An information determination method, apparatus, device, storage medium, and program product
By acquiring and processing skin parameters and evaluation parameters from multiple dimensions, a baseline coordinate system and target area are constructed, and the priority and processing order of the skin parameters to be adjusted are determined. This solves the problem that existing technologies cannot accurately reveal the core elements of complexion, and generates more precise targets for improving complexion.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU HUANINGXIANG BIOTECHNOLOGY CO LTD
- Filing Date
- 2026-03-18
- Publication Date
- 2026-07-14
AI Technical Summary
Existing skin analysis technologies cannot accurately reveal the core factors affecting complexion, making it impossible to generate precise targets for improving complexion.
By acquiring multi-dimensional skin parameters and evaluation parameters of sample users, the baseline skin parameters of reference users are determined. Based on these parameters and the skin parameters of the users to be processed, the target values of the skin parameters to be adjusted are calculated. Multi-dimensional data processing methods such as PCA and target outlier detection algorithms are used to construct a baseline coordinate system and target region, and to determine the priority and processing order of the skin parameters to be adjusted.
It enables the determination of target values for skin parameters to be adjusted based on multiple dimensions of skin parameters and evaluation parameters, generating more accurate targets for improving complexion, and solving the problem that existing technologies cannot accurately reveal the core elements affecting complexion.
Smart Images
Figure CN122376019A_ABST
Abstract
Description
Technical Field
[0001] This application relates to information determination technology in the field of computer technology, and more particularly to an information determination method, apparatus, device, computer-readable storage medium, and computer program product. Background Technology
[0002] As people pay increasing attention to health, complexion, as an important indicator of both outward appearance and inner health, is receiving more and more attention. Although current skin testing technologies can collect multiple physiological parameters, most of them are based on only a single dimension of physiological parameters for evaluation, which cannot accurately reveal the core factors affecting complexion, nor can they generate accurate complexion improvement targets for individuals. Summary of the Invention
[0003] This application provides an information determination method, apparatus, device, computer-readable storage medium, and computer program product, which solves the problem that the complexion assessment schemes in the related art cannot accurately reveal the core elements affecting complexion, and can generate more accurate complexion improvement targets.
[0004] The technical solution of this application embodiment is implemented as follows: An information determination method, the method comprising: Obtain multi-dimensional sample skin parameters and evaluation parameters for the facial skin of the sample users; Obtain an evaluation value for the facial skin of the sample users, and determine reference users from the sample users based on the evaluation value; Based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, the sample feature information of the facial skin of the reference user is determined, and the baseline skin parameters are determined based on the sample feature information; Obtain the skin parameters to be processed from the facial skin of the user to be processed; wherein, the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; Based on the baseline skin parameters and the skin parameters to be processed, the skin parameters to be adjusted for the user to be processed and the target values corresponding to the skin parameters to be adjusted are determined.
[0005] In the above scheme, determining the sample feature information of the reference user's facial skin based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, and determining the baseline skin parameters based on the sample feature information, includes: The sample skin parameters of the reference user and the evaluation parameters of the parameter user are processed; The facial skin sample feature information of the reference user is determined based on the processed sample skin parameters and the processed evaluation parameters; The sample feature information is processed, and the baseline skin parameters are determined based on the sample feature information and the processed sample feature information.
[0006] In the above scheme, determining the baseline skin parameters based on the sample feature information and the processed sample feature information includes: The sample feature matrix is determined based on the sample feature information, and the baseline feature information is determined from the processed sample feature information. A reference coordinate system is constructed based on the aforementioned reference feature information; Based on the sample feature matrix, determine the first position of each reference user in the reference coordinate system, and determine the reference point based on the first position; The reference skin parameters are determined based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position.
[0007] In the above scheme, determining the reference point based on the first position of each reference user in the reference coordinate system and the sample feature matrix includes: Based on the weight coefficients of each dimension corresponding to each coordinate axis of the reference coordinate system and the sample feature matrix, the first position of each reference user is determined. The reference point is determined based on the target outlier detection algorithm and each first position.
[0008] In the above scheme, determining the reference skin parameters based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position includes: Based on the target outlier detection algorithm and the target matrix determined at each first position, a first eigenvalue, a second eigenvalue, a third eigenvalue, and a fourth eigenvalue are determined based on the target matrix. A first value is calculated based on the first feature value and the target value, and a second value is calculated based on the second feature value and the target value. Calculate the target angle based on the third and fourth feature values; A target region is determined in the reference coordinate system based on the second position, the first value, the second value, and the target angle, and the reference skin parameters are determined based on the skin parameters of a reference user within the target region at the first position.
[0009] In the above scheme, determining the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed based on the baseline skin parameters and the skin parameters to be processed includes: Based on the value of each of the aforementioned reference skin parameters, a first reference value and a second reference value are calculated for each of the aforementioned reference skin parameters; For each parameter in the skin parameters to be processed, the degree of difference corresponding to each parameter is calculated based on the value of each parameter, the first benchmark value, and the second benchmark value; Based on the degree of difference of each parameter, the skin parameter to be adjusted is determined from the skin parameters to be processed; The target value is determined based on the value of the skin parameter to be adjusted and the value of the skin parameter to be adjusted in the baseline skin parameters.
