How to assess skin wrinkles

Abstract

Provided is an invention that makes it possible to more accurately evaluate the skin wrinkles of each individual.　A skin wrinkle evaluation method in which a skin wrinkle index for a given person is estimated on the basis of at least two values consisting of an age value and measured skin brightness value for the person. A wrinkle improvement composition evaluation or searching method including a step for using the wrinkle evaluation method to estimate a wrinkle index for a given person who has had a test substance administered thereto and a step for determining that the test substance is useful for wrinkle improvement if the estimated wrinkle index is lower than a wrinkle index for the given person from before the test substance was administered.

Description

[Technical field]

[0001] The present invention relates to a method for evaluating skin wrinkles. [Background technology]

[0002] In general, wrinkles on the skin tend to occur more frequently in areas such as the forehead, between the eyebrows, around the mouth, and at the corners of the eyes with age, but the state of wrinkles on the skin varies greatly between individuals. For this reason, in the fields of cosmetics, beauty, medicine, and the like, techniques for preventing, improving, or treating wrinkles on the skin have been proposed for each individual for the purpose of anti-aging, etc. For this reason, a method for accurately evaluating the state of wrinkles on the skin is required.

[0003] Conventionally, in order to evaluate the condition of wrinkles on the skin, a visual evaluation method for evaluating the skin condition, an instrumental measurement method for measuring the skin condition, and the like have been used. For example, in order to evaluate the condition of wrinkles, a visual evaluation method is known in which a professional evaluator performs an evaluation in accordance with the wrinkle grade standard table (0 to 7) in the guidelines (Non-Patent Document 1) published by the Japan Cosmetic Industry Association. For example, known measuring methods for evaluating the state of wrinkles include a two-dimensional image analysis method using oblique illumination with a replica of the wrinkled area, and a three-dimensional measurement method using a replica.

[0004] Furthermore, various methods for evaluating the condition of skin wrinkles with high accuracy have been investigated. For example, Patent Document 1 proposes a method for distinguishing skin texture and / or wrinkles, which includes a step of performing image processing, including cross binarization processing and / or short line matching processing, on a skin image to obtain physical quantities of the skin, and a step of substituting the physical quantities of the skin obtained in the above step into a prediction formula prepared in advance and distinguishing the obtained evaluation value as an evaluation value of skin texture and / or wrinkles. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2009 / 142069 [Non-patent literature]

[0006] [Non-Patent Document 1] Journal of the Japanese Society of Cosmetic Science, "Report of the Committee for the Review of Cosmetic Function Evaluation Methods: Guidelines for Cosmetic Function Evaluation Methods," Vol. 30, No. 4, pp.316-332 (2006). Summary of the Invention [Problem to be solved by the invention]

[0007] Furthermore, the inventors considered that by being able to evaluate skin wrinkles for each individual more easily and accurately, it would be easier to propose better skin care techniques for preventing, improving, or treating skin wrinkles that are suitable for each individual. Therefore, a main object of the present invention is to provide a technique for evaluating skin wrinkles for each individual more easily and accurately. [Means for solving the problem]

[0008] As a result of intensive research, the inventor was able to find a new optimum combination of age and skin condition that can estimate an index value of skin wrinkles for each individual based on the accumulation of the results of the device evaluation over a long period of time for each individual and the results of the multivariate analysis, and was also able to find a new wrinkle prediction model that fits well. As a result, the inventor has completed the present invention as follows.

[0009] The present invention provides a method for assessing skin wrinkles, which estimates a wrinkle index value of a subject's skin based on at least two of the subject's age and a measurement value of skin brightness. The method for evaluating skin wrinkles may estimate an index value for the subject's skin wrinkles based on the above two and one or two of a measurement value of skin redness and / or a measurement value of the amount of sebum on the skin. The method for evaluating skin wrinkles may estimate an index value for the wrinkles of the subject's skin by using two items, the subject's age and a measured value of skin brightness, in a wrinkle prediction model. The method for evaluating skin wrinkles may estimate an index value for the wrinkles of the subject's skin by using two measurements of the subject's age and skin brightness, and one or two of a measurement of skin redness and / or a measurement of the amount of sebum on the skin in a wrinkle prediction model. The wrinkle prediction model may be a model obtained by deriving an individual's wrinkle index value as a dependent variable using a linear mixed effects model including at least the individual's age and skin brightness measurements as explanatory variables. The wrinkle prediction model may be such that parameters of the linear mixed effects model are obtained using a maximum likelihood method or a restricted maximum likelihood method.

[0010] The present invention provides a method for evaluating wrinkles, comprising: estimating a wrinkle index value of the skin of a subject administered a test substance using the wrinkle evaluation method; It is possible to provide a method for evaluating or searching for a composition for improving wrinkles, which includes a step of identifying the test substance as being for improving wrinkles if the estimated skin wrinkle index value is lower than the wrinkle index value of the subject's skin before administration, thereby improving wrinkles. Effect of the Invention

[0011] The present invention can provide a technique for evaluating skin wrinkles more easily and accurately for each individual. Note that the effects described herein are not necessarily limited, and may be any of the effects described in the present invention. [Brief description of the drawings]

[0012] [Figure 1] 1 is a flowchart showing an example of a method for evaluating skin wrinkles of the present invention. [Diagram 2] 1 is a flowchart showing an example of a method for evaluating skin wrinkles of the present invention. [Diagram 3] 1 is a flowchart showing an example of a method for evaluating skin wrinkles of the present invention. [Figure 4] FIG. 1 is a hardware configuration diagram showing an embodiment of the present invention. [Diagram 5] 1 is a schematic diagram showing an example of a skin wrinkle evaluation device or system of the present invention. [Figure 6] 1 is a diagram showing an example of the method for evaluating skin wrinkles and the method for providing information for improving wrinkles of the present invention. [Figure 7] FIG. 1 is a block diagram showing a simplified processing procedure of a general specialized AI. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] A preferred embodiment for carrying out the present invention will be described below. Note that the embodiment described below shows an example of a typical embodiment of the present invention, and the scope of the present invention is not narrowly interpreted by this. Furthermore, in this specification, percentages are expressed by mass unless otherwise specified. Furthermore, the upper and lower limit values ​​of each numerical range (~) can be arbitrarily combined as desired.

[0014] 1. Method for Evaluating Skin Wrinkles According to the Present Invention

[0015] The present invention provides a method for evaluating skin wrinkles, which estimates an index value of skin wrinkles of a subject based on at least two values, the subject's age and the measured value of skin brightness, thereby enabling accurate and simple evaluation of skin wrinkles for each individual.

[0016] Furthermore, the present invention is suitable for combining the two values ​​(age value, skin brightness measurement value) with one or two values ​​of skin redness measurement value and / or skin sebum amount measurement value, and estimating the wrinkle index value of the subject's skin based on these values. This allows for more accurate and easier evaluation of skin wrinkles for each individual.

[0017] Furthermore, the present invention is more suitable for estimating the wrinkle index value of the subject's skin by using the wrinkle prediction model and the two values ​​of the subject (age value, skin brightness measurement value) or two or more values ​​selected from the four values ​​of the subject. The wrinkle prediction model has high model performance, can use instrumental evaluation, and can provide a wrinkle prediction model that is suitable for each individual with good fit. This allows skin wrinkles to be evaluated more accurately and more simply for each individual.

[0018] Furthermore, the present invention can evaluate the wrinkles of the skin of a subject by comparing the index value of the wrinkles of the skin with a reference value of the skin condition, which makes it possible to propose skin care (especially skin care for wrinkles) suitable for the subject more simply and accurately. The reference value of the skin condition may be a value that can be obtained using the wrinkle prediction model, and specifically, can be obtained by using (e.g., substituting) preset values ​​(such as age, skin brightness, skin redness, and sebum amount) in the wrinkle prediction model. As values ​​for obtaining the reference value, it is preferable that the age value and the skin condition (such as skin brightness, skin redness, and sebum amount) are linked to each other. The reference value for the skin condition may be a reference value for a general skin condition (for example, an average value for each skin condition for an age or age group corresponding to the age or age group of the subject).

