image pairs of experimental subjects, and the image pair of any experimental subject includes a control image and an experimental image of that experimental subject.

[0006] The amount of wrinkle change in the image corresponding to each target composition sample is obtained from the image set of each target composition sample in the target composition sample set; the amount of wrinkle change in the image corresponding to any target composition sample is the average amount of wrinkle change in the images of all experimental subjects corresponding to that target composition sample, and the amount of wrinkle change in the image of any experimental subject is the difference between the wrinkle ratio in the experimental image of that experimental subject and the wrinkle ratio in the control image.

[0007] The mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image of each target composition sample in the target composition sample set is obtained; in the mapping relationship, the mass percentage of AKG, the mass percentage of SOD and the mass percentage of nicotinamide are independent variables, and the amount of wrinkle change in the image is the dependent variable.

[0008] The priority value corresponding to each candidate density in the candidate density set of the target composition is obtained according to the mapping relationship; the candidate density set includes several candidate densities, and the priority value corresponding to any candidate density is obtained according to the amount of wrinkle change in the image corresponding to the target composition with that candidate density.

[0009] The candidate density with the highest priority value in the candidate density set is determined as the target density, and the mass percentage of the component in the target composition with the lowest wrinkle change in the corresponding image and the target density is determined as the target mass percentage of the component in the target composition.

[0010] Furthermore, obtaining the priority value corresponding to each candidate density in the candidate density set of the target composition according to the mapping relationship includes:

[0011] The amount of wrinkle change in the image corresponding to the target composition with a specified candidate density is obtained according to the mapping relationship; the specified candidate density is any candidate density in the candidate density set.

[0012] The average value of wrinkle variation in the image corresponding to the target composition with a specified candidate density is determined as the first value of the specified candidate density.

[0013] The variance of the amount of wrinkle variation in the image corresponding to the target composition with a specified candidate density is determined as the second value of the specified candidate density.

[0014] The priority value of the candidate density is obtained based on the first and second values ​​of the specified candidate density; the priority value of the specified candidate density is negatively correlated with both the first and second values ​​of the specified candidate density.

[0015] Furthermore, obtaining the priority value of the candidate density based on the first and second values ​​of the candidate density includes: obtaining the priority value of the candidate density based on the first value of the candidate density, the first preset weight, the second value of the candidate density, and the second preset weight.

[0016] Furthermore, the process of obtaining the target composition with a specified candidate density includes:

[0017] Obtain the mass percentage range of each component in the target composition, and obtain the mass percentage corresponding to each level of the component based on the mass percentage range of any component and the preset level number.

[0018] An orthogonal array matching the number of components and the preset number of levels in the target composition is selected to construct a component ratio combination matrix.

[0019] The target composition was prepared by combining the components in the specified proportions and the density of each target composition was obtained.

[0020] Screening target compositions with a specified candidate density from the prepared target compositions.

[0021] Furthermore, setting the mass percentage corresponding to each level of a component based on the mass percentage range of any component and the preset number of levels includes: dividing the mass percentage range of any component into equal parts according to the preset number of levels to obtain the mass percentage corresponding to each level of the component.

[0022] Furthermore, obtaining the mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image of each target composition sample in the target composition sample set includes: setting a preset fitting function, fitting the function to the mass percentage of the components in each target composition sample in the target composition sample set and the corresponding amount of wrinkle change in the image, and determining the fitted function expression as the mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image.

[0023] Furthermore, the preset fitting function is a multivariate quadratic polynomial function.

[0024] Furthermore, obtaining the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density according to the mapping relationship includes: substituting the mass percentage of the component in each target composition with a specified candidate density into the mapping relationship to obtain the amount of wrinkle change in the image corresponding to each target composition with a specified candidate density.

[0025] Furthermore, the wrinkle percentage of the experimental image of any experimental subject is the ratio of wrinkle pixels to the total number of pixels in the experimental image of that experimental subject, and the wrinkle percentage of the control image of any experimental subject is the ratio of wrinkle pixels to the total number of pixels in the control image of that experimental subject.

[0026] According to a second aspect of the present invention, a component production optimization system for a target composition is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned component production optimization method for the target composition.