[0010] The method in the above scheme further includes: Determine the priority of each skin parameter to be adjusted; The processing order of each skin parameter to be adjusted is determined based on the priority and the degree of difference of each skin parameter to be adjusted; The value of each skin parameter to be adjusted is set to the target value according to the processing order.
[0011] The method in the above scheme further includes: Determine the feature information to be processed for the skin parameters to be processed; The feature information to be processed is subjected to dimensionality reduction processing, and the target position of the user to be processed in the reference coordinate system is determined based on the processed feature information; Based on the target location and the second location, the degree of deviation between the skin parameters to be processed of the user to be processed and the skin parameters corresponding to the reference point is determined.
[0012] An information determining device, the device comprising: The first acquisition unit is used to acquire sample skin parameters of multiple dimensions of the sample user's facial skin and evaluation parameters for the sample user's facial skin. The second acquisition unit is used to acquire the evaluation value of the facial skin of the sample users, and to determine the reference users from the sample users based on the evaluation value; The first processing unit is configured to determine sample feature information of the facial skin of the reference user based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, and to determine the baseline skin parameters based on the sample feature information. The first acquisition unit is further configured to acquire the skin parameters to be processed of the facial skin of the user to be processed; wherein, the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; The second processing unit is used to determine the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed, based on the baseline skin parameters and the skin parameters to be processed.
[0013] An information determining device, the device comprising: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute the information determination program in the memory to implement the steps of the information determination method described above.
[0014] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the information determination method described above.
[0015] A computer program product comprising a computer program that, when executed by a processor, implements the aforementioned information determination method.
[0016] The information determination method, device, computer-readable storage medium, and computer program product provided in this application embodiment can acquire multi-dimensional sample skin parameters and evaluation parameters for the facial skin of sample users, obtain evaluation values for the facial skin of sample users, determine reference users from sample users based on evaluation values, determine sample feature information of the facial skin of reference users based on the sample skin parameters of reference users and the evaluation parameters of reference users, determine benchmark skin parameters based on the sample feature information, acquire unprocessed skin parameters for the facial skin of users to be processed, the unprocessed skin parameters include multi-dimensional skin parameters and evaluation parameters for the facial skin of users to be processed, and determine the reference user's facial skin based on the benchmark skin parameters and the unprocessed skin parameters. The system identifies the user's skin parameters to be adjusted and their corresponding target values. This allows for the determination of baseline skin parameters based on multiple dimensions of sample skin parameters and evaluation parameters from the acquired user data. Furthermore, it identifies the user's specific skin parameters to be adjusted and their corresponding target values based on these baseline parameters and the user's facial skin parameters to be processed. Clearly, the baseline skin parameters for adjustment are determined based on multiple dimensions of the sample user's skin parameters and evaluation parameters, rather than using only a single dimension as in related technologies. This addresses the problem in related technologies where complexion assessment schemes fail to accurately reveal the core factors influencing complexion, enabling the generation of more precise complexion improvement targets. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating an information determination method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the target area and reference point in an information determination method provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the difference between the user to be processed and a reference point in the target area in an information determination method provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of an information determination device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an information determination device provided in an embodiment of this application. Detailed Implementation
[0018] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0019] It should be understood that the phrases "embodiments of this application" or "foreign embodiments" throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "embodiments of this application" or "in the foreign embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.
[0020] Unless otherwise specified, any step in the embodiments of this application performed by the electronic device may be executed by the processor of the electronic device. It is also worth noting that the embodiments of this application do not limit the order in which the electronic device performs the following steps. Furthermore, the methods used to process data in different embodiments may be the same or different methods. It should also be noted that any step in the embodiments of this application can be executed independently by the electronic device; that is, when the electronic device performs any step in the following embodiments, it may not depend on the execution of other steps.
[0021] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.
[0022] This application provides an information determination method, which can be applied to an information determination device. (Refer to...) Figure 1 As shown, the method for determining this information may include the following steps: Step 101: Obtain multi-dimensional sample skin parameters and evaluation parameters for the sample user's facial skin.
[0023] Specifically, sample skin parameters can refer to skin parameters in multiple different dimensions of the sample user's facial skin.
[0024] In other embodiments of this application, the sample skin parameters may include: stratum corneum moisture content, transepidermal water loss rate, skin gloss, skin erythema information, skin elasticity, skin firmness, skin color, red area, wrinkle area, smoothness parameters, roughness parameters, crow's feet wrinkles, etc. It should be noted that skin erythema information may include the erythema index (EI) value; skin elasticity may include the skin elasticity R2 value; skin firmness may include the skin firmness F4 value; and skin color may include the individual typology angle (ITA) value and skin color L. Value, skin tone a Value, skin tone b Values and skin tone evenness; crow's feet wrinkles can include crow's feet wrinkle volume and average depth.
[0025] It should be noted that the following parameters are considered: stratum corneum moisture content, transepidermal water loss rate, skin radiance, skin erythema index (EI), skin elasticity (R2), skin firmness (F4), skin color (ITA), and skin color (L). Value, skin tone a Value, skin tone b Values such as skin red area, skin color uniformity, wrinkle area, smoothness parameter, roughness parameter, area of crow's feet wrinkles, volume of crow's feet wrinkles, and average depth of crow's feet wrinkles can be obtained by taking multiple measurements using specific test probes corresponding to their respective skin parameters and then averaging the measured values.