[0019] The present invention will now be described in more detail.

[0020] 1-1. Target Audience The subject is not particularly limited, and is preferably a human, regardless of age or gender. From the viewpoint of good wrinkle prediction accuracy, the subject is more preferably a female. The subject's race is not particularly limited, but is preferably Caucasian (white) or Mongoloid (yellow), and more preferably Mongoloid (preferably Mongoloid A, B, or C). The subject's ethnicity is preferably one or more selected from Chinese, Korean, and Japanese, and more preferably Japanese. In this specification, the term "subject" refers to a person whose wrinkle index value is estimated using the evaluation method of the present invention.

[0021] The age group of the subject is not particularly limited, but the lower limit is preferably 18 years or older, more preferably 20 years or older, and even more preferably 22 years or older, and the upper limit is not particularly limited, but can be, for example, 80 years or younger, 70 years or younger, or 60 years or younger. From the viewpoint of good wrinkle prediction accuracy, the preferred numerical range is more preferably 18 to 70 years old, and even more preferably 22 to 60 years old.

[0022] 1-2. Evaluation of subject's age and skin condition In the evaluation method of the present invention, a value of a certain age of a subject and measured values ​​of skin conditions at that age (measurements of skin brightness, skin redness, amount of sebum, etc.) are used. The value of a certain age of a subject and the measured values ​​of each skin condition at that age may be correlated or linked to each other.

[0023] 1-2-1. Age value The age value is not particularly limited, but when evaluating the current state of skin wrinkles, it is preferable that the age value be the actual age of the subject. In this specification, "age" can be expressed as full age + "number of months elapsed since birth month", or full age + "number of months elapsed since birth month / 12 months". For example, if an age is 30 years and 6 months, it can be expressed as 30.5. The "age" may also be converted to "monthly age" which is "number of months elapsed since birth date".

[0024] 1-2-2. Skin brightness measurements The brightness of the skin is the "lightness L*" when the skin color is expressed in the L*a*b* color system. In the L*a*b* color system, lightness is represented by L*, and chromaticity, which indicates hue and saturation, is represented by a* and b* (a* and b* indicate the direction of the color, with a* representing the red direction, -a* representing the green direction, b* representing the yellow direction, and -b* representing the blue direction). Furthermore, the measured values ​​of skin color such as skin brightness and redness used in the present invention are not limited to values ​​obtained by a measuring instrument capable of measuring the L*a*b* color system, but values ​​converted from measured values ​​obtained by a measuring instrument capable of measuring other color systems (e.g., values ​​of the XYZ color system, RGB color system, etc.) into the L*a*b* color system may be used as the measured values ​​of skin brightness, skin redness, etc. (e.g., Chaki Kiyoshi, "Measurement of Color," Color Materials, 57

[10] , pp. 558-568, 1984; Kodera Hiroteru, "Development of Color Space," Journal of the Imaging Society of Japan, Vol. 43, No. 2, pp. 73-81, 2004).

[0025] The measured value of the skin brightness can be obtained using a measuring device or an imaging device capable of measuring the L*a*b* color system, etc. As described above, the "brightness L*" of a value converted from a value of another color system such as the XYZ color system or the RGB color system to a value of the L*a*b* color system may be used as the measured value of the skin brightness. The site of the skin to be measured is not particularly limited, but is preferably the skin of the face, and more preferably the cheek (more specifically, the upper cheek).

[0026] The present invention may be configured such that, when an operator or a control unit selects a color panel (such as an image) that is the same as or similar to the subject's skin brightness, the control unit can select the measurement data of skin brightness linked to the data of the selected color panel as the measurement data of the subject's skin brightness. It is preferable that the color tone (color system value) of each color panel and the measurement data of skin brightness corresponding to the color tone (color system value) of each color panel are stored in advance, and the measurement data is preferably set and stored as the measurement data of skin brightness linked to the data of the color panel, thereby making it easy to convert between the two. In addition, "associating and storing" may mean storing specific data and other data in association with each other, but is not limited to this.

[0027] In order to measure the brightness of the skin, it is generally preferable to use a measuring device capable of measuring the L*a*b* color system (e.g., a handy color difference meter conforming to the JIS standard, a spectrophotometer, etc.), but the present invention is not limited thereto, and an imaging device (e.g., a camera, a video camera, a mobile terminal, etc.) may also be used. A color panel may also be used.

[0028] The color difference meter is not particularly limited, but is preferably one that complies with the JIS standard. As the spectrophotometer, an integrating sphere type spectrophotometer, for example, a CM-700d spectrophotometer (manufactured by Konica Minolta, Inc.) can be used. Also, a color panel can be used.

[0029] 1-2-3. Skin redness measurement The redness of the skin is the "chromaticity a*" when skin color is expressed in the L*a*b* color system. It should be noted that the terms "L*a*b* color system," "measuring equipment capable of measuring the L*a*b* color system," and "imaging device" overlap with what was stated above in "Measured values ​​of skin brightness," and so will be omitted here.

[0030] The measured value of the redness of the skin can be obtained using a measuring device capable of measuring the L*a*b* color system, or an imaging device. As described above in "Measured Value of Skin Brightness," the "chromaticity a*" obtained by converting values ​​in other color systems, such as the XYZ color system and the RGB color system, into values ​​in the L*a*b* color system may be used as the measured value of the redness of the skin. The site of the skin to be measured is not particularly limited, but is preferably the skin of the face, and more preferably the cheek (more specifically, the upper cheek).

[0031] The present invention may also be configured such that, when an operator or a control unit selects a color panel (such as an image) that is the same as or similar to the redness of the subject's skin, the control unit can select the measurement data of the skin redness linked to the data of the selected color panel as the measurement value of the skin redness of the subject. It is preferable that the color tone (color system value) of each color panel and the measurement data of the skin redness corresponding to the color tone (color system value) of each color panel are stored in advance, and the measurement data is preferably set and stored as the measurement data of the skin redness linked to the data of the color panel, thereby making it easy to convert between the two.

[0032] 1-2-4. Measurement of the amount of sebum on the skin The amount of sebum on the skin is the amount of sebum secreted on the surface of the skin. The measurement value of the amount of sebum on the skin can be obtained using a measuring device capable of measuring the amount of sebum or an imaging device. In this case, the part of the skin to be measured is not particularly limited, but is preferably the skin on the face, and more preferably the forehead (more specifically, the center of the forehead) from the viewpoint of being able to collect a stable amount of sebum within a short measurement time.

[0033] To measure the amount of sebum on the skin, it is generally preferable to use a measuring device capable of measuring the amount of sebum on the skin surface (e.g., a Sebumeter, etc.), but this is not limited thereto, and an imaging device (e.g., a camera, a video camera, a mobile terminal, etc.) may also be used.

[0034] The sebum amount measuring device may be, for example, a spectrophotometer Sebumeter SM 815 (manufactured by Courage+Khazaka). With the sebum amount measuring device, sebum secreted on the skin surface is attached to a tape, and the light transmittance is measured to obtain a measurement value of the sebum amount.

[0035] According to the present invention, as described above, the skin brightness measurement value, the skin redness measurement value, and the sebum amount measurement value can be measured by a skin condition measuring device such as a measuring instrument or an imaging device, and there is no need to perform a human sensory evaluation. In the case of an imaging device, the captured imaging data or image data may be converted into a measurement value of each skin condition (e.g., skin brightness, skin redness, skin sebum amount, etc.) by a program capable of converting the captured imaging data or image data into a measurement value of each skin condition (e.g., WO2013 / 094442, JP Patent Publication No. 8-308634, etc.). By using the measurement value obtained from the skin condition measuring device in this way, it is possible to obtain a measurement value of the skin condition that is more convenient, more accurate, and has less variation than a human sensory evaluation.