[0027] The present invention has at least the following beneficial effects:

[0028] This invention establishes a mapping relationship between the mass percentage of components in each target composition sample within a target composition sample set and the amount of wrinkle variation in the image. Based on this mapping relationship, the invention can quickly obtain the priority value corresponding to each candidate density in the candidate density set of the target composition, eliminating the need for extensive experiments to verify the amount of wrinkle variation in the image corresponding to each candidate density of the target composition. This reduces the cost of blind trial and error and improves the efficiency of component production optimization for the target composition. Moreover, this invention can automatically obtain the amount of wrinkle variation in experimental subjects based on image processing technology. Compared to manual observation of experimental subjects, the wrinkle variation obtained by this invention is more objective and accurate. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart of the component production optimization method for the target composition provided in Embodiment 1 of the present invention;

[0031] Figure 2 This is a flowchart illustrating the process of obtaining the priority value corresponding to each candidate density in the candidate density set of the target composition, as provided in Embodiment 1 of the present invention.

[0032] Figure 3 This is a flowchart illustrating the process of obtaining a target composition with a specified candidate density, as provided in Embodiment 1 of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] Example 1:

[0035] According to the present invention, a method for optimizing the production of components of a target composition is provided, such as... Figure 1 As shown, the method includes the following steps:

[0036] S100, acquire an image set for each target composition sample in the target composition sample set; the target composition sample set includes several target composition samples, and the components of any target composition sample include AKG, SOD and nicotinamide, and the mass percentage of the components in different target composition samples is different; the image set of any target composition sample includes several image pairs of experimental subjects, and the image pair of any experimental subject includes a control image and an experimental image of the experimental subject.

[0037] In this embodiment, the sum of the mass percentages of the components of the target composition is 1, and the mass percentages of the components are different for different target composition samples.

[0038] In this embodiment, target composition samples containing different component mass percentages are obtained, and image data of each target composition sample after being applied to experimental subjects are acquired. Any target composition sample is applied to multiple experimental subjects to improve the accuracy of target composition evaluation. The image set for each experimental sample includes control images and experimental images, where control images are images of the experimental subject before using the target composition, and experimental images are images of the experimental subject after using the target composition. Furthermore, the control images and experimental images of the same subject are taken under the same conditions, including lighting, shooting angle, and shooting distance. The shooting time intervals for control images and experimental images of different experimental subjects are equal, and the experimental subjects treated with different target composition samples have the same characteristics, including age, skin type, and initial wrinkle state. Therefore, the acquired image data is objective and comparable, accurately reflecting the impact of different component ratios on wrinkle changes, providing reliable raw data for subsequent analysis.

[0039] S200, obtain the wrinkle change amount in the image corresponding to each target composition sample according to the image set of each target composition sample in the target composition sample set; the wrinkle change amount in the image corresponding to any target composition sample is the average wrinkle change amount in the images of all experimental subjects corresponding to that target composition sample, and the wrinkle change amount in the image of any experimental subject is the difference between the wrinkle ratio in the experimental image of that experimental subject and the wrinkle ratio in the control image.

[0040] In this embodiment, the amount of wrinkle change in the image corresponding to the target composition sample is usually negative. The smaller the amount of wrinkle change in the image corresponding to a target composition sample, the better the anti-wrinkle effect of the target composition is determined.

[0041] In one specific implementation, the wrinkle ratio of the experimental image of any experimental subject is the ratio of wrinkled pixels to the total number of pixels in the experimental image of that experimental subject, and the wrinkle ratio of the control image of any experimental subject is the ratio of wrinkled pixels to the total number of pixels in the control image of that experimental subject. Those skilled in the art will understand that any method for obtaining wrinkled pixels in an image in the prior art falls within the protection scope of this invention. In one specific implementation, image processing is performed on the control image and the experimental image of any experimental subject, using techniques such as edge detection, threshold segmentation, and morphological operations to identify and extract wrinkled regions in the images, and the ratio of the number of wrinkled pixels to the total number of pixels in the control image is calculated to obtain the wrinkle ratio of the control image; similarly, the wrinkle ratio of the experimental image can also be obtained.