[0026] In other embodiments of this application, the evaluation parameters include user self-subjective evaluation and evaluation by experts (or professionally trained evaluators) in the field of cosmetic efficacy, and the evaluation content covers multiple skin dimensions related to complexion.
[0027] In one feasible embodiment, expert evaluation includes: skin tone evenness, radiance, fair and rosy complexion, skin without dullness or sallowness, moisturized and non-dry skin, firm and lifted skin, severity of eye wrinkles, severity of nasolabial folds, plump and full skin, skin elasticity, skin smoothness, fineness of pores, brightness of eyes, elegance of eyebrows and eyelashes, overall demeanor, overall vitality, mental state, overall complexion, and facial complexion. It should be noted that self-subjective evaluation includes skin tone evenness, radiance, fair and rosy complexion, skin without dullness or sallowness, moisturized and non-dry skin, firm and lifted skin, severity of eye wrinkles, severity of nasolabial folds, plump and full skin, skin elasticity, skin smoothness, fineness of pores, brightness of eyes, elegance of eyebrows and eyelashes, overall demeanor, overall vitality, mental state, overall complexion, facial complexion, skin barrier fragility, skin tolerance, and skin's ability to resist external stimuli.
[0028] Step 102: Obtain the evaluation value of the facial skin of the sample users, and determine the reference users from the sample users based on the evaluation value.
[0029] Specifically, it can obtain the evaluation information of the sample users' facial skin from a target number of evaluators, perform calculations on the evaluation information, and determine reference users from the sample users based on the calculation results.
[0030] In this embodiment, a target number of evaluators can assess the facial complexion of sample users, meaning that evaluators are required to view images of sample users and determine whether their complexion is good or bad. Specifically, a formula can be used. Calculate the percentage of users with a healthy complexion; where, This represents the percentage of healthy complexion for the i-th sample user. Let N represent the number of times the i-th sample user was rated as having "good complexion," and N represent the total number of ratings. Then, reference users are selected from the sample users based on the calculated proportion of good complexion for each sample user. In one feasible implementation, the good complexion proportions of all sample users can be sorted in descending order, and the top 20% of sample users in the sorted order can be selected as reference users.
[0031] Step 103: Determine the sample feature information of the reference user's facial skin based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, and determine the baseline skin parameters based on the sample feature information.
[0032] Specifically, the sample skin parameters and evaluation parameters of the reference user can be processed first, and the sample feature information can be determined based on the processed sample skin parameters and evaluation parameters; then, the sample feature information can be processed to obtain the baseline skin parameters.
[0033] Step 104: Obtain the skin parameters of the user's facial skin to be processed.
[0034] The skin parameters to be processed include multiple dimensions of skin parameters and evaluation parameters for the facial skin of the user to be processed.
[0035] Specifically, the evaluation parameters for the facial skin of the user to be treated can include the user's subjective self-evaluation and the evaluation by experts in the field of cosmetic efficacy (or professionally trained evaluators); the evaluation content covers multiple skin dimensions related to complexion.
[0036] In this embodiment, the skin parameters of the user to be processed include: stratum corneum moisture content, transepidermal water loss rate, skin gloss, skin erythema information, skin elasticity, skin firmness, skin color, red area, wrinkle area, smoothness parameters, roughness parameters, and crow's feet wrinkles. It should be noted that skin erythema information may include the erythema index (EI) value; skin elasticity may include the skin elasticity R2 value; skin firmness may include the skin firmness F4 value; and skin color may include the skin color ITA value and skin color L value. Value, skin tone a Value, skin tone b Values and skin tone evenness; crow's feet wrinkles can include crow's feet wrinkle volume and average depth.
[0037] In other embodiments of this application, the evaluation parameters of the user's facial skin may include: skin tone evenness, translucency and luster, fair and rosy skin tone, skin brightness, vitality and vitality, mental state, skin hydration, firmness, wrinkles, nasolabial folds, fullness, elasticity, smoothness, pores, eyes, eyebrows and eyelashes, and overall complexion.
[0038] Step 105: Based on the baseline skin parameters and the skin parameters to be processed, determine the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed.
[0039] Specifically, the baseline skin parameters and the skin parameters to be processed can be processed, and the skin parameters to be adjusted can be selected from the skin parameters to be processed based on the processing results; at the same time, the target value of the skin parameters to be adjusted can be determined based on the value of the skin parameters to be adjusted for the user and the value of the baseline skin parameters.
[0040] Based on the foregoing embodiments, in other embodiments of this application, step 103 can be implemented in the following ways: A1. Process the sample skin parameters of the reference users and the evaluation parameters of the parameter users.
[0041] Specifically, the sample skin parameters of reference users and the evaluation parameters of parameter users can be standardized and reduced in dimensionality. It should be noted that standardization can refer to normalization, which can be achieved using formulas. It is standardized; among them, This refers to the standardized sample skin parameters and the standardized evaluation parameters. This refers to the reference user's sample skin parameters and the user's evaluation parameters. This refers to the mean of the sample skin parameters of the reference users and the mean of the evaluation parameters of the reference users. This refers to the standard deviation of the sample skin parameters of the reference users and the standard deviation of the evaluation parameters of the parameter users.
[0042] Furthermore, Principal Components Analysis (PCA) can be used to reduce the dimensionality of the standardized, multi-dimensional dataset of sample skin parameters and evaluation parameters. PCA extracts several principal components with a cumulative variance contribution rate greater than 80%, removing redundant features and retaining the core parameters that represent the main data variations.