[0036] When the measurement is carried out, the subject's makeup state (presence or absence, etc.) is not particularly limited, and the subject may be wearing makeup. More preferably, the subject should have bare skin (more preferably a bare face) from the viewpoint of enabling more accurate evaluation of wrinkles, and more preferably, the subject should wash the skin (face) with a skin cleanser such as a facial cleanser to bring the skin (face) to a bare skin (bare face) state before carrying out the measurement. The part on which the measurement is carried out may be bare skin or skin after washing. In this specification, "bare skin (bare face)" refers to "skin (face) without makeup, in its natural state." More specifically, from the viewpoint of improving the accuracy of wrinkle evaluation, it is preferable to wash the face with a facial cleanser to make the face bare, and then to acclimate the face in an indoor environment for 20 to 60 minutes before carrying out the measurement. More specifically, it is preferable to acclimate the face in an environment controlled at 20 to 22°C and 50±5% for 30 minutes after the face washing, and then to carry out the measurement.

[0037] 1-3. Estimation of the subject's skin wrinkle index value As described above, the present invention can estimate the wrinkle index value of a subject's skin based on two or more values ​​selected from the group consisting of the value of the subject's age, the measured value of the skin brightness, the measured value of the skin redness, and the measured value of the amount of sebum. Preferably, the index value includes at least the two values ​​of the value of the age and the measured value of the skin brightness. As shown in the following [Examples], the "skin wrinkle index value" shows a high positive correlation with the "wrinkle grade standard table (0,1,2,3,4,5,6,7)" according to the guidelines published by the Japan Cosmetic Industry Association (Journal of the Japanese Cosmetic Science Society, "Cosmetic Function Evaluation Method Review Committee Report: Cosmetic Function Evaluation Method Guidelines", Vol. 30, No. 4, pp.316-332 (2006).). Thus, the "skin wrinkle index value" corresponds to the "wrinkle grade standard table" that has been conventionally used as a standard without any special conversion. Therefore, the skin wrinkle index value of the present invention can be said to be a value with high wrinkle prediction accuracy and high reliability. In addition, the skin wrinkle index value of the present invention can be used as the wrinkle grade of the "wrinkle grade standard table". Furthermore, in the skin wrinkle evaluation method of the present invention, it is easy to utilize information such as literature that adopts the "wrinkle grade standard table".

[0038] Previously, the "Wrinkle Grade Standard Table" (Wrinkle Grade) based on the guidelines issued by the Japan Cosmetic Industry Association was a visual sensory evaluation, so in order to ensure the accuracy of the wrinkle evaluation, a high level of training was required to become an expert evaluator. In addition, with sensory evaluation, the more subjects there are, the more likely it is that there will be inconsistencies in judgment, and there is a risk that the accuracy of the wrinkle evaluation will decrease. However, in the present invention, the measured values ​​of the skin condition are evaluated by using a measuring device or an imaging device, so that the measurer who measures the skin condition does not need to have a high level of skill, as is required for sensory evaluation. Furthermore, since the measured values ​​used in the present invention are evaluated by using a measuring device, the variation in the values ​​can be reduced compared to the variation in sensory evaluation. In addition, the present invention uses a measuring device to homogenize the ability of the measurer and the measurement method. Therefore, even if measurements are performed multiple times or over a long period of time, the reliability of the measured data is high. In this way, the present invention can use instrumental evaluation, making it possible to more easily and accurately evaluate wrinkles on a subject's skin.

[0039] 1-4. Wrinkle prediction model In the skin wrinkle evaluation method of the present invention, it is preferable to use a wrinkle prediction model. It is preferable that the wrinkle prediction model is a model obtained by deriving the model using a linear mixed effects model in which the wrinkle index value of an individual is used as the objective variable and the age (age value) and skin brightness (measurement value of skin brightness) of the individual are at least included as explanatory variables. Furthermore, the parameters (variables) of the linear mixed effects model are preferably obtained using the maximum likelihood method or the restricted maximum likelihood method. Note that the maximum likelihood method is a method in statistics for point estimating the parameters of the probability distribution to which given data follows. The restricted maximum likelihood method is a method for estimating parameters related to the variance of a linear mixed effect model, and is a maximum likelihood method for a likelihood function restricted to "error contrast" rather than the data itself.

[0040] It is more preferable that the explanatory variables further include one or two of skin redness (measured redness value) and / or skin sebum amount (measured sebum amount value) in addition to the above-mentioned age value and skin brightness measurement value, and it is even more preferable that the explanatory variables include these four.

[0041] In the method for evaluating skin wrinkles of the present invention, it is more preferable that the wrinkle prediction model uses at least two values ​​(age value and skin brightness measurement value) as described above. Even more preferable that the wrinkle prediction model uses two values, age value and skin brightness measurement value, and one or two values, skin redness measurement value and / or skin sebum amount measurement value. This makes it possible to evaluate skin wrinkles more simply and accurately.

[0042] In addition, in the wrinkle evaluation method of the present invention, as described above, the wrinkle prediction model can use two or more values ​​selected from the subject's "age value", "measurement value of skin brightness", "measurement value of skin redness", and "measurement value of skin sebum amount" to estimate the current wrinkle index value (wrinkle grade). Separately, a value for predicting the subject's future wrinkle state ("age", "skin brightness", "skin redness", "skin sebum amount") can be appropriately selected, and the selected value for predicting future wrinkles can be used to obtain a future wrinkle standard value. The current wrinkle prediction model can be used as the wrinkle prediction model when obtaining this future wrinkle standard value. Furthermore, by comparing the current wrinkle standard values ​​with future wrinkle standard values ​​(predictions), it is possible to suggest skin care for the subject.

[0043] In addition, the past wrinkle index value can be obtained as the wrinkle standard value in the same manner as described above using the subject's past age and the measured value of the past skin condition at that time. This makes it possible to propose skin care for the subject by comparing and examining the current wrinkle index value, the past wrinkle index value, and the future wrinkle standard value (prediction), etc. When obtaining the past wrinkle index value, a past wrinkle prediction model or a current wrinkle prediction model may be used.

[0044] 1-4-1.Prediction factors of wrinkle prediction model The wrinkle prediction model is preferably a wrinkle prediction model that is configured from specific wrinkle predictor factors. The number of the specific wrinkle predicting factors is not particularly limited, but is preferably 2 to 5 (specifically, 2, 3, 4, or 5), more preferably 3 to 5, even more preferably 4 to 5, and even more preferably 5.

[0045] Examples of the specific wrinkle predictor include "age," "skin brightness," "skin redness," "skin sebum amount," "interaction term between sebum amount and skin redness," etc. As the interaction, a multiplicative interaction is preferable.

[0046] Of these, two or more wrinkle predictors selected from the five wrinkle predictors of "age," "skin brightness," "skin redness," "skin sebum amount," and "interaction term between sebum amount and skin redness" are preferred. Among these five wrinkle predictors, at least two (specifically, "age" and "skin brightness") are important in the wrinkle prediction model of the present invention from the viewpoint of good wrinkle prediction accuracy. Therefore, in the wrinkle evaluation method of the present invention, a wrinkle prediction model composed of wrinkle predictors including at least these two is preferable. By using two of the subject's "age value" and "measurement value of skin brightness" in the wrinkle prediction model, the wrinkle index value can be obtained simply and with high accuracy.

[0047] Furthermore, the above two wrinkle predictors (specifically, "age" and "skin brightness") include one or more wrinkle predictors selected from the group consisting of "skin redness", "skin sebum amount", and "interaction term between sebum amount and skin redness", and a wrinkle prediction model composed of these wrinkle predictors is more preferable from the viewpoint of enabling more accurate wrinkle evaluation. More specifically, a wrinkle prediction model consisting of two wrinkle predictors, "age" and "skin brightness", and one or two wrinkle predictors, "skin redness" and / or "skin sebum amount", is more preferable. By using three or four values ​​of a subject (specifically, "age value", "measurement value of skin brightness", "measurement value of skin redness", and "measurement value of skin sebum amount") in the wrinkle prediction model consisting of three or four factors, a wrinkle index value can be obtained easily and more accurately.

[0048] Furthermore, in the wrinkle prediction model of the present invention, a wrinkle prediction model consisting of the above five wrinkle prediction factors (specifically, "age", "skin brightness", "skin redness", "skin sebum amount", and "interaction term between sebum amount and skin redness") is even more preferable from the viewpoint of particularly good wrinkle prediction accuracy. By using four subject's values ​​(subject's "age value", "measured skin brightness value", "measured skin redness value", and "measured skin sebum amount") in the wrinkle prediction model, the wrinkle index value can be obtained simply and with high accuracy.

