Process optimization method and system for realizing skin moisturizer

Abstract

The invention relates to the technical field of humectant process optimization, in particular to a process optimization method and system for achieving a skin humectant, and the method comprises the steps: determining a to-be-optimized direction group, designing a multi-dimensional option questionnaire based on the to-be-optimized direction group, carrying out the user experience return visit through a customer experience end and the multi-dimensional option questionnaire, and obtaining a multi-dimensional experience report, constructing a user skin feature matrix by using a multi-dimensional experience report, calculating user confidence, correcting the user skin feature matrix to obtain a corrected skin feature matrix, inputting the corrected skin feature matrix into a humectant proportion adjustment model to obtain a humectant proportion, and performing weighted averaging on a humectant proportion set by using a user confidence set to obtain a humectant proportion; the target humectant proportion is obtained. According to the method, the user universality of humectant process optimization can be improved, and the dynamic change required by a user can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of moisturizing agent process optimization, and in particular to a process optimization method and system for realizing skin moisturizing agent. Background Art

[0002] With growing consumer demand for personalized skincare and increasingly competitive market conditions, optimizing moisturizer processes has become increasingly crucial. An efficient moisturizing process must not only meet the needs of diverse skin types but also be able to rapidly adapt to market changes. Therefore, developing an intelligent moisturizing process optimization method that comprehensively considers user skin characteristics, usage habits, and environmental factors is crucial for enhancing product competitiveness, meeting consumer needs, and promoting sustainable development of the industry.

[0003] Traditional technology usually relies on laboratory testing and user feedback to optimize moisturizer processes. Although this method can achieve moisturizer process optimization to a certain extent, it relies too much on small-scale laboratory data and limited user feedback, resulting in insufficient data sample size, making it difficult to fully cover different skin types and usage scenarios, thereby affecting the universality of the optimization results. Secondly, traditional methods lack real-time and dynamic features, and cannot quickly respond to market changes and dynamic changes in user needs. Summary of the Invention

[0004] The present invention provides a process optimization method and system for realizing skin moisturizing agent, the main purpose of which is to improve the user universality of moisturizing agent process optimization and to meet the dynamic changes of user needs.

[0005] To achieve the above objectives, the present invention provides a process optimization method for producing a skin moisturizing agent, comprising:

[0006] receiving a process optimization instruction, and determining a direction group to be optimized based on the process optimization instruction, wherein the direction group to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction;

[0007] Extracting directions to be optimized from the direction group to be optimized in sequence, designing multiple-choice questions based on the directions to be optimized, and merging the multiple-choice questions corresponding to each direction to be optimized in the direction group to be optimized to obtain a multi-dimensional option questionnaire;

[0008] Identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone APP;

[0009] The customer experience end is extracted sequentially from the customer experience end, and the user experience return visit is conducted using the customer experience end and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group;

[0010] Utilize the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report to construct a user skin quality feature matrix, and calculate the user confidence based on the user skin quality feature group;

[0011] Performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix;

[0012] Inputting the modified skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model;

[0013] The moisturizer ratios and user confidences are summarized to obtain a moisturizer ratio set and a user confidence set. The moisturizer ratio set is weighted averaged using the user confidence set to obtain a target moisturizer ratio. Process optimization for achieving a skin moisturizer is completed based on the target moisturizer ratio.

[0014] Optionally, the designing of multiple-choice questions based on the direction to be optimized includes:

[0015] Determine a binary skin quality problem group based on the direction to be optimized, wherein the binary skin quality problem group includes multiple binary skin quality problems, and the binary skin quality problems include: options of yes and options of no;

[0016] Extracting binary skin quality problems in sequence from the binary skin quality problem group, and designing an extended numerical question group based on the binary skin quality problems, wherein the extended numerical question group includes a plurality of extended numerical questions, and the extended numerical questions include a plurality of numerical options related to the skin quality problems;

[0017] Summarizing the extended numerical problem groups to obtain an extended numerical problem group set;

[0018] Determining a user habit question group, wherein the user habit question group includes a plurality of user habit questions, and the user habit questions include a plurality of numerical options related to the user's usage habits;

[0019] Designing optional input items, wherein the optional input items include image input items;

[0020] Based on the optional input items, user habit question group, binary skin quality question group and extended numerical question group set, the design of multiple-choice questions is completed.

[0021] Optionally, the user experience feedback is conducted using the customer experience terminal and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, including:

[0022] Sending a multi-dimensional option questionnaire to a customer experience end, wherein the multi-dimensional option questionnaire is filled out by pre-confirmed users;

[0023] If it is confirmed that the multi-dimensional option questionnaire is completed, the completed multi-dimensional option questionnaire will be recorded as the multi-dimensional option answer sheet;

[0024] Generate a multi-dimensional experience report based on the multi-dimensional option questionnaire.

[0025] Optionally, generating a multi-dimensional experience report based on the multi-dimensional option questionnaire includes:

[0026] Extracting binary skin quality questions in sequence from the binary skin quality question group of the multi-dimensional option answer sheet, and identifying user binary options for the binary skin quality questions, wherein the user binary options include: option yes and option no;

[0027] If the user's binary option is option yes, then confirm the extended numerical question group corresponding to the binary skin quality problem, and obtain the user numerical option of each extended numerical question in the extended numerical question group to obtain a user numerical option group;

[0028] If the user binary option is option no, the preset zero option group is recorded as the user numerical option group, wherein the zero option group consists of a plurality of zero elements, and the number of zero elements in the zero option group is the same as the number of extended numerical questions in the extended numerical question group;

[0029] Summarizing the user value option groups to obtain a user value option group set;

[0030] Identifying a user habit option group of a user habit question group in a multi-dimensional option answer sheet, and determining a user skin characteristic group based on optional input items in the multi-dimensional option answer sheet;

[0031] The generation of a multi-dimensional experience report is completed based on the user numerical option group set, the user habit option group and the user skin characteristic group.

[0032] Optionally, determining the user's skin quality feature group based on the optional input items in the multi-dimensional option answer sheet includes:

[0033] Determine whether the optional input items in the multi-dimensional option answer sheet are filled in;

[0034] If the optional input items in the multi-dimensional option answer sheet are filled in, then receiving the user skin quality image group of the optional input items, wherein the user skin quality image group includes: an image before moisturizing and an image after moisturizing;

[0035] Performing image detection on the user's skin quality image group to obtain a pre-moisturizing feature group and a post-moisturizing feature group, wherein the pre-moisturizing feature group includes: skin saturation, skin smoothness, and skin glossiness;

[0036] The user's skin quality feature group is obtained by calculating the ratio based on the feature group before moisturizing and the feature group after moisturizing;

[0037] If the optional input items in the multi-dimensional option answer sheet are not filled in, the preset zero feature group will be recorded as the user's skin feature group.