[0043] A2. Based on the processed sample skin parameters and processed evaluation parameters, determine the sample feature information of the reference user's facial skin.
[0044] Specifically, feature extraction can be performed on the processed sample skin parameters and processed evaluation parameters to obtain sample feature information of the reference user's facial skin.
[0045] A3. Process the sample feature information and determine the baseline skin parameters based on the sample feature information and the processed sample feature information.
[0046] Specifically, dimensionality reduction can be performed on the sample feature information to obtain processed sample feature information. It should be noted that PCA (Programmable Conversion Method) can be used to perform dimensionality reduction on the sample feature information.
[0047] In this embodiment of the application, a reference coordinate system can be determined first based on the processed sample feature information, a reference point can be determined based on the reference coordinate system and the sample feature information, and reference skin parameters can be determined based on the reference point, the reference coordinate system and the processed sample feature information.
[0048] In other embodiments of this application, the above-described determination of baseline skin parameters based on sample feature information and processed sample feature information includes: The sample feature matrix is determined based on the sample feature information, and the baseline feature information is determined from the processed sample feature information.
[0049] Specifically, a corresponding sample feature matrix can be constructed based on the sample feature information; it should be noted that the sample feature matrix... Where n represents the number of reference users, p represents the dimension of the skin parameters, and x ij Let represent the feature value of the j-th skin parameter dimension of the i-th reference user.
[0050] In other embodiments of this application, the baseline feature information can be feature information of a target number selected from the processed sample feature information; in one feasible implementation, the first two principal feature information (i.e., PC1 and PC2) in the processed sample feature information can be selected. It should be noted that PC1 and PC2 are orthogonal directions with the largest variance, which can preserve the variation information of skin parameters to the greatest extent.
[0051] A reference coordinate system is constructed based on the reference feature information.
[0052] Specifically, a reference coordinate system is constructed using reference feature information as coordinate axes; in one feasible implementation, such as... Figure 2 As shown, a reference coordinate system is constructed with PC1 as the x-axis and PC2 as the y-axis.
[0053] The first position of each reference user in the reference coordinate system is determined based on the sample feature matrix, and the reference point is determined based on the first position.
[0054] Specifically, the processed sample feature information of each reference user is mapped to a reference coordinate system, and the first position of each reference user in the reference coordinate system is determined.
[0055] Based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position, the reference skin parameters are determined.
[0056] Specifically, the target region can be determined based on the baseline feature information and the second position, and the baseline skin parameters can be determined based on the target region and the first position. It should be noted that the target region can refer to a specific area in the baseline coordinate system.
[0057] In other embodiments of this application, determining the reference point based on the first position of each reference user in the reference coordinate system and the sample feature matrix includes: Based on the weight coefficients of each dimension corresponding to each coordinate axis of the reference coordinate system and the sample feature matrix, the first position of each reference user is determined.
[0058] Specifically, the first position of each reference user can be obtained by calculating the weight coefficient of each dimension corresponding to each coordinate axis and the eigenvalues in the sample feature matrix. It should be noted that for each reference user, the formula can be used... and Calculate the first position of each reference user in the reference coordinate system; where w ij It is the weighting coefficient, x ip This represents the feature value of the skin parameter in the j-th dimension for the i-th reference user.
[0059] Based on the target outlier detection algorithm and each first position, a reference point is determined.
[0060] Specifically, a coordinate matrix can be constructed based on each initial position. Then, a target outlier detection algorithm is used to process the position corresponding to each sample point in the sample subset corresponding to the coordinate matrix, and the baseline point is determined based on the processing results. It should be noted that the target outlier detection algorithm can refer to the minimum covariance determinant (MinCovDet) algorithm.
[0061] In other embodiments of this application, a coordinate matrix can be constructed first based on each first position. Then, the target numerical sample points are determined from the coordinate matrix to obtain the first sample subset; subsequently, the mean vector of this first sample subset is calculated. Covariance Matrix Next, calculate the Mahalanobis distance of all sample points in the coordinate matrix. Then select the h samples with the smallest Mahalanobis distance to form a new subset H. (k+1)The process of forming subsets is repeated k times, with the statistics recalculated and a new subset selected in each iteration, until the following convergence condition is met: or, , It is a pre-set threshold. Finally, the benchmark point is determined. Let be the mean vector of the last obtained subset, and let (u1, u2) be the second position of the reference point in the reference coordinate system. It should be noted that the position of the reference point in the reference coordinate system and the target region can be as follows: Figure 2 and Figure 3 As shown in the image.
[0062] In other embodiments of this application, determining the reference skin parameters based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position includes: The target outlier detection algorithm is used to determine the target matrix at each first position, and the first, second, third, and fourth eigenvalues are determined based on the target matrix.
[0063] Here, the target matrix can refer to the covariance matrix. Specifically, a coordinate matrix is first constructed based on the first position, and the MinCovDet algorithm is used to process the sample points in the sample subset corresponding to the coordinate matrix to output the covariance matrix. Then, the covariance matrix can be processed to determine the first, second, third, and fourth eigenvalues. In one feasible implementation, the covariance matrix... , V represents the eigenvector matrix, and v1 and v2 represent the variation strength of the features. , Represents an eigenvalue diagonal matrix. and This represents the eigenvalues of the covariance matrix; specifically, the first eigenvalue can be obtained by processing the covariance matrix. Second eigenvalue The third eigenvalue v2 and the fourth eigenvalue v1.