[0049] In the wrinkle prediction model of the present invention, wrinkle prediction factors other than the above-mentioned five wrinkle prediction factors (e.g., skin moisture content, transepidermal water loss, etc.) may be included in the configuration of the wrinkle prediction model of the present invention. However, from the viewpoint of wrinkle prediction accuracy as described above, the wrinkle prediction model using the above-mentioned five wrinkle prediction factors is the most preferable model.

[0050] Examples of equations for the wrinkle prediction model of the present invention (hereinafter also referred to as "wrinkle prediction equations") include, but are not limited to, wrinkle prediction equations 1 to 7 described below. Among Wrinkle Prediction Formulas 1 to 7, Wrinkle Prediction Formula 1 and Wrinkle Prediction Formula 2 are preferred since they have better wrinkle prediction accuracy and can be used as standard for subjects, and Wrinkle Prediction Formula 1 is more preferred since it has better wrinkle prediction accuracy.

[0051] <Wrinkle prediction formula 1 (Formula 1)>

[0052] Wrinkle grade i =0.1469×Age + 0.7540×Ln(sebum) + 0.3270×Skin color a* + 0.1654×Mean[Skin color L*] - 0.1044×[Ln(sebum)×Skin color a*] - 15.90 + b 0,i (Formula 1) b 0,i ~N(0, 0.4847) Final equation for prediction of wrinkle grade in Japanese women aged 22-60 years

[0053] <Wrinkle prediction formula 2 (Formula 2)>

[0054] Wrinkle grade i = 0.1200~0.2053×Age + 0.2200~1.280×Ln(sebum) + 0.050~0.5710×Skin color a* + 0.050~0.4000×Mean[Skin color L*] - 0.030~0.1800×[Ln(sebum)×Skin color a*] - 25.00~7.600 (Formula 2)

[0055] In the method of the present invention, by performing each step of the present invention, an index value of wrinkles on the subject's skin can be estimated, and since this index value has a high correlation with a sensory evaluation of the "Wrinkle Grade Standard Table" by visual inspection by a professional evaluator, it can be used as an evaluation value of skin wrinkles at the same level as the "Wrinkle Grade Standard Table." Therefore, by having a subject select two or more from the group consisting of age, measured values ​​of skin color (brightness, redness), and measured values ​​of sebum amount, and applying these to the wrinkle prediction model or wrinkle prediction formula of the present invention, the wrinkle index value of the subject's skin can be estimated, and further, skin wrinkles can be evaluated based on the index value. Therefore, the wrinkle evaluation method of the present invention can easily and accurately provide a wrinkle index value that has a high positive correlation with the wrinkle evaluation derived by a professional evaluator according to the "Wrinkle Grade Standard Table."

[0056] The method of the present invention does not rely on sensory evaluation, but can use instrumental evaluation using a skin condition measuring device such as a measuring device or an imaging device, so that wrinkles on the skin can be evaluated more easily, more accurately, and more objectively. Therefore, the deterioration of the accuracy of wrinkle evaluation caused by the skill level of the measurer or individual differences can be reduced. Furthermore, by using the wrinkle prediction model of the present invention, the future wrinkle index value for each individual can be easily and accurately predicted. Furthermore, it is possible to propose skin care that corresponds to these future wrinkles.

[0057] The method for evaluating skin wrinkles in the present invention may be used for non-therapeutic purposes, and the evaluation results may ultimately be used for therapeutic purposes. The present invention can be applied to, for example, a method for assisting in the diagnosis of skin wrinkles, rather than a direct medical procedure by a doctor. Here, "non-therapeutic purposes" is a concept that does not include medical procedures, i.e., treatments performed on the human body by treatment, and non-therapeutic purposes include, for example, cosmetic purposes and the provision of skin care products. The advantage of the present invention is that the above-mentioned measurements of age and skin condition can be evaluated or measured by devices such as measuring instruments or imaging devices without being performed by a doctor. In the present invention, "prevention" refers to preventing or delaying the onset of symptoms or disease in a subject, or reducing the risk of onset of symptoms or disease in a subject, etc. In this technology, "improvement" refers to improving or maintaining a disease, symptom, or condition in a subject; preventing or delaying deterioration; or reversing, preventing, or delaying progression.

[0058] 1-4-2.How to create a wrinkle prediction model The wrinkle prediction model of the present invention can be created according to the flow of the below-mentioned [Example], and an example of this is shown below, but the wrinkle prediction model of the present invention is not limited thereto. The number of participants when preparing a wrinkle prediction model may be, for example, 40 to 60 people, but is not limited thereto. As the number of tests, skin characteristics are evaluated at least once a year for the participants. The test period is not particularly limited, but is preferably 4 to 6 years. As a test method, the participants wash their faces with a facial cleanser to make their skin bare, and then allow them to acclimate for 30 minutes in an environment controlled at 20 to 22°C and 50±5%, and then obtain the measurement values ​​of each skin condition. A more specific test method can be performed by referring to the description in the following [Examples]. A generalized linear mixed-effects model can be used for the statistical analysis to create a wrinkle prediction model. A stepwise method using elimination of variables is used to select wrinkle predictors, and the model with the smallest AIC (Akaike Information Criterion) is determined to be the best model. Sensitivity analysis is performed using the wrinkle predictors obtained. For the analysis, it is preferable to use R ver.3.5.2 statistical software, but this is not limiting as long as it is capable of performing statistical analysis to create a wrinkle prediction model.

[0059] 2. Application Examples of the Skin Wrinkle Evaluation Method of the Present Invention The skin wrinkle evaluation method, skin wrinkle evaluation device, skin wrinkle evaluation system, etc., according to the present invention can be described with reference to Figs. 1 to 7, but the present invention is not limited to these figures. 2-1. Skin wrinkle evaluation device and evaluation system The skin wrinkle evaluation method of the present invention can also be realized by a control unit including a CPU (Central Processing Unit) in a skin wrinkle evaluation device (e.g., a computer, etc.) (see, for example, Figs. 4 to 6, etc.). For example, the present invention may be a skin wrinkle evaluation method or a method of providing a skin wrinkle evaluation by a computer by causing a computer to execute the skin wrinkle evaluation method related to the present invention (wrinkle prediction model, wrinkle evaluation procedure, program, etc.) (see, for example, Figs. 1 to 3, Fig. 7, etc.). The method of the present invention can also be stored as a program in hardware resources including a recording medium (non-volatile memory (such as a USB memory), HDD, CD, DVD, Blu-ray (registered trademark) Disc, network server, etc.) and realized by a control unit that determines the skin wrinkle evaluation. Alternatively, by providing or using the control unit, it is possible to provide a skin wrinkle evaluation system, an evaluation or search system for wrinkle-improving compositions, or devices thereof. It is preferable that the recording medium is a computer-readable recording medium.

[0060] The wrinkle evaluation device or system may include an input unit such as a keyboard, a communication unit such as a network, an output unit such as a display, a storage unit such as a HDD, a measurement unit for measuring the skin condition such as the above-mentioned measuring device or imaging device, etc. The device or system preferably includes an input unit, an output unit, and a storage unit, and further preferably includes a communication unit and / or a measurement unit. The input unit can receive user operations by an operator who uses the wrinkle evaluation method. The input unit can include, for example, a mouse and / or a keyboard. In addition, the display surface of the display device may be configured as the input unit that receives touch operations. The output unit can output the obtained skin wrinkle evaluation and related information (e.g., a table, a diagram, an explanatory text, etc.) The output unit can be, for example, a display device that displays an image, a speaker that outputs sound, a printer that prints on a print medium such as paper, etc., but is not limited to these. The storage unit can store data input by an operator and data set in advance for wrinkle evaluation (e.g., wrinkle prediction model, etc.). The storage unit may include, for example, a recording medium.