[0038] Optionally, performing image detection on the user skin quality image group to obtain a pre-moisturizing feature group and a post-moisturizing feature group includes:

[0039] Determining an image feature category group, wherein the image feature category group includes: saturation, smoothness, and glossiness;

[0040] Based on the image feature category group, image detection is performed on the pre-moisturizing image and the post-moisturizing image in the user skin type image group to obtain the original pre-moisturizing feature group and the original post-moisturizing feature group;

[0041] According to the preset normal characteristic range group, the original pre-moisturizing characteristic group and the original post-moisturizing characteristic group are screened respectively to obtain the effective pre-moisturizing characteristic group and the effective post-moisturizing characteristic group;

[0042] Perform the same category screening on the effective pre-moisturizing feature group and the effective post-moisturizing feature group to obtain the target pre-moisturizing feature group and the target post-moisturizing feature group;

[0043] The target pre-moisturizing feature group and the target post-moisturizing feature group are respectively filled into the image feature category group to obtain the pre-moisturizing feature group and the post-moisturizing feature group, wherein the vacant positions in the pre-moisturizing feature group and the post-moisturizing feature group are filled with zero values.

[0044] Optionally, the step of constructing a user skin quality feature matrix using the user numerical option set and the user skin quality feature set in the multi-dimensional experience report includes:

[0045] determining the number of options in each user numerical option group in the user numerical option group set, wherein the number of options in different user numerical option groups in the user numerical option group set is the same;

[0046] Based on the number of options, the user skin quality feature group is expanded to obtain an extended skin quality feature group, wherein the number of extended skin quality features in the extended skin quality feature group is the same as the number of options, and the expansion method includes: squaring the data in the user skin quality feature group;

[0047] According to the user numerical option set and the extended skin quality feature set, a user skin quality feature matrix is ​​constructed, where the user skin quality feature matrix is ​​expressed as:

[0048]

[0049] Among them, R represents the user's skin quality feature matrix, (D 1,1 … D 1,n ) represents the first user value option group in the user value option group set, D 1,1 Indicates the first user value option in the first user value option group, D 1,n Indicates the nth user numerical option in the first user numerical option group, where n represents the number of options. (D m,1 … D m,n ) represents the mth user numerical option group in the user numerical option group set, m represents the number of user numerical option groups in the user numerical option group set, D m,1 Indicates the first user value option in the mth user value option group, D m,n Indicates the nth user value option in the mth user value option group, (K1 … K n ) represents the extended skin quality feature group, K1 represents the first extended skin quality feature in the extended skin quality feature group, K n Represents the nth extended skin quality feature.

[0050] Optionally, the calculating of the user confidence based on the user skin quality feature group includes:

[0051] Determine the experience terminal address and experience report date of the customer experience terminal, and obtain a user environment data set of the experience terminal address on the experience report date, wherein the user environment data set includes: climate dryness index and ultraviolet intensity;

[0052] Determine the number of valid features in the user skin quality feature group, and count the number of valid environments in the user environment data group, wherein the valid feature number is the number of data with non-zero values ​​in the user skin quality feature group, and the valid environment number is the number of user environment data in the user environment data group;

[0053] The user confidence is calculated based on the number of valid features and the number of valid environments using the following formula:

[0054]

[0055] Wherein, C represents the user confidence, α1 and α2 represent the preset feature coefficient and the preset environment coefficient respectively, S1 represents the effective feature number, S2 represents the effective environment number, and e represents the natural logarithm.

[0056] Optionally, performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix includes:

[0057] Constructing a user habit vector for the user habit option group;

[0058] Selecting a reference environment data group corresponding to the user environment data group from a preset standard environment data group;

[0059] Based on the user habit vector, the user environment data set and the reference environment data set, the user skin quality feature matrix is ​​adjusted to obtain a modified skin quality feature matrix, wherein the modified skin quality feature matrix is ​​expressed as:

[0060]

[0061] Among them, R' represents the modified skin quality feature matrix, represents the preset habit weight vector, represents the user habit vector, p represents the number of user environment data in the user environment data group or the number of reference environment data in the reference environment data group, represents the i-th user environment data in the user environment data group, Represents the i-th reference environment data in the reference environment data group.

[0062] To achieve the above object, the present invention further provides a process optimization system for producing a skin moisturizing agent, comprising:

[0063] An option questionnaire design module is configured to receive a process optimization instruction, determine a group of directions to be optimized based on the process optimization instruction, wherein the group of directions to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction, sequentially extract directions to be optimized from the group of directions to be optimized, design multiple-option questions based on the directions to be optimized, and combine the multiple-option questions corresponding to each direction to be optimized in the group of directions to be optimized to obtain a multi-dimensional option questionnaire;

[0064] An experience report generation module is used to identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone app, sequentially extract customer experience terminals from the customer experience terminal set, use the customer experience terminals and a multi-dimensional option questionnaire to conduct user experience feedback, and obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group;

[0065] A skin quality matrix construction module is used to construct a user skin quality feature matrix using the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report, calculate the user confidence based on the user skin quality feature group, and perform user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix;

[0066] A formula ratio optimization module is used to input the corrected skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model, which summarizes the moisturizer ratios and user confidence levels to obtain a moisturizer ratio set and a user confidence level set, and uses the user confidence level set to perform weighted averaging on the moisturizer ratio set to obtain a target moisturizer ratio.

[0067] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0068] a memory storing at least one instruction;

[0069] The processor executes the instructions stored in the memory to implement the above-mentioned process optimization method for realizing the skin moisturizing agent.

[0070] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned process optimization method for realizing a skin moisturizer.

[0071] In order to solve the problems described in the background technology, the present invention first receives process optimization instructions and determines the direction group to be optimized. This step accurately locates the functional areas that need to be improved in moisturizers, ensuring that resources are concentrated on the most critical issues. Then, multiple-choice questions are designed and a multi-dimensional option questionnaire is constructed. This step can comprehensively and accurately collect users' specific needs and feedback under different skin types, and provide a structured tool for subsequent user experience return visits. Then, the customer experience terminal set is confirmed and user experience return visits are conducted. Through multiple customer experience terminals, a large amount of actual user experience data can be obtained quickly and easily, which not only increases the diversity of data, but also improves user participation, providing rich first-hand information for subsequent analysis. More importantly, a user skin feature matrix is ​​constructed and user confidence is calculated. This step converts the collected user experience data into a quantitative matrix, making the data more structured and easy to analyze. At the same time, calculating user confidence can evaluate the reliability of the data This provides quality assurance for subsequent model training and ratio adjustment, and then corrects the user's skin quality feature matrix based on user habits. This step takes into account the impact of user usage habits on skin quality characteristics, which can make the data more accurately reflect the user's actual situation, improve the accuracy of model prediction, and ensure that the recommended moisturizer ratio is more in line with the user's actual needs. The corrected matrix is ​​then input into the moisturizer ratio adjustment model. Using the trained neural network model, the optimal moisturizer ratio can be predicted from the corrected skin quality feature matrix quickly and efficiently, greatly shortening the R&D cycle and improving the efficiency of process optimization. Finally, the data is summarized and weighted averaged to obtain the target moisturizer ratio. By comprehensively analyzing the collected ratio data and confidence levels, a target ratio that balances user needs and data reliability can be obtained. This step ensures that the final moisturizer formula can meet the needs of most users, thereby achieving effective process optimization.