[0064] The first value is calculated based on the first eigenvalue and the target value, and the second value is calculated based on the second eigenvalue and the target value.
[0065] The target angle is calculated based on the third and fourth eigenvalues.
[0066] The target value can be a pre-set value. Specifically, the first feature value and the target value can be processed to obtain the first value 'a', the second feature value and the target value can be processed to obtain the second value 'b', and the third feature value and the fourth feature value can be processed to obtain the target angle. In one feasible implementation, the target value represents the critical value of the chi-square distribution. , , , It should be noted that when the confidence level is 0.6... .
[0067] The target region is determined in the reference coordinate system based on the second position, the first value, the second value, and the target angle, and the reference skin parameters are determined based on the skin parameters of the reference user within the target region at the first position.
[0068] Specifically, taking the second position as the center point coordinates, 'a' as the length of the major axis of the ellipse, and 'b' as the length of the minor axis of the ellipse. The target region is constructed in the reference coordinate system by using the ellipse rotation angle. It should be noted that the target region can refer to an elliptical region, and the target region can be as follows: Figure 2 and Figure 3 The area shown.
[0069] In addition, based on the first position, the skin parameters of all reference users distributed in the target area are statistically analyzed, and the mean, standard deviation and interval range of each dimension of the skin parameters of all reference users in the target area are calculated, including the ideal complexion parameter range (such as skin color, elasticity, luster, etc.). These skin parameters are used as the benchmark skin parameters.
[0070] In other embodiments of this application, step 105 described above can be implemented in the following ways: B1. Based on the value of each baseline skin parameter, calculate the first baseline value and the second baseline value for each baseline skin parameter.
[0071] Specifically, the first and second baseline values of the skin parameters for each dimension are calculated by performing calculations on all the baseline skin parameters. It should be noted that the first baseline value can refer to the mean of all the baseline skin parameters for each dimension, and the second baseline value can refer to the standard deviation of all the baseline skin parameters for each dimension.
[0072] B2. For each parameter in the skin parameters to be processed, calculate the degree of difference corresponding to each parameter based on the value of each parameter, the first baseline value, and the second baseline value.
[0073] This involves standardizing each parameter of the skin parameters to be processed and using a formula. Calculate the degree of difference for each parameter; where, Indicates the degree of difference for each parameter. This represents the value of each parameter. Indicates the first reference value. This represents the second baseline value.
[0074] B3. Based on the degree of difference of each parameter, determine the skin parameters to be adjusted from the skin parameters to be processed.
[0075] Specifically, the degree of difference of each parameter can be compared with the magnitude of the target threshold, and skin parameters that are greater than the target threshold can be identified as skin parameters to be adjusted. In one feasible implementation, the target threshold can be set to 0.5, and parameters among the skin parameters to be processed whose degree of difference is greater than the target threshold can be selected as skin parameters to be adjusted.
[0076] B4. Determine the target value based on the value of the skin parameter to be adjusted and the value of the skin parameter to be adjusted in the baseline skin parameters.
[0077] Specifically, for each skin parameter to be adjusted, we can first determine the value of the skin parameter to be adjusted in each dimension and the mean value of the skin parameter in the benchmark skin parameters, and then determine the target value based on the maximum, minimum and mean values of the skin parameter in the benchmark skin parameters; however, it is necessary to ensure that the target value is within the range of the maximum and minimum values.
[0078] In other embodiments of this application, the method may further include: Determine the priority of each skin parameter to be adjusted.
[0079] The processing order of each skin parameter to be adjusted is determined based on priority and the degree of difference between each parameter.
[0080] The priority of each skin parameter to be adjusted can be preset; specifically, the processing order of each skin parameter to be adjusted can be determined according to the order of priority from largest to smallest and the order of difference from largest to smallest.
[0081] Adjust the value of each skin parameter to be adjusted to the target value according to the processing order.
[0082] It should be noted that the target value is determined by the direction of deviation of the skin parameter to be adjusted relative to the target value. If the value of the skin parameter to be adjusted is less than the corresponding minimum value in the baseline skin parameters, then the value of the skin parameter to be adjusted needs to be increased to the target value. If the value of the skin parameter to be adjusted is greater than the corresponding maximum value in the baseline skin parameters, then the value of the skin parameter to be adjusted needs to be decreased to the target value.
[0083] In other embodiments of this application, the top N (e.g., top 5) most important parameters from the skin parameters to be adjusted can be selected, and their corresponding information can be output. In one feasible implementation, the current value of parameter [IPP_skin chroma L value_mean] is 0.28; the range of the baseline skin parameters is 0.44-0.98, and the mean is 0.65; the suggestion is to improve this indicator; the improvement target is to improve it to at least 0.47.
[0084] In other embodiments of this application, the method may further include: Determine the feature information to be processed for the skin parameters; The feature information to be processed is dimensionality reduced, and the target position of the user to be processed in the reference coordinate system is determined based on the processed feature information. Specifically, feature extraction can be performed on the skin parameters to be processed to obtain the feature information to be processed; and the PCA algorithm can be used to reduce the dimensionality of the feature information to be processed, and the processed feature information can be mapped to the reference coordinate system to obtain the target position of the user to be processed in the reference coordinate system.