[0042] This embodiment utilizes image processing technology to transform wrinkle changes, which are difficult to quantify precisely with the naked eye, into calculable pixel ratio differences. By calculating the average value, the influence of individual differences in a single experimental subject is reduced, making the results more representative. Thus, this embodiment achieves objective and accurate quantification of wrinkle changes, avoiding errors from subjective human evaluation, and providing accurate quantitative indicators for establishing the mapping relationship between component mass percentage and anti-wrinkle effect.

[0043] S300, based on the amount of wrinkle change in the image of each target composition sample in the target composition sample set, obtain the mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image; in the mapping relationship, the mass percentage of AKG, the mass percentage of SOD and the mass percentage of nicotinamide are independent variables, and the amount of wrinkle change in the image is the dependent variable.

[0044] This embodiment establishes a mapping relationship based on the component mass percentage and corresponding wrinkle change amount of each target composition sample in the target composition sample set. The component percentage in the target composition is the independent variable, and the wrinkle change amount in the corresponding image is the dependent variable. As a specific implementation, obtaining the mapping relationship between the component mass percentage and wrinkle change amount in the image of each target composition sample in the target composition sample set includes: setting a preset fitting function, fitting the function based on the component mass percentage and corresponding wrinkle change amount in the image of each target composition sample in the target composition sample set, and determining the fitted function expression as the mapping relationship between the component mass percentage and wrinkle change amount in the image.

[0045] In one specific implementation, the preset fitting function is a multivariate quadratic polynomial function. The component mass percentages of each target composition sample and the corresponding wrinkle changes in the image are substituted into this multivariate quadratic polynomial function. Fitting methods such as least squares are used to calculate the values ​​of each coefficient, thus obtaining the fitted function expression, i.e., the target mapping relationship. The multivariate quadratic polynomial function can effectively describe the potentially nonlinear relationship between the mass percentages of multiple components and the corresponding wrinkle changes in the image. By fitting and establishing a mathematical model, the prediction from component ratios to anti-wrinkle effects can be achieved.

[0046] The mapping relationship constructed in this embodiment can accurately reflect the intrinsic relationship between the mass percentage of each component in the target composition and the anti-wrinkle effect, providing a basis for subsequent prediction of wrinkle changes under different component ratios, and facilitating efficient component optimization.

[0047] S400, according to the mapping relationship, obtain the priority value corresponding to each candidate density in the candidate density set of the target composition; the candidate density set includes several candidate densities, and the priority value corresponding to any candidate density is obtained according to the amount of wrinkle change in the image corresponding to the target composition with that candidate density.

[0048] In this embodiment, the candidate density set of the target composition is preset and is known.

[0049] In this embodiment, based on the established mapping relationship, the priority value corresponding to each candidate density in the candidate density set is calculated to quantitatively evaluate the priority value of each candidate density, providing a basis for selecting the optimal target density. As a specific implementation method, such as... Figure 2 As shown, obtaining the priority value corresponding to each candidate density in the candidate density set of the target composition according to the mapping relationship includes:

[0050] S410, obtain the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density according to the mapping relationship; the specified candidate density is any candidate density in the candidate density set.

[0051] In this embodiment, obtaining the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density according to the mapping relationship includes: substituting the mass percentage of the component in each target composition with a specified candidate density into the mapping relationship to obtain the amount of wrinkle change in the image corresponding to each target composition with a specified candidate density.

[0052] As a specific implementation method, such as Figure 3 As shown, the process for obtaining a target composition with a specified candidate density includes:

[0053] S411, obtain the mass percentage range of each component in the target composition, and obtain the mass percentage corresponding to each level of the component based on the mass percentage range of any component and the preset level number.

[0054] In this embodiment, the mass percentage range of each component in the target composition is preset and is known.

[0055] Optionally, the preset level number is an empirical value. It should be understood that the larger the preset level number, the more mass percentages of each component can be divided, and thus the more target compositions can be configured subsequently.

[0056] As a specific implementation, setting the mass percentage corresponding to each level of a component based on the mass percentage range of any component and a preset number of levels includes: dividing the mass percentage range of any component into equal parts according to the preset number of levels to obtain the mass percentage corresponding to each level of the component. It should be understood that dividing the mass percentage range of any component into equal parts according to the preset number of levels results in discrete mass percentages of the preset number of levels, and the distance between any two adjacent mass percentages is equal.