[0072] Therefore, the present invention can improve the user universality of moisturizing agent process optimization and can meet the dynamic changes in user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic flow chart of a method for optimizing the process of a skin moisturizer according to an embodiment of the present invention;

[0074] Figure 2 A functional module diagram of a process optimization system for skin moisturizing agents provided by one embodiment of the present invention;

[0075] Figure 3 A schematic structural diagram of an electronic device for implementing the process optimization method for skin moisturizing agents provided in one embodiment of the present invention.

[0076] Description of reference numerals:

[0077] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0078] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0079] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0080] The present embodiment provides a method for optimizing a process for producing a skin moisturizer. The method may be executed by at least one of a server, a terminal, or other electronic device capable of executing the method provided by the present embodiment. In other words, the method may be executed by software or hardware installed on a terminal or server device, where the software may be a blockchain platform. The server may include, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0081] Reference Figure 1 FIG. 1 is a flow chart of a process optimization method for producing a skin moisturizing agent according to an embodiment of the present invention. In this embodiment, the process optimization method for producing a skin moisturizing agent includes:

[0082] S1. Receive a process optimization instruction, and determine a direction group to be optimized based on the process optimization instruction, wherein the direction group to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction.

[0083] It can be understood that the process optimization instruction refers to an instruction initiated manually to optimize the process of the moisturizer. The group of directions to be optimized includes multiple directions to be optimized, and the directions to be optimized refer to the functions of the moisturizer that need to be improved in this process optimization. For example: the dryness optimization direction aims to improve the moisturizing effect of the moisturizer on dry skin, the oiliness optimization direction focuses on improving the applicability of the moisturizer to oily skin, and the sensitivity optimization direction focuses on improving the mildness and tolerance of the moisturizer to sensitive skin.

[0084] S2. Extract the directions to be optimized from the direction group to be optimized in turn, design multiple-choice questions based on the directions to be optimized, merge the multiple-choice questions corresponding to each direction to be optimized in the direction group to obtain a multi-dimensional option questionnaire.

[0085] It is understood that the multiple-choice questions are artificially designed questions about the direction to be optimized. These multiple-choice questions can reflect the improvement of the user's skin quality in the direction to be optimized, and are designed by professionals. The merging of multiple-choice questions refers to placing multiple multiple-choice questions into the same questionnaire. The multi-dimensional option questionnaire refers to a questionnaire that includes multiple-choice questions corresponding to different directions to be optimized.

[0086] Specifically, the design of multiple-choice questions based on the direction to be optimized includes:

[0087] Determine a binary skin quality problem group based on the direction to be optimized, wherein the binary skin quality problem group includes multiple binary skin quality problems, and the binary skin quality problems include: options of yes and options of no;

[0088] Extracting binary skin quality problems in sequence from the binary skin quality problem group, and designing an extended numerical question group based on the binary skin quality problems, wherein the extended numerical question group includes a plurality of extended numerical questions, and the extended numerical questions include a plurality of numerical options related to the skin quality problems;

[0089] Summarizing the extended numerical problem groups to obtain an extended numerical problem group set;

[0090] Determining a user habit question group, wherein the user habit question group includes a plurality of user habit questions, and the user habit questions include a plurality of numerical options related to the user's usage habits;

[0091] Designing optional input items, wherein the optional input items include image input items;

[0092] Based on the optional input items, user habit question group, binary skin quality question group and extended numerical question group set, the design of multiple-choice questions is completed.

[0093] It is understandable that the binary skin quality question refers to a question that only contains two options, wherein the two options contained in the question are option yes and option no. The extended numerical question group refers to a combination of multiple questions with specific numerical options corresponding to the binary skin quality question. When the user selects the binary skin quality question as an option, it will jump to the extended numerical question group to further collect the user's experience. The user habit question refers to a question used to reflect the user's habit of using moisturizers, such as: the number of times a day the moisturizer is used, the time when the moisturizer was first used, etc. These questions all have clear numerical options. The optional input item refers to a question that the user can choose to fill in, such as: taking facial images before and after using moisturizer. Since the image will more clearly show the effect of the moisturizer, but not all users are willing to provide images, this optional input item is provided.

[0094] For example, a binary skin quality question is designed under the direction of dryness optimization: Does your skin often feel dry? The options are: yes and no. The binary skin quality question corresponds to the following extended numerical question group: Extended numerical question 1: How often is your skin dry? The options are: once a day (severity is set to 1), 1 to 3 times a day (severity is set to 2), 3 to 5 times or more a day (severity is set to 3), and more than 5 times a day (severity is set to 4); Extended numerical question 2: How dry is your skin? The options are: occasionally tight (severity is set to 1), often tight, with slight desquamation (severity is set to 2), obvious desquamation and roughness (severity is set to 3), and dryness causing skin cracking (severity is set to 4).

[0095] S3. Confirm a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone APP.

[0096] It can be understood that the customer experience end refers to the receiving software that allows users to receive multi-dimensional option questionnaires, such as a mobile phone APP.

[0097] S4. Extract the customer experience end in sequence from the customer experience end, use the customer experience end and the multi-dimensional option questionnaire to conduct a user experience return visit, and obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group and a user skin characteristic group.

[0098] It can be understood that the multidimensional experience report refers to a multidimensional option questionnaire filled out by the user, wherein the user numerical option group set refers to the numerical set obtained after filling in the binary skin problem group and the extended numerical problem group set, the user habit option group refers to the numerical set obtained after filling in the user habit problem group, and the user skin feature group refers to the numerical combination obtained after analyzing the images in the optional input items.

[0099] Specifically, the user experience feedback is conducted using the customer experience terminal and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, including:

[0100] Sending a multi-dimensional option questionnaire to a customer experience end, wherein the multi-dimensional option questionnaire is filled out by pre-confirmed users;

[0101] If it is confirmed that the multi-dimensional option questionnaire is completed, the completed multi-dimensional option questionnaire will be recorded as the multi-dimensional option answer sheet;

[0102] Generate a multi-dimensional experience report based on the multi-dimensional option questionnaire.

[0103] It is understandable that the multi-dimensional option answer sheet refers to the multi-dimensional option questionnaire after filling in. It should be understood that a submission option should be set in the multi-dimensional option questionnaire. This option is located at the end of the multi-dimensional option questionnaire. When the user selects the submission option, it is determined that the user has completed filling in the multi-dimensional option questionnaire.