[0085] Based on the target location and the second location, determine the degree of deviation between the skin parameters to be processed for the user and the skin parameters corresponding to the reference point.
[0086] Specifically, the distance between the user to be processed and the reference point can be calculated based on the target location and the second location; in one feasible implementation, a formula can be used. Calculate the Euclidean distance between the user to be processed and the reference point, and determine the degree of deviation of this Euclidean distance; where d represents the Euclidean distance, and (PC1, PC2) represents the target location of the user to be processed. It should be noted that this degree of deviation can be used to quantify the overall complexion of the user being processed; and, as Figure 3 The display shows the magnitude of the difference between the user being processed and the baseline.
[0087] The information determination method provided in the embodiments of this application can determine the baseline skin parameters based on the multi-dimensional sample skin parameters and evaluation parameters of the sample users, and determine the skin parameters to be adjusted and the corresponding target values of the skin parameters to be adjusted for the user based on the baseline skin parameters and the skin parameters to be processed of the user's facial skin. It is clear that the baseline skin parameters for determining the skin parameters to be adjusted are determined based on the multi-dimensional skin parameters and evaluation parameters of the sample users, rather than using only a single-dimensional parameter as in related technologies. This solves the problem in the complexion assessment schemes of related technologies that cannot accurately reveal the core elements affecting complexion, and can generate more accurate complexion improvement targets.
[0088] Based on the foregoing embodiments, embodiments of this application provide an information determining device, which can be applied to... Figure 1 In the information determination method provided in the corresponding embodiment, refer to Figure 4 As shown, the information determining device 2 may include: a first acquisition unit 21, a second acquisition unit 22, a first processing unit 23, and a second processing unit 24, wherein: The first acquisition unit 21 is used to acquire sample skin parameters of multiple dimensions of the sample user's facial skin and evaluation parameters of the sample user's facial skin. The second acquisition unit 22 is used to acquire the evaluation value of the facial skin of the sample users and determine the reference users from the sample users based on the evaluation value. The first processing unit 23 is used to determine the sample feature information of the facial skin of the reference user based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, and to determine the baseline skin parameters based on the sample feature information. The first acquisition unit 21 is also used to acquire the skin parameters to be processed of the facial skin of the user to be processed; wherein, the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; The second processing unit 24 is used to determine the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed, based on the baseline skin parameters and the skin parameters to be processed.
[0089] In other embodiments of this application, the first processing unit 23 is further configured to perform the following steps: Process the sample skin parameters of the reference users and the evaluation parameters of the parameter users; Based on the processed sample skin parameters and the processed evaluation parameters, the sample feature information of the reference user's facial skin is determined; The sample feature information is processed, and the baseline skin parameters are determined based on the sample feature information and the processed sample feature information.
[0090] In other embodiments of this application, the first processing unit 23 is further configured to perform the following steps: The sample feature matrix is determined based on the sample feature information, and the baseline feature information is determined from the processed sample feature information. Construct a reference coordinate system based on reference feature information; The first position of each reference user in the reference coordinate system is determined based on the sample feature matrix, and the reference point is determined based on the first position; Based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position, the reference skin parameters are determined.
[0091] In other embodiments of this application, the first processing unit 23 is further configured to perform the following steps: Based on the weight coefficients of each dimension corresponding to each coordinate axis of the reference coordinate system and the sample feature matrix, the first position of each reference user is determined. Based on the target outlier detection algorithm and each first position, a reference point is determined.
[0092] In other embodiments of this application, the first processing unit 23 is further configured to perform the following steps: The first feature value, the second feature value, the third feature value, and the fourth feature value are determined based on the baseline feature information; The first value is calculated based on the first eigenvalue and the target value, and the second value is calculated based on the second eigenvalue and the target value. Calculate the target angle based on the third and fourth eigenvalues; The target region is determined in the reference coordinate system based on the second position, the first value, the second value, and the target angle, and the reference skin parameters are determined based on the skin parameters of the reference user within the target region at the first position.
[0093] In other embodiments of this application, the second processing unit 24 is further configured to perform the following steps: Based on the value of each baseline skin parameter, calculate the first baseline value and the second baseline value for each baseline skin parameter; For each parameter in the skin parameters to be processed, the degree of difference corresponding to each parameter is calculated based on the value of each parameter, the first baseline value, and the second baseline value. Based on the degree of difference of each parameter, determine the skin parameters to be adjusted from the skin parameters to be processed; The target value is determined based on the value of the skin parameter to be adjusted and the value of the skin parameter to be adjusted in the baseline skin parameter.
[0094] In other embodiments of this application, the second processing unit 24 is further configured to perform the following steps: Determine the priority of each skin parameter to be adjusted; The processing order of each skin parameter to be adjusted is determined based on priority and the degree of difference of each skin parameter to be adjusted; Adjust the value of each skin parameter to be adjusted to the target value according to the processing order.
[0095] In other embodiments of this application, the second processing unit 24 is further configured to perform the following steps: Determine the feature information to be processed for the skin parameters; The feature information to be processed is dimensionality reduced, and the target position of the user to be processed in the reference coordinate system is determined based on the processed feature information. Based on the target location and the second location, determine the degree of deviation between the skin parameters to be processed for the user and the skin parameters corresponding to the reference point.
[0096] It should be noted that the specific implementation process of the steps performed by each unit in the embodiments of this application can be referred to Figure 1 The implementation process of the information determination method provided in the corresponding embodiments will not be described in detail here.