[0057] S412, select an orthogonal array that matches the number of components and the preset number of levels in the target composition to construct a component ratio combination matrix.

[0058] Those skilled in the art will recognize that orthogonal arrays are prior art and will not be described further here.

[0059] S413, prepare the target composition according to the component ratio combination matrix, and obtain the density of each group of target compositions.

[0060] In this embodiment, if the sum of the mass percentages of the components in a certain combination in the component ratio combination matrix is ​​not 1, then the mass percentages of the components in that combination can be adjusted proportionally so that the sum of the mass percentages of the components in the adjusted combination is 1.

[0061] Those skilled in the art will recognize that the process of obtaining density is prior art and will not be described in detail here.

[0062] S414, Screening target compositions with a specified candidate density from the prepared target compositions.

[0063] Based on S411-S414, this embodiment is able to obtain a target composition with a density of a specified candidate density.

[0064] S420, the average value of the wrinkle change in the image corresponding to the target composition with a specified candidate density is determined as the first value of the specified candidate density.

[0065] In this embodiment, the first value of the specified candidate density is used to reflect the average anti-wrinkle effect of the target composition at the specified candidate density.

[0066] S430, the variance of the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density is determined as a second value of the specified candidate density.

[0067] In this embodiment, the second value of the specified candidate density is used to reflect the differences in the anti-wrinkle effect of different combinations of mass percentages under the specified candidate density.

[0068] It should be understood that if the second value of the specified candidate density is small, it indicates that the difference in wrinkle variation in the image corresponding to different mass percentage combinations of the target composition at the specified candidate density is small. If the mass percentage of the components is adjusted while the density remains constant, the difference between the adjusted anti-wrinkle effect and the original effect will be small, which is beneficial to ensuring the stability of the anti-wrinkle effect of the target composition. The purpose of adjusting the mass percentage of the components while keeping the density constant is to ensure that the volume of the same mass of target composition remains unchanged after adjustment, which has advantages such as not needing to change the container used to fill the target composition.

[0069] S440, obtain the priority value of the candidate density based on the first and second values ​​of the specified candidate density; the priority value of the specified candidate density is negatively correlated with both the first and second values ​​of the specified candidate density.

[0070] In this embodiment, the smaller the first value of the candidate density and the smaller the second value of the candidate density, the better the anti-wrinkle effect of the target composition at the candidate density, and the smaller the difference in anti-wrinkle effect among different mass percentage combinations at the candidate density. As a specific implementation, obtaining the priority value of the candidate density based on the first and second values ​​includes: obtaining the priority value of the candidate density based on the first value of the candidate density, a first preset weight, the second value of the candidate density, and the second preset weight. Optionally, the first and second preset weights are empirical values, the sum of the first and second preset weights is 1, and the priority value of the candidate density is: -w1×a-w2×b, where w1 and w2 are the first and second preset weights, respectively, a is the normalized first value of the specified candidate density, and b is the normalized second value of the specified candidate density. Those skilled in the art will understand that the normalization process is prior art and will not be described further here.

[0071] This embodiment utilizes orthogonal experimental design to efficiently obtain composition samples at different densities. By mapping relationships, its anti-wrinkle effect is predicted. The mean and variance are combined to comprehensively evaluate the merits of candidate densities from two dimensions: effect and variability. The weighting settings reflect different emphases on effect and variability. Therefore, this embodiment achieves quantitative evaluation and ranking of candidate densities, avoiding the randomness and inefficiency of traditional blind trial-and-error methods. It can quickly locate candidate densities with good average anti-wrinkle effect and small variability, and can screen out candidate densities with good average anti-wrinkle effect and small variability.

[0072] S500, the candidate density with the highest priority value in the candidate density set is determined as the target density, and the mass percentage of the component in the target composition with the lowest wrinkle change in the corresponding image and the density of the target density is determined as the target mass percentage of the component in the target composition.