[0104] Specifically, the multi-dimensional experience report is generated based on the multi-dimensional option questionnaire, including:

[0105] Extracting binary skin quality questions in sequence from the binary skin quality question group of the multi-dimensional option answer sheet, and identifying user binary options for the binary skin quality questions, wherein the user binary options include: option yes and option no;

[0106] If the user's binary option is option yes, then confirm the extended numerical question group corresponding to the binary skin quality problem, and obtain the user numerical option of each extended numerical question in the extended numerical question group to obtain a user numerical option group;

[0107] If the user binary option is option no, the preset zero option group is recorded as the user numerical option group, wherein the zero option group consists of a plurality of zero elements, and the number of zero elements in the zero option group is the same as the number of extended numerical questions in the extended numerical question group;

[0108] Summarizing the user value option groups to obtain a user value option group set;

[0109] Identifying a user habit option group of a user habit question group in a multi-dimensional option answer sheet, and determining a user skin characteristic group based on optional input items in the multi-dimensional option answer sheet;

[0110] The generation of a multi-dimensional experience report is completed based on the user numerical option group set, the user habit option group and the user skin characteristic group.

[0111] For example, a binary skin quality question is: Does your skin often feel dry? The options are: Yes and No. If the user selects Yes, the user will be redirected to the extended numerical question group corresponding to the binary skin quality question: Extended numerical question 1: How often is your skin dry? The options are: once a day (severity is set to 1), 1 to 3 times a day (severity is set to 2), 3 to 5 times or more a day (severity is set to 3), and more than 5 times a day (severity is set to 4). Extended numerical question 2: How dry is your skin? The options are: Occasionally feeling tight (severity is set to 1), often feeling tight, with slight desquamation (severity is set to 2), obvious desquamation and roughness (severity is set to 3), and dryness causing skin cracking (severity is set to 4). The user's options for the above extended numerical question group are: once a day (severity is set to 1), often feeling tight, with slight desquamation (severity is set to 2), and the user numerical option group is (1,2). If the user selects No, the zero option group is set: (0,0), and the zero option group is recorded as the user numerical option group.

[0112] Specifically, the method of determining the user's skin quality feature group based on the optional input items in the multi-dimensional option answer sheet includes:

[0113] Determine whether the optional input items in the multi-dimensional option answer sheet are filled in;

[0114] If the optional input items in the multi-dimensional option answer sheet are filled in, then receiving the user skin quality image group of the optional input items, wherein the user skin quality image group includes: an image before moisturizing and an image after moisturizing;

[0115] Performing image detection on the user's skin quality image group to obtain a pre-moisturizing feature group and a post-moisturizing feature group, wherein the pre-moisturizing feature group includes: skin saturation, skin smoothness, and skin glossiness;

[0116] The user's skin quality feature group is obtained by calculating the ratio based on the feature group before moisturizing and the feature group after moisturizing;

[0117] If the optional input items in the multi-dimensional option answer sheet are not filled in, the preset zero feature group will be recorded as the user's skin feature group.

[0118] It is understood that the user skin quality image group refers to the combination of images entered by the user in the optional input items, wherein the pre-moisturizing image and the post-moisturizing image refer to images taken before and after the user applies a moisturizer, respectively. The pre-moisturizing feature group and the post-moisturizing feature group refer to the combination of features in the pre-moisturizing image and the post-moisturizing feature group, respectively, used to represent the moisturizing effect of the skin. Among them, skin saturation refers to the color saturation of the user's skin in the pre-moisturizing image. This saturation is used to represent the moisture content of the user's skin. The greater the saturation, the greater the moisture content of the skin. Skin smoothness refers to the image texture smoothness of the pre-moisturizing image. The contrast of the skin texture can be analyzed using a gray-level co-occurrence matrix (GLCM), and the contrast is recorded as texture smoothness. This skin smoothness is used to represent the smoothness of the user's skin. The higher the skin smoothness, the greater the skin smoothness. Skin glossiness refers to the glossiness of the skin area in the pre-moisturizing image. It is represented by the glossiness index (LI). The higher the skin glossiness, the smoother the user's skin. Corresponding to the explanations of each parameter in the pre-moisturizing feature group, the post-moisturizing feature group also has the same parameters and corresponding parameter explanations.

[0119] For example, a feature group before moisturizing and a feature group after moisturizing are (A1, A2, A3) and (B1, B2, B3), respectively, where A1, A2 and A3 represent the skin saturation, skin smoothness and skin glossiness in the feature group before moisturizing, respectively. B1, B2 and B3 have the same definition and are not repeated here. Taking A1 and B1 as an example, the user skin quality feature is calculated as: (B1-A1) / (1+A1), thereby obtaining the user skin quality feature group.

[0120] Furthermore, when the optional input items are not filled in, in order to ensure the correctness of the subsequent construction of the user skin quality feature matrix, it is necessary to set a zero feature group, which includes multiple zero numbers, and the number of zero numbers is the same as the number of user skin quality features in the user skin quality feature group.

[0121] In detail, the image detection is performed on the user skin type image group to obtain the pre-moisturizing feature group and the post-moisturizing feature group, including:

[0122] Determining an image feature category group, wherein the image feature category group includes: saturation, smoothness, and glossiness;

[0123] Based on the image feature category group, image detection is performed on the pre-moisturizing image and the post-moisturizing image in the user skin type image group to obtain the original pre-moisturizing feature group and the original post-moisturizing feature group;

[0124] According to the preset normal characteristic range group, the original pre-moisturizing characteristic group and the original post-moisturizing characteristic group are screened respectively to obtain the effective pre-moisturizing characteristic group and the effective post-moisturizing characteristic group;

[0125] Perform the same category screening on the effective pre-moisturizing feature group and the effective post-moisturizing feature group to obtain the target pre-moisturizing feature group and the target post-moisturizing feature group;

[0126] The target pre-moisturizing feature group and the target post-moisturizing feature group are respectively filled into the image feature category group to obtain the pre-moisturizing feature group and the post-moisturizing feature group, wherein the vacant positions in the pre-moisturizing feature group and the post-moisturizing feature group are filled with zero values.

[0127] It should be explained that the image feature category group refers to the type of numerical value that needs to be obtained by artificially setting image detection, which can be set as: saturation, smoothness and glossiness, which means that the image detection needs to obtain the saturation, smoothness and glossiness of the user's skin in the image. The original pre-moisturizing feature group and the original post-moisturizing feature group respectively refer to the numerical combination of each category in the above-mentioned image feature category group obtained after image detection. However, since the image here is taken by the user himself, and different users use different equipment, shooting environments and other conditions, not all features obtained after image detection are valid features. For example, the ambient illumination of a user's shooting is low, which makes the accuracy of the glossiness features in the pre-moisturizing feature group or the post-moisturizing feature group low. Here, the artificially set normal feature range group can be used for screening: the original pre-moisturizing features and original post-moisturizing features that are not in the normal feature range group are eliminated, and the eliminated original pre-moisturizing feature group and original post-moisturizing feature group are recorded as the effective pre-moisturizing feature group and effective moisturizing feature group. After-moisturizing feature group, since the feature categories in the effective pre-moisturizing feature group and the effective post-moisturizing feature group are different, in order to enable the two to calculate the user skin feature group in the subsequent process, the same category screening is required: the intersection between the effective pre-moisturizing feature group and the effective post-moisturizing feature group is extracted. The intersection here refers to the part with the same image feature category between them. Finally, in order to ensure that the target pre-moisturizing feature group and the target post-moisturizing feature group of different users have the same number of parameters, it is necessary to replace the eliminated features with zero values. The replaced target pre-moisturizing feature group and target post-moisturizing feature group are the pre-moisturizing feature group and the post-moisturizing feature group.