[0097] The information determination device provided in the embodiments of this application can determine the baseline skin parameters based on the multi-dimensional sample skin parameters and evaluation parameters of the sample user, and determine the skin parameters to be adjusted and the corresponding target values of the skin parameters to be adjusted for the user based on the baseline skin parameters and the skin parameters to be processed of the user's facial skin. It is clear that the baseline skin parameters for determining the skin parameters to be adjusted are determined based on the multi-dimensional skin parameters and evaluation parameters of the sample user, rather than using only a single-dimensional parameter as in related technologies. This solves the problem in related technologies where the complexion assessment scheme cannot accurately reveal the core elements affecting complexion, and can generate more accurate complexion improvement targets.
[0098] Based on the foregoing embodiments, embodiments of this application provide an information determining device, which can be applied to... Figure 1 In the information determination method provided in the corresponding embodiment, refer to Figure 5 As shown, the information determining device 3 may include: a processor 31, a memory 32, and a communication bus 33, wherein: Communication bus 33 is used to realize the communication connection between processor 31 and memory 32; The memory 32 is used to store computer programs that can run on the processor 31; Processor 31 is used to run computer programs to perform the following steps: Obtain multi-dimensional sample skin parameters and evaluation parameters for the sample users' facial skin; Obtain evaluation scores for the facial skin of sample users, and determine reference users from the sample users based on the evaluation scores; Based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, the sample feature information of the facial skin of the reference user is determined, and the baseline skin parameters are determined based on the sample feature information; Obtain the skin parameters to be processed from the facial skin of the user to be processed; the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; Based on the baseline skin parameters and the skin parameters to be processed, the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user are determined.
[0099] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: Process the sample skin parameters of the reference users and the evaluation parameters of the parameter users; Based on the processed sample skin parameters and the processed evaluation parameters, the sample feature information of the reference user's facial skin is determined; The sample feature information is processed, and the baseline skin parameters are determined based on the sample feature information and the processed sample feature information.
[0100] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: The sample feature matrix is determined based on the sample feature information, and the baseline feature information is determined from the processed sample feature information. Construct a reference coordinate system based on reference feature information; The first position of each reference user in the reference coordinate system is determined based on the sample feature matrix, and the reference point is determined based on the first position; Based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position, the reference skin parameters are determined.
[0101] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: Based on the weight coefficients of each dimension corresponding to each coordinate axis of the reference coordinate system and the sample feature matrix, the first position of each reference user is determined. Based on the target outlier detection algorithm and each first position, a reference point is determined.
[0102] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: The first feature value, the second feature value, the third feature value, and the fourth feature value are determined based on the baseline feature information; The first value is calculated based on the first eigenvalue and the target value, and the second value is calculated based on the second eigenvalue and the target value. Calculate the target angle based on the third and fourth eigenvalues; The target region is determined in the reference coordinate system based on the second position, the first value, the second value, and the target angle, and the reference skin parameters are determined based on the skin parameters of the reference user within the target region at the first position.
[0103] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: Based on the value of each baseline skin parameter, calculate the first baseline value and the second baseline value for each baseline skin parameter; For each parameter in the skin parameters to be processed, the degree of difference corresponding to each parameter is calculated based on the value of each parameter, the first baseline value, and the second baseline value. Based on the degree of difference of each parameter, determine the skin parameters to be adjusted from the skin parameters to be processed; The target value is determined based on the value of the skin parameter to be adjusted and the value of the skin parameter to be adjusted in the baseline skin parameter.
[0104] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: Determine the priority of each skin parameter to be adjusted; The processing order of each skin parameter to be adjusted is determined based on priority and the degree of difference of each skin parameter to be adjusted; Adjust the value of each skin parameter to be adjusted to the target value according to the processing order.
[0105] In other embodiments of this application, the processor 31 is used to run computer programs and can also perform the following steps: Determine the feature information to be processed for the skin parameters; The feature information to be processed is dimensionality reduced, and the target position of the user to be processed in the reference coordinate system is determined based on the processed feature information. Based on the target location and the second location, determine the degree of deviation between the skin parameters to be processed for the user and the skin parameters corresponding to the reference point.
[0106] It should be noted that a detailed description of the steps performed by the processor can be found in [reference needed]. Figure 1 The information determination method provided in the corresponding embodiments will not be described again here.
[0107] The information determination device provided in the embodiments of this application can determine the baseline skin parameters based on the multi-dimensional sample skin parameters and evaluation parameters of the sample user, and determine the skin parameters to be adjusted and the corresponding target values of the skin parameters to be adjusted for the user based on the baseline skin parameters and the skin parameters to be processed of the user's facial skin. It is clear that the baseline skin parameters for determining the skin parameters to be adjusted are determined based on the multi-dimensional skin parameters and evaluation parameters of the sample user, rather than using only a single-dimensional parameter as in related technologies. This solves the problem in the complexion assessment schemes of related technologies that cannot accurately reveal the core elements affecting complexion, and can generate more accurate complexion improvement targets.
[0108] Based on the foregoing embodiments, embodiments of this application provide a computer-readable storage medium storing one or more programs, which can be executed by one or more processors 31 to implement... Figure 1 The corresponding embodiments provide the steps of the information determination method.