[0073] In this embodiment, the priority values ​​of each candidate density in the candidate density set are compared, and the candidate density with the highest priority value is identified and determined as the target density. For all target compositions with the target density, the amount of wrinkle change in their corresponding images is compared, and the composition with the smallest amount of wrinkle change is selected. The mass percentage of the component in this composition is determined as the target mass percentage of the target composition.

[0074] In this embodiment, the candidate density with the highest priority value comprehensively considers the average anti-wrinkle effect and the differences in anti-wrinkle effects of different mass percentage combinations. Based on this, the composition with the smallest wrinkle change is selected, ensuring that the final determined component mass percentage can achieve a better anti-wrinkle effect. Thus, this embodiment determines the preferred component mass percentage of the target composition through a dual screening mechanism of the highest priority value + the smallest wrinkle change, so that the anti-wrinkle effect of the target composition is better and it is easy to adjust the component mass percentage during the production process (when the mass percentage of the component in the target composition is the target mass percentage, if the mass percentage of the component is adjusted while the density of the target composition remains unchanged, the difference between the adjusted anti-wrinkle effect and the original effect is small, ensuring the adjusted anti-wrinkle effect), thus achieving the goal of optimizing the production of the target composition.

[0075] This embodiment obtains a mapping relationship between the mass percentage of components in each target composition sample in the target composition sample set and the amount of wrinkle change in the image. Based on this mapping relationship, this embodiment can quickly obtain the priority value corresponding to each candidate density in the candidate density set of the target composition, without having to conduct a large number of experiments to verify the amount of wrinkle change in the image corresponding to each candidate density of the target composition. This reduces the cost of blind trial and error and improves the efficiency of component production optimization of the target composition. Moreover, this embodiment can automatically obtain the amount of wrinkle change of the experimental object based on image processing technology. Compared with the method of manually observing the experimental object, the amount of wrinkle change obtained by this embodiment is more objective and accurate.

[0076] Example 2:

[0077] This embodiment provides a component production optimization system for a target composition, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps:

[0078] Obtain an image set for each target composition sample in the target composition sample set; the target composition sample set includes several target composition samples, and the components of any target composition sample include AKG, SOD and nicotinamide, and the mass percentage of the components in different target composition samples is different; the image set of any target composition sample includes several image pairs of experimental subjects, and the image pair of any experimental subject includes a control image and an experimental image of that experimental subject.

[0079] The amount of wrinkle change in the image corresponding to each target composition sample is obtained from the image set of each target composition sample in the target composition sample set; the amount of wrinkle change in the image corresponding to any target composition sample is the average amount of wrinkle change in the images of all experimental subjects corresponding to that target composition sample, and the amount of wrinkle change in the image of any experimental subject is the difference between the wrinkle ratio in the experimental image of that experimental subject and the wrinkle ratio in the control image.

[0080] The mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image of each target composition sample in the target composition sample set is obtained; in the mapping relationship, the mass percentage of AKG, the mass percentage of SOD and the mass percentage of nicotinamide are independent variables, and the amount of wrinkle change in the image is the dependent variable.

[0081] The priority value corresponding to each candidate density in the candidate density set of the target composition is obtained according to the mapping relationship; the candidate density set includes several candidate densities, and the priority value corresponding to any candidate density is obtained according to the amount of wrinkle change in the image corresponding to the target composition with that candidate density.

[0082] The candidate density with the highest priority value in the candidate density set is determined as the target density, and the mass percentage of the component in the target composition with the lowest wrinkle change in the corresponding image and the target density is determined as the target mass percentage of the component in the target composition.