[0128] S5. Utilize the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report to construct a user skin quality feature matrix, and calculate the user confidence based on the user skin quality feature group.

[0129] It is understood that the user skin quality matrix refers to a matrix used to represent the moisturizing effect of a moisturizer on a user's skin, and the user confidence level refers to a numerical value representing the degree of confidence in the user's skin quality characteristics. Because different users may have different levels of data completeness (for example, a user may not have the aforementioned images), data with lower user confidence levels will be weighted less heavily in the subsequent adjustment of the moisturizer ratio.

[0130] Specifically, the method of constructing a user skin quality feature matrix using the user numerical option set and the user skin quality feature set in the multi-dimensional experience report includes:

[0131] determining the number of options in each user numerical option group in the user numerical option group set, wherein the number of options in different user numerical option groups in the user numerical option group set is the same;

[0132] Based on the number of options, the user skin quality feature group is expanded to obtain an extended skin quality feature group, wherein the number of extended skin quality features in the extended skin quality feature group is the same as the number of options, and the expansion method includes: squaring the data in the user skin quality feature group;

[0133] According to the user numerical option set and the extended skin quality feature set, a user skin quality feature matrix is ​​constructed, where the user skin quality feature matrix is ​​expressed as:

[0134]

[0135] Among them, R represents the user's skin quality feature matrix, (D 1,1 … D 1,n ) represents the first user value option group in the user value option group set, D 1,1 Indicates the first user value option in the first user value option group, D 1,n Indicates the nth user value option in the first user value option group, where n represents the number of options. (D m,1 … D m,n ) represents the mth user numerical option group in the user numerical option group set, m represents the number of user numerical option groups in the user numerical option group set, D m,1 Indicates the first user value option in the mth user value option group, D m,n Indicates the nth user value option in the mth user value option group, (K1 … K n ) represents the extended skin quality feature group, K1 represents the first extended skin quality feature in the extended skin quality feature group, K n Represents the nth extended skin quality feature.

[0136] It is understandable that the number of options refers to the number of user numerical options in the user numerical option group. The extended skin quality feature group refers to the user skin quality feature group after expansion. Since the number of user skin quality features in the user skin quality feature group is less than the number of options, it is necessary to expand the user skin quality feature group so that the number of features in the extended skin quality feature group obtained after expansion is the same as the number of options, wherein the expansion method is: extract the user skin quality features in the user skin quality feature group in sequence, and perform square or cube or other preset function processing on the user skin quality features to obtain the expansion number, and add the expansion number to the user skin quality feature group, repeat the above steps of extracting the user skin quality features in the user skin quality feature group in sequence until the number of features in the extended user skin quality feature group is equal to the number of options, and stop the above steps of extracting in sequence, and record the user skin quality feature group at this time as the extended skin quality feature group.

[0137] In detail, the calculation of user confidence based on the user skin quality feature group includes:

[0138] Determine the experience terminal address and experience report date of the customer experience terminal, and obtain a user environment data set of the experience terminal address on the experience report date, wherein the user environment data set includes: climate dryness index and ultraviolet intensity;

[0139] Determine the number of valid features in the user skin quality feature group, and count the number of valid environments in the user environment data group, wherein the valid feature number is the number of data with non-zero values ​​in the user skin quality feature group, and the valid environment number is the number of user environment data in the user environment data group;

[0140] The user confidence is calculated based on the number of valid features and the number of valid environments using the following formula:

[0141]

[0142] Wherein, C represents the user confidence, α1 and α2 represent the preset feature coefficient and the preset environment coefficient respectively, S1 represents the effective feature number, S2 represents the effective environment number, and e represents the natural logarithm.

[0143] It is understood that the experience end address refers to the IP address of the customer experience end, the experience report date refers to the date when the user completes the multi-dimensional option questionnaire, and the user environment data group is a combination of the change index of the user's IP address at the time of the experience report date, wherein the climate dryness index characterizes the dryness of the experience end address. It should be noted that the specific data contained in the user environment data group can be adjusted manually. The skin quality of users in different regions and climates will also be different, so it is necessary to obtain the environmental parameters when the user completes the multi-dimensional option questionnaire. The more user environment data in the user environment data group, the higher the completeness of the environmental parameters. The effective feature number refers to the number of features in the user skin quality feature group whose values ​​are not 0. Due to the above-mentioned step of filling the vacant positions in the pre-moisturizing feature group and the post-moisturizing feature group with zero values, there are features with a value of 0 in the user skin quality feature group. The features here will not represent any information about the user's skin quality, so the statistical effective feature number can reflect the data completeness of the user's skin quality features. The feature coefficient and the environment coefficient refer to the constants set manually to represent the weights of the effective feature number and the effective environment number, respectively.

[0144] S6. Performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix.

[0145] It is understandable that due to the different daily habits and environmental conditions of different users, for example, some users use moisturizers at different times a day, and the climate dryness of the users' regions is different, etc., the information represented by the above-mentioned user skin quality feature matrix will be interfered by the differences in user habits and environmental conditions. In order to suppress this interference, a user habit option group (such as how many times a day to spray moisturizer, etc.) can be included in the questionnaire to obtain the user's habit data on using moisturizer and the environmental data of the user's address (i.e., the user environmental data group). Based on these habit data and environmental data, the user skin quality feature matrix can be adjusted, so that the adjusted and modified skin quality feature matrix has stronger representativeness.

[0146] In detail, the user habit modification of the user skin quality feature matrix according to the user habit option group to obtain the modified skin quality feature matrix includes:

[0147] Constructing a user habit vector for the user habit option group;

[0148] Selecting a reference environment data group corresponding to the user environment data group from a preset standard environment data group;

[0149] Based on the user habit vector, the user environment data set and the reference environment data set, the user skin quality feature matrix is ​​adjusted to obtain a modified skin quality feature matrix, wherein the modified skin quality feature matrix is ​​expressed as:

[0150]

[0151] Among them, R' represents the modified skin quality feature matrix, represents the preset habit weight vector, represents the user habit vector, p represents the number of user environment data in the user environment data group or the number of reference environment data in the reference environment data group, represents the i-th user environment data in the user environment data group, Represents the i-th reference environment data in the reference environment data group.

[0152] It is understood that the user habit vector refers to a vector composed of the user habit options in the user habit option group. The standard environment data set refers to an array of manually set standard environment data. This standard environment data set is used to train the neural network model. The number of environmental data included in the standard environment data set must be greater than or equal to the number of environmental data in the user environment data set. Therefore, it is necessary to select a reference environment data set from the standard environment data set that has the same environmental data category as the user environment data set. For example, if the standard environment data set is: (climate dryness index Q1, ultraviolet intensity Q2, relative humidity Q3, sunshine time Q4), and the user environment data set is: (climate dryness index E1, ultraviolet intensity E2, relative humidity E3), then the data in the standard environment data set corresponding to the user environment data set is: climate dryness index Q1, ultraviolet intensity Q2, relative humidity Q3. Therefore, the reference environment data set is: (climate dryness index Q1, ultraviolet intensity Q2, relative humidity Q3). The habit weight vector refers to a vector composed of the weights of each element in the manually set user habit vector.