[0061] Specific examples of the skin wrinkle evaluation device are not particularly limited as long as they are equipped with a CPU, and include, but are not limited to, mobile terminals (e.g., notebook computers, smartphones, tablet terminals, etc.), desktop personal computers, servers, cloud computing, etc. The skin wrinkle evaluation device is preferably a device further equipped with a measurement unit, and is preferably, for example, a mobile terminal equipped with a camera (e.g., a web camera).

[0062] In addition, data relating to wrinkle evaluation, such as a program relating to the skin wrinkle evaluation method of the present invention, a wrinkle prediction model, wrinkle evaluation results obtained by the wrinkle evaluation method, and data for executing each step of the present invention, may be stored inside the wrinkle evaluation device, or in a memory unit or server outside the device, or on the cloud.

[0063] <Example of Hardware Configuration of Skin Wrinkle Evaluation Device and Evaluation System of the Present Invention> The skin wrinkle evaluation device and evaluation system of the present invention can be implemented by utilizing a program and hardware. An embodiment of a computer 1 according to an embodiment of the present invention will be described below with reference to Figs. 4 to 6, but the present invention is not limited thereto. The components of the computer 1 include at least a CPU, and may further include one or two selected from a RAM, a storage unit, an output unit, an input unit, a communication unit, a ROM, and a measurement unit, and among these, it is preferable to include a RAM, a storage unit, an output unit, and an input unit, and it is preferable to further include at least one of a communication unit, a measurement unit, a ROM, and the like. The components are connected, for example, by a bus as a data transmission path (see Fig. 4).

[0064] The CPU is realized by, for example, a microcomputer, and controls each component of the computer 1. The CPU can use, for example, a control unit capable of performing data acquisition, data processing, evaluation, and other determinations. These data acquisitions can be realized or executed by, for example, a program, and the CPU can function by reading this program. The ROM can store programs used by the CPU, control data such as calculation parameters, and the like. The RAM can temporarily store, for example, programs executed by the CPU.

[0065] The storage unit can store various data, and can store all or part of the data involved in the implementation of the present invention. The data is not particularly limited, and examples thereof include personal data for each subject, wrinkle evaluation data, product recommendation data, calculation parameters, programs, etc. The storage unit can function as a database present inside or outside the device. The storage unit can be realized, for example, by using a storage device, etc.

[0066] The output unit can output information such as: personal data for each subject, such as items for identifying the subject (e.g., name, serial number, etc.), the subject's age value, and the measurement value of the subject's skin condition; wrinkle evaluation data, such as wrinkle index values, wrinkle evaluation results, optimal wrinkle risk, future wrinkle prediction, charts such as figures, tables, graphs, etc., or images of wrinkled areas; and product proposal data, such as display columns for one or more recommended products (product names, product images, etc.), such as "current recommendations, recommended items for ages . . .," and "broader recommended items" than these. The output unit can output, for example, each measurement value input column (numerical value input, color panel selection, etc.), each index value, wrinkle evaluation result, recommended product, etc., to the operator or subject. The output unit can be realized by a display unit, such as an LCD (Liquid Crystal Display) or an OLED (Organic Light-Emitting Diode), for example. The input unit can also acquire information input by the operator or the subject, such as items for identifying the subject, the subject's age, and measurements of the subject's skin condition. The input unit can be realized by, for example, a microphone, a touch sensor, a keyboard, a mouse, a camera, etc. The input unit can acquire data for evaluating skin wrinkles, for example, from input of each measurement value, selection of each color panel image, selection of each level, selection of each index value, etc.

[0067] The communication unit may have a function of communicating via an information and communication network using communication technologies such as Wi-Fi, Bluetooth (registered trademark), LTE (Long Term Evolution), etc. The example computer 1 may include a communication I / F (interface).

[0068] The computer 1 may be, for example, a PC (Personal Computer) 1a, a server 1b, a smartphone terminal 1c, a tablet terminal, a mobile phone terminal, a PDA (Personal Digital Assistant), or a wearable terminal (such as a Head Mounted Display (HMD), a glasses-type HMD, or a band-type terminal) (see FIG. 5). These may be standalone or connected via a network.

[0069] The program for executing the method of the present invention may be stored in a computer device or computer system other than the computer 1. In this case, the computer can use a cloud service that provides the functions of the program (see FIG. 5). Examples of such cloud services include SaaS (Software as a Service), IaaS (Infrastructure as a Service), and PaaS (Platform as a Service).

[0070] Furthermore, this program can be stored in various types of computer-readable recording media and supplied to a computer. Examples of computer-readable recording media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), Compact Disc Read Only Memory (CD-ROM), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM, programmable ROM (PROM), erasable PROM (EPROM), flash ROM, random access memory (RAM)). The above program may also be supplied to a computer by various types of computer recording media.

[0071] The computer 1 can be configured in a variety of ways, including but not limited to the above, and can be modified to other configurations as appropriate.

[0072] An operator or a subject inputs data into the input section of the computer 1, including at least two values, the subject's age and the measured value of skin brightness, and one or two values, the measured value of skin redness and / or the measured value of skin sebum amount. The control section may select and input such data, and at this time, the control section may access the storage section and transmit the data related to the data from the storage section to the control section. When inputting data, in addition to inputting numerical values, a color panel image may be selected from a plurality of color panel images, or a level may be selected from a level bar, etc., and the control section may obtain data such as age and each measurement value based on the image or level by selecting the image or level.

[0073] For example, in the case of skin brightness, an image that is most similar to or has the same color as the brightness of the subject's skin is selected from among the brightness color panel images, and the brightness measurement value linked to the selected image data is used as the brightness measurement value data of the subject. Similarly, in the case of skin redness, an image that is most similar to or has the same color as the redness of the subject's skin is selected from among the redness color panel images, and the redness measurement value linked to the selected image is used as the redness measurement data of the subject. In the case of skin sebum amount, a level is selected using a level bar or the like, and the numerical value of the selected level is used as the measurement data of the subject's sebum amount.

[0074] Furthermore, when computer 1 is equipped with one or more types of measuring units, data on each measurement value may be transmitted from the measuring unit to be input to the control unit. Furthermore, measurement value data obtained by measuring the subject with measuring device 2 located outside computer 1 may be transmitted to computer 1 or its control unit via a network and input thereto (see FIG. 5).

[0075] This allows computer 1 to use the skin wrinkle evaluation method of the present invention to estimate an index value for the subject's skin wrinkles from these data, obtain a wrinkle evaluation result for the subject, and provide this evaluation result to an operator or the subject as wrinkle information. Furthermore, computer 1 can output wrinkle evaluation data and personal data obtained based on the skin wrinkle evaluation result to the output unit. Furthermore, computer 1 may output recommended products based on the skin wrinkle evaluation result to the output unit.

[0076] The computer 1 can output, for example, the wrinkle risk of the subject as wrinkle evaluation data of the subject, and provide this information to the operator or the subject. More specifically, for example, the current wrinkle risk of the subject and the best wrinkle risk pattern (for example, a graph of a linear function), the degree of risk reduction that the subject aims to achieve (for example, the subject's past, present, and future facial images), etc. can be output. Furthermore, the computer 1 can output one or more recommended products (for example, cosmetics, skin topicals, etc.) for the subject as recommended items. Examples of the "recommended items" include "current recommended items" for presenting products suitable for the current situation, "switching items from age . . . " for presenting products suitable for the future, and "widened recommended items" for broadening the range of product selection of the subject, but are not limited thereto, and the operator or subject can appropriately switch or select the output "recommended items" items.

[0077] The computer example 1 can store these result data in the memory unit as the personal data of the subject, linked or attached to the data of the items that identify the subject. This allows the control unit to access the memory unit as appropriate and use these result data in the memory unit for various purposes. The proposal or provision of recommended products will be explained later in "3. Method for evaluating or searching for a wrinkle-improving composition according to the present invention."

[0078] 2-2. Example of skin wrinkle evaluation according to the present invention The procedure for evaluating skin wrinkles according to the present invention will be described in more detail below, but the skin wrinkle evaluation according to the present invention is not limited thereto. The explanation of the procedure for evaluating skin wrinkles may also be a description of the operation of the method for evaluating skin wrinkles, the device for evaluating skin wrinkles, and the evaluation system according to the present invention.