[0083] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. It should also be understood that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for optimizing the production of components of a target composition, characterized in that, The method includes the following steps: Obtain an image set for each target composition sample in the target composition sample set; the target composition sample set includes several target composition samples, and the components of any target composition sample include AKG, SOD and nicotinamide, and the mass percentage of the components in different target composition samples is different; the image set of any target composition sample includes several image pairs of experimental subjects, and the image pair of any experimental subject includes a control image and an experimental image of that experimental subject; The amount of wrinkle change in the image corresponding to each target composition sample is obtained from the image set of each target composition sample in the target composition sample set; the amount of wrinkle change in the image corresponding to any target composition sample is the average amount of wrinkle change in the images of all experimental subjects corresponding to that target composition sample, and the amount of wrinkle change in the image of any experimental subject is the difference between the wrinkle ratio of the experimental image of that experimental subject and the wrinkle ratio of the control image. The mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image of each target composition sample in the target composition sample set is obtained; in the mapping relationship, the mass percentage of AKG, the mass percentage of SOD and the mass percentage of nicotinamide are independent variables, and the amount of wrinkle change in the image is the dependent variable. The priority value corresponding to each candidate density in the candidate density set of the target composition is obtained according to the mapping relationship; the candidate density set includes several candidate densities, and the priority value corresponding to any candidate density is obtained according to the amount of wrinkle change in the image corresponding to the target composition with that candidate density; The candidate density with the highest priority value in the candidate density set is determined as the target density, and the mass percentage of the component in the target composition with the lowest wrinkle change in the corresponding image and the density of the target density is determined as the target mass percentage of the component in the target composition. The priority value corresponding to each candidate density in the candidate density set of the target composition is obtained according to the mapping relationship, including: The amount of wrinkle change in the image corresponding to the target composition with a specified candidate density is obtained according to the mapping relationship; the specified candidate density is any candidate density in the candidate density set. The average value of wrinkle changes in the image corresponding to the target composition with a specified candidate density is determined as the first value of the specified candidate density; The variance of the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density is determined as the second value of the specified candidate density; The priority value of the candidate density is obtained based on the first and second values ​​of the specified candidate density; the priority value of the specified candidate density is negatively correlated with both the first and second values ​​of the specified candidate density.

2. The method for optimizing the production of components of the target composition according to claim 1, characterized in that, Obtaining the priority value of candidate density based on the first and second values ​​of candidate density includes: obtaining the priority value of candidate density based on the first value of candidate density, the first preset weight, the second value of candidate density, and the second preset weight.

3. The method for optimizing the production of components of the target composition according to claim 1, characterized in that, The process of obtaining a target composition with a specified candidate density includes: Obtain the mass percentage range of each component in the target composition, and obtain the mass percentage corresponding to each level of the component based on the mass percentage range of any component and the preset level number; An orthogonal array matching the number of components and the preset number of levels in the target composition is used to construct a component ratio combination matrix; The target composition was prepared according to the component ratio combination matrix, and the density of each target composition was obtained; Screening target compositions with a specified candidate density from the prepared target compositions.

4. The method for optimizing the production of components of the target composition according to claim 3, characterized in that, Setting the mass percentage corresponding to each level of a component based on the mass percentage range of any component and a preset number of levels includes: dividing the mass percentage range of any component into equal parts according to the preset number of levels to obtain the mass percentage corresponding to each level of the component.

5. The method for optimizing the production of components of the target composition according to claim 1, characterized in that, Obtaining the mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image of each target composition sample in the target composition sample set includes: setting a preset fitting function, fitting the function to the mass percentage of the components in each target composition sample in the target composition sample set and the corresponding amount of wrinkle change in the image, and determining the fitted function expression as the mapping relationship between the mass percentage of the components in the target composition and the amount of wrinkle change in the image.

6. The method for optimizing the production of components of the target composition according to claim 5, characterized in that, The default fitting function is a multivariate quadratic polynomial function.

7. The method for optimizing the production of components of the target composition according to claim 1, characterized in that, Obtaining the amount of wrinkle change in the image corresponding to the target composition with a specified candidate density according to the mapping relationship includes: substituting the mass percentage of the component in each target composition with a specified candidate density into the mapping relationship to obtain the amount of wrinkle change in the image corresponding to each target composition with a specified candidate density.

8. The method for optimizing the production of components of the target composition according to claim 1, characterized in that, The wrinkle percentage of the experimental image of any experimental subject is the ratio of wrinkle pixels to the total number of pixels in the experimental image of that experimental subject. The wrinkle percentage of the control image of any experimental subject is the ratio of wrinkle pixels to the total number of pixels in the control image of that experimental subject.

9. A component production optimization system for a target composition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the component production optimization method of the target composition as described in any one of claims 1 to 8.

Images