[0153] Furthermore, in the above formula for calculating and correcting the skin quality characteristic matrix, The elements in the user habit vector can be mapped to the (0,1) interval, thereby dynamically scaling the values ​​of each element in the user skin quality feature matrix. It is an environmental compensation item. By comparing the data in the user environment data set with the data in the reference environment data set, the user skin quality feature matrix can be further scaled so that the environment in which the user skin quality feature matrix is ​​located is close to the reference environment data set.

[0154] S7. Inputting the corrected skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model.

[0155] It should be explained that the moisturizer ratio adjustment model refers to a model obtained by artificially pre-training a neural network. The model can obtain a moisturizer ratio that conforms to the skin quality information contained in the modified skin quality feature matrix by modifying the skin quality feature matrix. The training of the neural network model is as follows: first, multiple testers are obtained, and the multiple testers are at the same address, and a standard environmental data set at the address is measured. Then, the multiple testers are used to experience the moisturizer and obtain multiple training skin quality feature matrices. The method for obtaining the matrix is ​​the same as the method for obtaining the above-mentioned user skin quality feature matrix. Professionals communicate with the multiple testers. After understanding the usage requirements and ideas of the multiple testers, the professionals improve the original moisturizer ratio to obtain a training moisturizer ratio. The above steps are repeated to obtain a large amount of training data. The training data is a large amount of training skin quality feature matrices and a large amount of training moisturizer ratios (the specific amount of data is determined manually and is not specifically limited here). The neural network is trained using the obtained large amount of training data to obtain a moisturizer ratio adjustment model, wherein the number of neurons in the input layer of the neural network is the same as the number of matrix elements in the training skin quality feature matrix, and the number of neurons in the output layer is the same as the number of each material in the training moisturizer ratio.

[0156] Furthermore, the moisturizing agent ratio refers to the output value of the moisturizing agent ratio adjustment model.

[0157] For example, after a corrected skin quality feature matrix is ​​input into the moisturizer ratio adjustment model, the model output is: hyaluronic acid: 1.5%, glycerin: 7%, butylene glycol: 3%, allantoin: 0.7%, plant extract: 2%, deionized water: 82.5%, then the moisturizer ratio can be obtained as: 1.5%: 7%: 3%: 0.7%: 2%: 82.5%.

[0158] S8. Summarize the moisturizer ratios and user confidences to obtain a moisturizer ratio set and a user confidence set, perform weighted averaging on the moisturizer ratio set using the user confidence set to obtain a target moisturizer ratio, and complete process optimization for achieving a skin moisturizer based on the target moisturizer ratio.

[0159] It should be explained that the target moisturizer ratio refers to the value obtained after weighted average, and the formula involved in the weighted average is as follows:

[0160]

[0161] Among them, F m represents the target moisturizing agent ratio, z represents the number of user confidences in the user confidence set or the number of moisturizing agent ratios in the moisturizing agent ratio set, C j represents the jth user confidence in the user confidence set, Fj represents the jth moisturizing agent ratio in the moisturizing agent ratio set, C ALL Represents the sum of all user confidences in the user confidence set, where in item C j ×F j In the middle, C j With F j Multiply the weights of each material in the formula. For example, in the ratio of 1.5%: 7%: 3%: 0.7%: 2%: 82.5%, 1.5% is the weight of one material.

[0162] In order to solve the problems described in the background technology, the present invention first receives process optimization instructions and determines the direction group to be optimized. This step accurately locates the functional areas that need to be improved in moisturizers, ensuring that resources are concentrated on the most critical issues. Then, multiple-choice questions are designed and a multi-dimensional option questionnaire is constructed. This step can comprehensively and accurately collect users' specific needs and feedback under different skin types, and provide a structured tool for subsequent user experience return visits. Then, the customer experience terminal set is confirmed and user experience return visits are conducted. Through multiple customer experience terminals, a large amount of actual user experience data can be obtained quickly and easily, which not only increases the diversity of data, but also improves user participation, providing rich first-hand information for subsequent analysis. More importantly, a user skin feature matrix is ​​constructed and user confidence is calculated. This step converts the collected user experience data into a quantitative matrix, making the data more structured and easy to analyze. At the same time, calculating user confidence can evaluate the reliability of the data This provides quality assurance for subsequent model training and ratio adjustment, and then corrects the user's skin quality feature matrix based on user habits. This step takes into account the impact of user usage habits on skin quality characteristics, which can make the data more accurately reflect the user's actual situation, improve the accuracy of model prediction, and ensure that the recommended moisturizer ratio is more in line with the user's actual needs. The corrected matrix is ​​then input into the moisturizer ratio adjustment model. Using the trained neural network model, the optimal moisturizer ratio can be predicted from the corrected skin quality feature matrix quickly and efficiently, greatly shortening the R&D cycle and improving the efficiency of process optimization. Finally, the data is summarized and weighted averaged to obtain the target moisturizer ratio. By comprehensively analyzing the collected ratio data and confidence levels, a target ratio that balances user needs and data reliability can be obtained. This step ensures that the final moisturizer formula can meet the needs of most users, thereby achieving effective process optimization.

[0163] like Figure 2 FIG. 1 is a functional module diagram of a process optimization system for realizing skin moisturizing agent according to an embodiment of the present invention.

[0164] The process optimization system 100 for producing a skin moisturizer according to the present invention can be installed in an electronic device. Depending on the functionality implemented, the process optimization system 100 can include a questionnaire design module 101, a user experience report generation module 102, a skin quality matrix construction module 103, and a formula ratio optimization module 104. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These modules are stored in the electronic device's memory.

[0165] The option questionnaire design module 101 is configured to receive a process optimization instruction, determine a group of directions to be optimized based on the process optimization instruction, wherein the group of directions to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction, sequentially extract directions to be optimized from the group of directions to be optimized, design multiple-option questions based on the directions to be optimized, and combine the multiple-option questions corresponding to each direction to be optimized in the group of directions to be optimized to obtain a multi-dimensional option questionnaire;

[0166] The experience report generation module 102 is used to identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminals include mobile phone apps, sequentially extract customer experience terminals from the customer experience terminal set, and use the customer experience terminals and a multi-dimensional option questionnaire to conduct user experience feedback to obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group;

[0167] The skin quality matrix construction module 103 is used to construct a user skin quality feature matrix using the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report, calculate the user confidence based on the user skin quality feature group, and perform user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix;

[0168] The formula ratio optimization module 104 is used to input the corrected skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model, which summarizes the moisturizer ratios and user confidence levels to obtain a moisturizer ratio set and a user confidence level set, and uses the user confidence level set to perform weighted averaging on the moisturizer ratio set to obtain a target moisturizer ratio.