[0079] The operator who performs the skin wrinkle evaluation may input various data such as the subject's age, the measured value of the skin brightness, and items that identify the subject (e.g., name, identification number, etc.) into the input unit. This data is then transmitted from the input unit to the control unit. The storage unit may be configured to store data of items for identifying the subject (e.g., name, serial number, etc.) in advance in association with data of the measured values ​​of the skin condition and / or data of the age of the subject, input by an operator. The control unit may be configured to control the data associated with the inputted identification items of the subject so that the data is transmitted from the storage unit to the control unit.

[0080] In addition, when the measurement unit measures the skin condition of the subject, the measurement unit may be configured to transmit data of the measurement value to the control unit. In this case, the control unit may be configured to store the data together with specific items of the subject in the storage unit.

[0081] 2-2-1. Embodiments 1 and 2 of the present invention relating to evaluation of skin wrinkles In the present embodiments 1 and 2, the wrinkle index value of a subject's skin can be estimated based on four values: the subject's age, the measurement value of the skin's brightness, the measurement value of the skin's redness, and the measurement value of the skin's sebum amount (see, for example, FIG. 1).

[0082] In step 101, four values ​​are transmitted to the control unit: the subject's age, the measured value of skin brightness, the measured value of skin redness, and the measured value of the amount of sebum on the skin. In step 102, the control unit estimates a wrinkle index value of the subject's skin based on the four values: the subject's age, the measured skin brightness, the measured skin redness, and the measured skin sebum amount. The control unit outputs the wrinkle index value of the subject.

[0083] In this embodiment 1a, the wrinkle index value of a subject's skin can be estimated based on four values, namely, the subject's age, the measured value of skin brightness, the measured value of skin redness, and the measured value of skin sebum amount, and a wrinkle prediction model (Wrinkle Prediction Formula 1 below) (see, for example, FIG. 2). In addition, in the present embodiment 2a, the wrinkle index value of the subject's skin can be estimated in the same manner as in the present embodiment 1a, except that Wrinkle Prediction Formula 1 is replaced with Wrinkle Prediction Formula 2 (see, for example, FIG. 2).

[0084] The wrinkle prediction formula 1 shown below is composed of five wrinkle prediction factors: "age," "skin brightness," "skin redness," "skin sebum amount," and "interaction term between sebum amount and skin redness." In step 101a, the control unit can estimate a wrinkle index value (wrinkle grade) by substituting the four values ​​of the subject's "age value," "measurement value of skin brightness," "measurement value of skin redness," and "measurement value of skin sebum amount" into a wrinkle prediction model (wrinkle prediction formula 1 below) (see, for example, FIG. 2). In step 102a, a wrinkle reference value can also be obtained based on preset values ​​for predicting the subject's future wrinkle state and wrinkle prediction formula 1 (see, for example, FIG. 2). The preset values ​​are one, two, or more values ​​selected from the group consisting of age values, skin brightness values, skin redness values, and skin sebum amount values, and the control unit can obtain the wrinkle reference value by substituting the selected values ​​into wrinkle prediction formula 1. The values ​​for predicting the subject's future wrinkle state may be appropriately substituted by the operator. In step 103a, the wrinkle index value is compared with the wrinkle reference value, whereby skin care for the subject can be suggested. Specifically, when the wrinkle index value is less than the wrinkle standard value, the time when the wrinkle standard value is reached is output to the subject as the time to start using the wrinkle improving composition, and when the wrinkle index value is equal to or greater than the wrinkle standard value, an output is output to the subject indicating that use of the wrinkle improving composition should be started. The operator can also suggest skin care based on the wrinkle index value and wrinkle reference value output from the control unit as described above.

[0085] <Wrinkle prediction formula 1 (Formula 1)>

[0086] Wrinkle grade i =0.1469×Age + 0.7540×Ln(sebum) + 0.3270×Skin color a* + 0.1654×Mean[Skin color L*] - 0.1044×[Ln(sebum)×Skin color a*] - 15.90 + b 0,i (Formula 1) b 0,i ~N(0, 0.4847) Final equation for prediction of wrinkle grade in Japanese women aged 22-60 years

[0087] <Wrinkle prediction formula 2 (Formula 2)> The wrinkle prediction formula 2 shown below is composed of five wrinkle prediction factors, namely, "age," "skin brightness," "skin redness," "skin sebum amount," and "interaction term between sebum amount and skin redness." Note that parts that overlap with what has already been described in the above embodiments 1 and 1a will be omitted as appropriate. By substituting the four values ​​of the subject's "age," "skin brightness," "skin redness," and "skin sebum amount" into the wrinkle prediction model (wrinkle prediction formula 2), the wrinkle index value (wrinkle grade) can be estimated (see, for example, Figure 2). In addition, by substituting four preset values ​​("age value," "skin brightness value," "skin redness value," and "skin sebum amount value") into the wrinkle prediction formula 2, the wrinkle standard value can also be obtained (see, for example, Figure 2). In the present embodiment 2a, similarly to the present embodiment 1a in which the above-mentioned wrinkle prediction formula 1 is adopted, it is possible to predict the future wrinkle state of the subject, and also possible to suggest skin care for the subject.

[0088] Wrinkle grade i= 0.1200~0.2053×Age + 0.2200~1.280×Ln(sebum) + 0.050~0.5710×Skin color a* + 0.050~0.4000×Mean[Skin color L*] - 0.030~0.1800×[Ln(sebum)×Skin color a*] - 25.00~7.600 (Formula 2)

[0089] 2-2-2.Evaluation of Skin Wrinkles in the Present Invention: Embodiment 3 In the third embodiment, the wrinkle index value of the subject's skin can be estimated based on at least two of the subject's age and the measured value of the skin brightness (see, for example, FIG. 1). Note that although a diagram showing the flow of steps in this embodiment itself is omitted, this flow can be understood by referring to FIG. 1 and FIG. 2.

[0090] In step 301, at least two values ​​are transmitted to the control unit: a value for the subject's age and a measurement of the subject's skin lightness. In step 302, the control unit estimates a wrinkle index value of the subject's skin based on both the value of the subject's age and the measured value of the skin brightness. The control unit outputs the wrinkle index value of the subject.

[0091] In this embodiment 3a, the wrinkle index value of the subject's skin can be estimated based on the subject's age and the measured skin brightness value and a wrinkle prediction model (Wrinkle Prediction Equation 3 below) (see, for example, FIG. 2). The wrinkle prediction formula 3 shown below is a wrinkle prediction formula consisting of two wrinkle prediction factors, namely, "age" and "skin brightness". Note that the parts that overlap with those already described in the above-mentioned embodiments 1 and 2 will be omitted as appropriate. In step 301a, the control unit can estimate a wrinkle index value (wrinkle grade) by substituting two values, the subject's "age value" and "skin brightness measurement value," into a wrinkle prediction model (wrinkle prediction formula 3 below) (see, for example, FIG. 2). Also, by substituting two preset values ​​("age value" and "skin brightness value") into the wrinkle prediction formula 3, a wrinkle standard value can be obtained (see, for example, FIG. 2). As in the above-mentioned embodiments 1 and 2, it is possible to predict the future state of wrinkles of the subject, and also possible to suggest skin care for the subject.

[0092] <Wrinkle prediction formula 3 (Formula 3)>

[0093] Wrinkle grade i = 0.1484×Age + 0.1844×Mean[Skin color L*] - 14.80 (Formula 3)

[0094] 2-2-3.Evaluation of Skin Wrinkles in the Present Invention: Embodiment 4 In the fourth embodiment, the wrinkle index value of the subject's skin can be estimated based on three values: the subject's age, the measured value of the skin's brightness, and the measured value of the skin's sebum amount (see, for example, FIG. 1). Note that although a diagram showing the flow of steps in this embodiment itself is omitted, this flow can be understood by referring to FIG. 1 and FIG. 2.

[0095] In step 401, at least three values ​​are transmitted to the control unit: the subject's age, a measurement value of skin brightness, and a measurement value of the amount of sebum on the skin. In step 402, the control unit estimates a wrinkle index value of the subject's skin based on three values: the subject's age, the measured value of the skin brightness, and the measured value of the skin sebum amount. The control unit outputs the wrinkle index value of the subject.