[0109] Based on the foregoing embodiments, embodiments of this application provide a computer program product, including a computer program that can be executed by a processor 31 to perform... Figure 1 The corresponding embodiments provide the steps of the information determination method.
[0110] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.
[0111] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0114] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for determining information, characterized in that, The method includes: Obtain multi-dimensional sample skin parameters and evaluation parameters for the facial skin of the sample users; Obtain an evaluation value for the facial skin of the sample users, and determine reference users from the sample users based on the evaluation value; Based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, the sample feature information of the facial skin of the reference user is determined, and the baseline skin parameters are determined based on the sample feature information; Obtain the skin parameters to be processed from the facial skin of the user to be processed; wherein, the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; Based on the baseline skin parameters and the skin parameters to be processed, the skin parameters to be adjusted for the user to be processed and the target values corresponding to the skin parameters to be adjusted are determined.
2. The method according to claim 1, characterized in that, The process of determining sample feature information of the facial skin of the reference user based on the sample skin parameters of the reference user and the evaluation parameters of the reference user, and determining benchmark skin parameters based on the sample feature information, includes: The sample skin parameters of the reference user and the evaluation parameters of the parameter user are processed; The facial skin sample feature information of the reference user is determined based on the processed sample skin parameters and the processed evaluation parameters; The sample feature information is processed, and the baseline skin parameters are determined based on the sample feature information and the processed sample feature information.
3. The method according to claim 2, characterized in that, The step of determining the baseline skin parameters based on the sample feature information and the processed sample feature information includes: The sample feature matrix is determined based on the sample feature information, and the baseline feature information is determined from the processed sample feature information. A reference coordinate system is constructed based on the aforementioned reference feature information; Based on the sample feature matrix, determine the first position of each reference user in the reference coordinate system, and determine the reference point based on the first position; The reference skin parameters are determined based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position.
4. The method according to claim 3, characterized in that, The process of determining the reference point based on the first position of each reference user in the reference coordinate system and the sample feature matrix includes: Based on the weight coefficients of each dimension corresponding to each coordinate axis of the reference coordinate system and the sample feature matrix, the first position of each reference user is determined. The reference point is determined based on the target outlier detection algorithm and each first position.
5. The method according to claim 3, characterized in that, The determination of the reference skin parameters based on the second position of the reference point in the reference coordinate system, the reference feature information, and the first position includes: Based on the target outlier detection algorithm and the target matrix determined at each first position, a first eigenvalue, a second eigenvalue, a third eigenvalue, and a fourth eigenvalue are determined based on the target matrix. A first value is calculated based on the first feature value and the target value, and a second value is calculated based on the second feature value and the target value. Calculate the target angle based on the third and fourth feature values; The target region is determined in the reference coordinate system based on the second position, the first value, the second value, and the target angle, and the reference skin parameters are determined based on the skin parameters of a reference user within the target region at the first position.
6. The method according to claim 1, characterized in that, The step of determining the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed, based on the baseline skin parameters and the skin parameters to be processed, includes: Based on the value of each of the aforementioned reference skin parameters, a first reference value and a second reference value are calculated for each of the aforementioned reference skin parameters; For each parameter in the skin parameters to be processed, the degree of difference corresponding to each parameter is calculated based on the value of each parameter, the first benchmark value, and the second benchmark value; Based on the degree of difference of each parameter, the skin parameter to be adjusted is determined from the skin parameters to be processed; The target value is determined based on the value of the skin parameter to be adjusted and the value of the skin parameter to be adjusted in the baseline skin parameters.
7. The method according to claim 6, characterized in that, The method further includes: Determine the priority of each skin parameter to be adjusted; The processing order of each skin parameter to be adjusted is determined based on the priority and the degree of difference of each skin parameter to be adjusted; The value of each skin parameter to be adjusted is set to the target value according to the processing order.
8. The method according to claim 3, characterized in that, The method further includes: Determine the feature information to be processed for the skin parameters to be processed; The feature information to be processed is subjected to dimensionality reduction processing, and the target position of the user to be processed in the reference coordinate system is determined based on the processed feature information; Based on the target location and the second location, the degree of deviation between the skin parameters to be processed of the user to be processed and the skin parameters corresponding to the reference point is determined.
9. An information determining device, characterized in that, The device includes The first acquisition unit is used to acquire sample skin parameters of multiple dimensions of the sample user's facial skin and evaluation parameters for the sample user's facial skin. The second acquisition unit is used to acquire the evaluation value of the facial skin of the sample users, and to determine the reference users from the sample users based on the evaluation value; The first processing unit is configured to determine sample feature information of the facial skin of the reference user based on the sample skin parameters of the reference user and the evaluation parameters of the parameter user, and to determine the baseline skin parameters based on the sample feature information. The first acquisition unit is further configured to acquire the skin parameters to be processed of the facial skin of the user to be processed; wherein, the skin parameters to be processed include skin parameters of multiple dimensions and evaluation parameters for the facial skin of the user to be processed; The second processing unit is used to determine the skin parameters to be adjusted and the target values corresponding to the skin parameters to be adjusted for the user to be processed, based on the baseline skin parameters and the skin parameters to be processed.
10. An information determining device, characterized in that, The device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute an information determination program in memory to implement the steps of the information determination method as described in any one of claims 1-8.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the information determination method as described in any one of claims 1-8.
12. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the information determination method according to any one of claims 1-8.