[0169] In detail, the modules in the process optimization system 100 for realizing skin moisturizing agent in the embodiment of the present invention are used in the same manner as above. Figure 1 The same technical means as described in the process optimization method for achieving skin moisturizers are used and can produce the same technical effects, so they will not be repeated here.

[0170] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing a process optimization method for a skin moisturizer provided by an embodiment of the present invention.

[0171] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a process optimization method program for implementing a skin moisturizer.

[0172] Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Furthermore, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code for the process optimization method program for implementing skin moisturizers, but can also be used to temporarily store data that has been output or is to be output.

[0173] In some embodiments, the processor 10 may be comprised of an integrated circuit, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (control unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or runs programs or modules stored in the memory 11 (e.g., a program for implementing a process optimization method for skin moisturizers) and accesses data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0174] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0175] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0176] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management system, thereby implementing functions such as charge management, discharge management, and power consumption management through the power management system. The power source may further include any components such as one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may further include a variety of sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be described in detail here.

[0177] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0178] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0179] The program for realizing the process optimization method of skin moisturizing agent stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:

[0180] receiving a process optimization instruction, and determining a direction group to be optimized based on the process optimization instruction, wherein the direction group to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction;

[0181] Extracting directions to be optimized from the direction group to be optimized in sequence, designing multiple-choice questions based on the directions to be optimized, and merging the multiple-choice questions corresponding to each direction to be optimized in the direction group to be optimized to obtain a multi-dimensional option questionnaire;

[0182] Identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone APP;

[0183] The customer experience end is extracted sequentially from the customer experience end, and the user experience return visit is conducted using the customer experience end and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group;

[0184] Utilize the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report to construct a user skin quality feature matrix, and calculate the user confidence based on the user skin quality feature group;

[0185] Performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix;

[0186] Inputting the modified skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model;

[0187] The moisturizer ratios and user confidences are summarized to obtain a moisturizer ratio set and a user confidence set. The moisturizer ratio set is weighted averaged using the user confidence set to obtain a target moisturizer ratio. Process optimization for achieving a skin moisturizer is completed based on the target moisturizer ratio.

[0188] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0189] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0190] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0191] receiving a process optimization instruction, and determining a direction group to be optimized based on the process optimization instruction, wherein the direction group to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction;

[0192] Extracting directions to be optimized from the direction group to be optimized in sequence, designing multiple-choice questions based on the directions to be optimized, and merging the multiple-choice questions corresponding to each direction to be optimized in the direction group to be optimized to obtain a multi-dimensional option questionnaire;

[0193] Identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone APP;

[0194] The customer experience end is extracted sequentially from the customer experience end, and the user experience return visit is conducted using the customer experience end and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group;

[0195] Utilize the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report to construct a user skin quality feature matrix, and calculate the user confidence based on the user skin quality feature group;

[0196] Performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix;

[0197] Inputting the modified skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model;

[0198] The moisturizer ratios and user confidences are summarized to obtain a moisturizer ratio set and a user confidence set. The moisturizer ratio set is weighted averaged using the user confidence set to obtain a target moisturizer ratio. Process optimization for achieving a skin moisturizer is completed based on the target moisturizer ratio.

[0199] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0200] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0201] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0202] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A process optimization method for achieving a skin moisturizing agent, characterized in that: The method comprises: receiving a process optimization instruction, and determining a direction group to be optimized based on the process optimization instruction, wherein the direction group to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction; Extracting directions to be optimized from the direction group to be optimized in sequence, designing multiple-choice questions based on the directions to be optimized, and merging the multiple-choice questions corresponding to each direction to be optimized in the direction group to be optimized to obtain a multi-dimensional option questionnaire; Identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone APP; The customer experience end is extracted sequentially from the customer experience end, and the user experience return visit is conducted using the customer experience end and a multi-dimensional option questionnaire to obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group; Utilize the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report to construct a user skin quality feature matrix, and calculate the user confidence based on the user skin quality feature group; Performing user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix; Inputting the modified skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model; The moisturizer ratios and user confidences are summarized to obtain a moisturizer ratio set and a user confidence set. The moisturizer ratio set is weighted averaged using the user confidence set to obtain a target moisturizer ratio. Process optimization for achieving a skin moisturizer is completed based on the target moisturizer ratio.

2. The process optimization method for achieving a skin moisturizing agent according to claim 1, wherein: The multiple-choice problem is designed based on the direction to be optimized, including: Determine a binary skin quality problem group based on the direction to be optimized, wherein the binary skin quality problem group includes multiple binary skin quality problems, and the binary skin quality problems include: options of yes and options of no; Extracting binary skin quality problems in sequence from the binary skin quality problem group, and designing an extended numerical question group based on the binary skin quality problems, wherein the extended numerical question group includes a plurality of extended numerical questions, and the extended numerical questions include a plurality of numerical options related to the skin quality problems; Summarizing the extended numerical problem groups to obtain an extended numerical problem group set; Determining a user habit question group, wherein the user habit question group includes a plurality of user habit questions, and the user habit questions include a plurality of numerical options related to the user's usage habits; Designing optional input items, wherein the optional input items include image input items; Based on the optional input items, user habit question group, binary skin quality question group and extended numerical question group set, the design of multiple-choice questions is completed.

3. The process optimization method for achieving a skin moisturizing agent according to claim 2, wherein: The user experience feedback is conducted using the customer experience terminal and the multi-dimensional option questionnaire to obtain a multi-dimensional experience report, including: Sending a multi-dimensional option questionnaire to a customer experience end, wherein the multi-dimensional option questionnaire is filled out by pre-confirmed users; If it is confirmed that the multi-dimensional option questionnaire is completed, the completed multi-dimensional option questionnaire will be recorded as the multi-dimensional option answer sheet; Generate a multi-dimensional experience report based on the multi-dimensional option questionnaire.

4. The process optimization method for achieving a skin moisturizing agent according to claim 3, wherein: The multi-dimensional experience report is generated based on the multi-dimensional option questionnaire, including: Extracting binary skin quality questions in sequence from the binary skin quality question group of the multi-dimensional option answer sheet, and identifying user binary options for the binary skin quality questions, wherein the user binary options include: option yes and option no; If the user's binary option is option yes, then confirm the extended numerical question group corresponding to the binary skin quality problem, and obtain the user numerical option of each extended numerical question in the extended numerical question group to obtain a user numerical option group; If the user binary option is option no, the preset zero option group is recorded as the user numerical option group, wherein the zero option group consists of a plurality of zero elements, and the number of zero elements in the zero option group is the same as the number of extended numerical questions in the extended numerical question group; Summarizing the user value option groups to obtain a user value option group set; Identifying a user habit option group of a user habit question group in a multi-dimensional option answer sheet, and determining a user skin characteristic group based on optional input items in the multi-dimensional option answer sheet; The generation of a multi-dimensional experience report is completed based on the user numerical option group set, the user habit option group and the user skin characteristic group.