[0096] In this embodiment 4a, the wrinkle index value of the subject's skin can be estimated based on the subject's age, the measured value of the skin brightness, the measured value of the skin's sebum amount, and a wrinkle prediction model (Wrinkle Prediction Formula 4 below) (see, for example, FIG. 2). The wrinkle prediction formula 4 shown below is composed of three wrinkle prediction factors, namely, "age," "skin brightness," and "amount of sebum in the skin." Note that the parts that overlap with those already described in the above embodiments 1 to 3 will be omitted as appropriate. In step 401a, the control unit can estimate a wrinkle index value (wrinkle grade) by substituting three values ​​of the subject's "age value," "skin brightness value," and "skin sebum amount value" into the wrinkle prediction model (wrinkle prediction formula 3 below). Also, by substituting three preset values ​​("age value," "skin brightness value," and "skin sebum amount value") into the wrinkle prediction formula 4, a wrinkle standard value can be obtained (see, for example, FIG. 2). As in the above-described first to third embodiments, it is possible to predict the future state of wrinkles of the subject, and also to suggest skin care for the subject.

[0097] <Wrinkle prediction formula 4 (Formula 4)>

[0098] Wrinkle grade i = 0.1504×Age + 0.1880×Mean[Skin color L*] +0.044×Ln(sebum) - 15.28 (Formula 4)

[0099] 2-2-4. Fifth embodiment of the present invention relating to evaluation of skin wrinkles In the fifth embodiment, the wrinkle index value of the subject's skin can be estimated based on the subject's age, the measured value of the skin's brightness, the measured value of the skin's sebum amount, and the measured value of the skin's redness (see, for example, FIG. 1). Note that although a diagram showing the flow of steps in this embodiment itself is omitted, this flow can be understood by referring to FIG. 1 and FIG. 2.

[0100] In step 501, four values ​​are transmitted to the control unit: the subject's age, the measured value of skin brightness, the measured value of the amount of sebum on the skin, and the measured value of redness on the skin. In step 502, the control unit estimates a wrinkle index value of the subject's skin based on the four values: the subject's age, the measured value of the skin brightness, the measured value of the skin sebum amount, and the measured value of the skin redness. The control unit outputs the wrinkle index value of the subject.

[0101] In this embodiment 5a, the wrinkle index value of the subject's skin can be estimated based on the subject's age, the measurement value of the skin brightness, the measurement value of the skin's sebum amount, and the measurement value of the skin's redness, as well as a wrinkle prediction model (Wrinkle Prediction Formula 5 below) (see, for example, FIG. 2). The wrinkle prediction formula 5 shown below is composed of four wrinkle prediction factors, namely, "age," "amount of sebum in the skin," "redness in the skin," and "brightness of the skin." Note that the parts that overlap with those already described in the above-mentioned embodiments 1 to 4 will be omitted as appropriate. In step 501a, the control unit can estimate a wrinkle index value (wrinkle grade) by substituting the four values ​​of the subject's "age value," "measurement value of skin sebum amount," "measurement value of skin redness," and "measurement value of skin brightness" into a wrinkle prediction model (wrinkle prediction formula 5 below) (see, for example, FIG. 2). In addition, by substituting four preset values ​​("age value," "skin sebum value," "skin redness value," and "skin brightness value") into the wrinkle prediction formula 5, a wrinkle standard value can be obtained (see, for example, FIG. 2). As in the above-mentioned first to fourth embodiments, it is possible to predict the future state of wrinkles of the subject, and also possible to suggest skin care for the subject.

[0102] <Wrinkle Prediction Formula 5 (Formula 5)>

[0103] Wrinkle grade i = 0.1460×Age + 0.035×Ln(sebum) + 0.013×Skin color a* + 0.1812×Mean[Skin color L*] (Formula 5)

[0104] 2-2-5. Embodiment 6 of the present invention relating to evaluation of skin wrinkles In the sixth embodiment, the wrinkle index value of the subject's skin can be estimated based on the four values ​​of the subject's age, the measured value of the skin brightness, the measured value of the amount of sebum on the skin, and the measured value of redness on the skin (see, for example, Figs. 1 to 3). By using two values, the subject's age and the measured value of the skin brightness, in the wrinkle prediction model of the sixth embodiment, the wrinkle index value of the subject's skin can be estimated. More specifically, in the sixth embodiment, based on the measured value of the skin brightness of the subject, it is determined whether the skin is light or dark, and cases are classified according to the state of the skin brightness of the subject (light and dark), and the evaluation of the skin wrinkles is determined for each case, so that skin care suitable for the subject can be proposed with higher accuracy. Note that, although the points that overlap with those already described in the above-mentioned first to fifth embodiments will be omitted as appropriate, the configurations of the above-mentioned first to fifth embodiments can be applied as appropriate.

[0105] <Distinguishing between light and dark skin> In step 601, the control unit determines whether the subject's skin is light or dark based on the measured value of skin brightness. Specifically, the control unit compares the measured value of the subject's skin brightness with a reference value of skin brightness. The reference value of skin brightness can be set appropriately, and may be, for example, the average value of skin brightness of general humans (preferably women, particularly yellow race (Mongoloid race)). If the brightness of the subject's skin is equal to or greater than the standard value for skin brightness (Yes), the subject's skin is determined to be light; otherwise (i.e., if it is less than the specified value) (No), the subject's skin is determined to be dark (see, for example, Figure 3).

[0106] <For light skin (S602~S607)> In step 602, if the control unit determines that the subject has light skin (Yes), then wrinkle prediction formula 6 is selected. If the subject has light skin, the control unit can estimate the wrinkle index value (wrinkle grade) by substituting the subject's "age value," "measurement value of skin redness," and "measurement value of skin sebum amount" into wrinkle prediction formula 6.

[0107] In step 603, the control unit can obtain a wrinkle reference value for lighter skin, separately from step 602, based on the value for predicting the future wrinkle state and wrinkle prediction formula 6. Specifically, the control unit can select a value of each skin state for predicting the future wrinkle state of the subject, and substitute the selected value into wrinkle prediction formula 6. Each value may be input by the operator.

[0108] In step 604, the control unit can obtain a wrinkle reference value of standard skin based on a value for predicting a future wrinkle state and wrinkle prediction formula 1 or wrinkle prediction formula 2, separately from step 603. Specifically, using the wrinkle prediction formula 1 representing a standard human, a wrinkle reference value of standard skin can also be obtained based on a value for predicting a future wrinkle state and wrinkle prediction formula 1 or 2, in the same manner as in the above-mentioned embodiments 1 and 2. Each value may be input by an operator.

[0109] If step 604 is included, step 603 may be skipped, in which case the control unit compares the wrinkle index value with the wrinkle reference value of standard skin. Also, if step 603 is included, step 604 may be skipped, in which case the control unit compares the wrinkle index value with the wrinkle reference value of light skin.

[0110] In step 605, the control unit compares the wrinkle index value with the light wrinkle reference value and / or the standard wrinkle reference value, thereby making it possible to suggest skin care for the subject with light skin. Specifically, in step 606, if the wrinkle index value is less than the wrinkle standard value, the time when the wrinkle standard value is reached is output to the subject as the time to start using the wrinkle-improving composition. In step 607, if the wrinkle index value is equal to or greater than the wrinkle standard value, an output is given to the subject instructing him / her to start using the wrinkle-improving composition.

[0111] Prediction formulas 6 and 7 show that lighter skin is more prone to wrinkles. Therefore, by adopting a lighter wrinkle standard value, it is easier to prevent or improve wrinkles in subjects with lighter skin. The operator can also suggest skin care based on the wrinkle index value and wrinkle reference value output from the control unit as described above.

[0112] <For darker skin (S608~S613)> In step 608, if the control unit determines that the subject does not have light skin (No) (ie, the subject has dark skin), wrinkle prediction formula 7 is selected. If the subject has dark skin, the control unit can estimate the wrinkle index value (wrinkle grade) by substituting the subject's "age value," "measurement value of skin redness," and "measurement value of skin sebum amount" into wrinkle prediction formula 7.