5. The process optimization method for achieving a skin moisturizing agent according to claim 4, wherein: The step of determining the user's skin quality feature group based on the optional input items in the multi-dimensional option answer sheet includes: Determine whether the optional input items in the multi-dimensional option answer sheet are filled in; If the optional input items in the multi-dimensional option answer sheet are filled in, then receiving the user skin quality image group of the optional input items, wherein the user skin quality image group includes: an image before moisturizing and an image after moisturizing; Performing image detection on the user's skin quality image group to obtain a pre-moisturizing feature group and a post-moisturizing feature group, wherein the pre-moisturizing feature group includes: skin saturation, skin smoothness, and skin glossiness; The user's skin quality feature group is obtained by calculating the ratio based on the feature group before moisturizing and the feature group after moisturizing; If the optional input items in the multi-dimensional option answer sheet are not filled in, the preset zero feature group will be recorded as the user's skin feature group.

6. The process optimization method for achieving a skin moisturizing agent according to claim 5, wherein: The image detection is performed on the user skin quality image group to obtain the pre-moisturizing feature group and the post-moisturizing feature group, including: Determining an image feature category group, wherein the image feature category group includes: saturation, smoothness, and glossiness; Based on the image feature category group, image detection is performed on the pre-moisturizing image and the post-moisturizing image in the user skin type image group to obtain the original pre-moisturizing feature group and the original post-moisturizing feature group; According to the preset normal characteristic range group, the original pre-moisturizing characteristic group and the original post-moisturizing characteristic group are screened respectively to obtain the effective pre-moisturizing characteristic group and the effective post-moisturizing characteristic group; Perform the same category screening on the effective pre-moisturizing feature group and the effective post-moisturizing feature group to obtain the target pre-moisturizing feature group and the target post-moisturizing feature group; The target pre-moisturizing feature group and the target post-moisturizing feature group are respectively filled into the image feature category group to obtain the pre-moisturizing feature group and the post-moisturizing feature group, wherein the vacant positions in the pre-moisturizing feature group and the post-moisturizing feature group are filled with zero values.

7. The process optimization method for achieving a skin moisturizing agent according to claim 6, wherein: The user skin quality feature matrix is ​​constructed by using the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report, including: determining the number of options in each user numerical option group in the user numerical option group set, wherein the number of options in different user numerical option groups in the user numerical option group set is the same; Based on the number of options, the user skin quality feature group is expanded to obtain an extended skin quality feature group, wherein the number of extended skin quality features in the extended skin quality feature group is the same as the number of options, and the expansion method includes: squaring the data in the user skin quality feature group; According to the user numerical option set and the extended skin quality feature set, a user skin quality feature matrix is ​​constructed, where the user skin quality feature matrix is ​​expressed as: Among them, R represents the user's skin quality feature matrix, (D 1,1 …D 1,n ) represents the first user value option group in the user value option group set, D 1,1 Indicates the first user value option in the first user value option group, D 1,n Indicates the nth user value option in the first user value option group, where n represents the number of options. (D m,1 … D m,n ) represents the mth user numerical option group in the user numerical option group set, m represents the number of user numerical option groups in the user numerical option group set, D m,1 Indicates the first user value option in the mth user value option group, D m,n Indicates the nth user value option in the mth user value option group, (K1 … K n ) represents the extended skin quality feature group, K1 represents the first extended skin quality feature in the extended skin quality feature group, K n Represents the nth extended skin quality feature.

8. The process optimization method for achieving a skin moisturizing agent according to claim 7, wherein: The calculating of the user confidence based on the user skin quality feature group includes: Determine the experience terminal address and experience report date of the customer experience terminal, and obtain a user environment data set of the experience terminal address on the experience report date, wherein the user environment data set includes: climate dryness index and ultraviolet intensity; Determine the number of valid features in the user skin quality feature group, and count the number of valid environments in the user environment data group, wherein the valid feature number is the number of data with non-zero values ​​in the user skin quality feature group, and the valid environment number is the number of user environment data in the user environment data group; The user confidence is calculated based on the number of valid features and the number of valid environments using the following formula: Wherein, C represents the user confidence, α1 and α2 represent the preset feature coefficient and the preset environment coefficient respectively, S1 represents the effective feature number, S2 represents the effective environment number, and e represents the natural logarithm.

9. The process optimization method for achieving a skin moisturizing agent according to claim 8, wherein: The user habit correction of the user skin quality feature matrix according to the user habit option group to obtain the corrected skin quality feature matrix includes: Constructing a user habit vector for the user habit option group; Selecting a reference environment data group corresponding to the user environment data group from a preset standard environment data group; Based on the user habit vector, the user environment data set and the reference environment data set, the user skin quality feature matrix is ​​adjusted to obtain a modified skin quality feature matrix, wherein the modified skin quality feature matrix is ​​expressed as: Among them, R' represents the modified skin quality feature matrix, represents the preset habit weight vector, represents the user habit vector, p represents the number of user environment data in the user environment data group or the number of reference environment data in the reference environment data group, represents the i-th user environment data in the user environment data group, Represents the i-th reference environment data in the reference environment data group.

10. A process optimization system for achieving skin moisturizing agent, characterized in that, The system comprises: An option questionnaire design module is configured to receive a process optimization instruction, determine a group of directions to be optimized based on the process optimization instruction, wherein the group of directions to be optimized includes: a dryness optimization direction, an oiliness optimization direction, and a sensitivity optimization direction, sequentially extract directions to be optimized from the group of directions to be optimized, design multiple-option questions based on the directions to be optimized, and combine the multiple-option questions corresponding to each direction to be optimized in the group of directions to be optimized to obtain a multi-dimensional option questionnaire; An experience report generation module is used to identify a customer experience terminal set, wherein the customer experience terminal set includes multiple customer experience terminals, and the customer experience terminal includes a mobile phone app, sequentially extract customer experience terminals from the customer experience terminal set, use the customer experience terminals and a multi-dimensional option questionnaire to conduct user experience feedback, and obtain a multi-dimensional experience report, wherein the multi-dimensional experience report includes: a user numerical option group set, a user habit option group, and a user skin characteristic group; A skin quality matrix construction module is used to construct a user skin quality feature matrix using the user numerical option group set and the user skin quality feature group in the multi-dimensional experience report, calculate the user confidence based on the user skin quality feature group, and perform user habit correction on the user skin quality feature matrix according to the user habit option group to obtain a corrected skin quality feature matrix; A formula ratio optimization module is used to input the corrected skin quality feature matrix into a pre-trained moisturizer ratio adjustment model to obtain a moisturizer ratio, wherein the moisturizer ratio adjustment model is a trained neural network model, which summarizes the moisturizer ratios and user confidence levels to obtain a moisturizer ratio set and a user confidence level set, and uses the user confidence level set to perform weighted averaging on the moisturizer ratio set to obtain a target moisturizer ratio.

Images