[0113] In step 609, the control unit can obtain a wrinkle reference value for darker skin based on the value for predicting the subject's future wrinkle state and Wrinkle Prediction Equation 7, separately from step 608. Specifically, the control unit can select a value for each skin state for predicting the subject's future wrinkle state, and substitute the selected value into Wrinkle Prediction Equation 7. Each value may be input by the operator.

[0114] In step 610, the control unit can perform the same operation as in step 603 described above, separately from step 609, to obtain a standard skin wrinkle reference value.

[0115] If step 609 is included, step 610 may be skipped, in which case the control unit compares the wrinkle index value with the wrinkle reference value of standard skin. If step 610 is included, step 609 may be skipped, in which case the control unit compares the wrinkle index value with the wrinkle reference value of light skin.

[0116] In step 611, the control unit compares the wrinkle index value with the darker wrinkle reference value and / or the standard wrinkle reference value, thereby making it possible to provide skin care suggestions for the subject with darker skin. Specifically, in step 612, if the wrinkle index value is less than the wrinkle standard value, the time when the wrinkle standard value is reached is output to the subject as the time to start using the wrinkle-improving composition. In step 613, if the wrinkle index value is equal to or greater than the wrinkle standard value, an output is given to the subject instructing him / her to start using the wrinkle-improving composition.

[0117] Prediction formulas 6 and 7 show that lighter skin is more prone to wrinkles. Therefore, by adopting a standard wrinkle reference value, it is easier to prevent or improve wrinkles in subjects with darker skin. The operator can also suggest skin care based on the wrinkle index value and wrinkle reference value output from the control unit as described above.

[0118] Wrinkle prediction formula 6, which can be applied when the subject has light skin, is preferably composed of four wrinkle predictors: "age," "skin redness," "amount of sebum on the skin," and "interaction term between amount of sebum and redness on the skin." On the other hand, when the subject has dark skin, wrinkle prediction formula 7, which is composed of three wrinkle predictors: "age," "skin redness," and "amount of sebum on the skin," is preferably used. When using these wrinkle prediction formulas, the subject preferably has a value for "age," and measured values ​​of "lightness of the skin," "redness of the skin," and "amount of sebum on the skin" at that age. Each wrinkle prediction formula can be obtained in <1-4-2. Method for creating a wrinkle prediction model>, and can be obtained using the data obtained in Test Example 1 in the Examples section described below.

[0119] 3. Method for evaluating or searching for a wrinkle-improving composition according to the present invention Hereinafter, an embodiment of the method for evaluating or searching for a wrinkle-improving composition of the present invention will be described. In the description of this embodiment, the description of each configuration and evaluation method that overlaps with the above-mentioned "1." and "2." will be omitted as appropriate, but the description of "1." and "2." also applies to this embodiment and can be adopted as appropriate. In this embodiment, the above-mentioned skin wrinkle evaluation and wrinkle prediction models (e.g., wrinkle prediction formulas 1 to 7, etc.) can be adopted as appropriate.

[0120] The present invention includes a step of estimating a wrinkle index value of the skin of a subject administered a test substance using the wrinkle evaluation method described in "1." and "2." above; A method for evaluating or searching for a composition for improving wrinkles can be provided, which includes a step of identifying the test substance as being for improving wrinkles if the estimated wrinkle index value of the subject's skin is lower than the wrinkle index value of the subject's skin before administration. This allows the wrinkle index value of the subject to be estimated simply and accurately, and therefore allows a wrinkle-improving composition suitable for each subject to be evaluated or searched for more simply and accurately. In the method for evaluating or searching for a wrinkle-improving composition of the present invention, it is preferable to use the mobile terminal with a camera of the present invention, since it allows continuous and detailed recording and is convenient.

[0121] The test substance is not particularly limited, and may be a commercially available product that is commercially available as a composition for preventing, improving, or treating wrinkles. Even if it is a commercially available product, the degree of efficacy varies between individuals, so that the present invention allows the selection of a commercially available product suitable for an individual. In addition, the test substance may be a new or known substance that is expected to prevent, improve, or treat wrinkles, and thus, a more suitable substance for preventing, improving, or treating wrinkles can be searched for and selected. The administration may be either oral administration or parenteral administration (eg, injection, application, etc.), with application being preferred. The administration time can be appropriately selected, and the compound may be administered once a day or in divided doses multiple times a day, or may be administered once every few days or weeks.

[0122] The present invention also provides a method for evaluating wrinkles, comprising: estimating a wrinkle index value of a subject's skin using the wrinkle evaluation method described in "1." and "2." above; and A method for providing a wrinkle-improving composition can be provided, the method including a step of identifying one or more wrinkle-improving compositions based on the estimated wrinkle index value of the subject's skin. This makes it possible to identify a wrinkle-improving composition corresponding to the wrinkle index value, and to propose or provide a wrinkle-improving composition suitable for the subject. Furthermore, it is preferable that the method further includes a step of outputting the identified wrinkle-improving composition by an output unit. Note that the output wrinkle-improving composition may be proposed or provided to the subject by an operator or a control unit.

[0123] The wrinkle-improving composition may be a composition for preventing or treating wrinkles, and is not particularly limited, and may be a commercial product. The data of each wrinkle-improving composition may be linked or attached to specific data on the wrinkle index value of the skin that can be handled by each wrinkle-improving composition. The corresponding wrinkle index value of the skin can be obtained based on the known efficacy of the wrinkle-improving composition, or based on the results of the above-mentioned method for evaluating or searching for the wrinkle-improving composition of the present invention. By linking or attaching the data of the wrinkle index value of the skin that can be handled to the data of the wrinkle-improving composition, it is possible to more easily and accurately search for a wrinkle-improving composition that corresponds to the wrinkle condition of the subject's skin (e.g., wrinkle index value, wrinkle grade, etc.), and to more easily and accurately provide information on the searched wrinkle-improving composition to the subject. This makes it possible to propose or provide information on a wrinkle-improving composition that is more suitable for the wrinkle condition of the subject's skin.

[0124] The data of each wrinkle improving composition may be grouped into a predetermined range based on the wrinkle index value data of the skin that can be handled by each wrinkle improving composition. The control unit may group the data of each wrinkle improving composition based on the data of the wrinkle index value that can be handled attached to the data of each wrinkle improving composition. The grouping into a predetermined range may be performed according to the classification of the standard table of wrinkle grades, for example, wrinkle grade 3-4: wrinkle improving compositions A, B, C, etc., wrinkle grade 4-5: wrinkle compositions D, F, etc., wrinkle grade 5-6: wrinkle improving compositions G, H, i, J, etc., wrinkle grade 6-7: wrinkle improving compositions O, P, etc., and the data of each composition may be assigned the data of the wrinkle index value that can be handled (for example, 4.5 or 6.7, etc.). The interval for each predetermined range is not particularly limited, and may be an interval of 1 or 0.5, and may be, for example, 8 stages of 1 increments of 0, 1, 2, 3, 4, 5, 6, 7. By grouping, information on one or more groups containing a wrinkle-improving composition corresponding to the wrinkle condition of the subject's skin can be more simply and accurately proposed or provided to the operator or the subject. Various data relating to the wrinkle-improving composition, such as data on the wrinkle-improving composition, corresponding wrinkle index value data, and group data, may be stored in a storage unit.

[0125] Furthermore, the wrinkle-improving composition proposed or provided to the operator or subject may be a wrinkle-improving composition corresponding to the subject's current or future wrinkle grade. For example, the control unit can determine, based on the wrinkle index value of the subject's skin, one or more wrinkle-improving compositions or groups that are equivalent to or higher than the wrinkle index value (more preferably equivalent to or one level higher than the wrinkle index value), and output, propose, or provide information on the determined wrinkle-improving composition or group to the operator or subject. The control unit can propose or provide information on the determined wrinkle-improving composition or group as the subject's "currently recommended item."

[0126] The control unit can also obtain the subject's future skin wrinkle index value based on the subject's skin wrinkle index value and the wrinkle prediction model, and output, propose, or provide information on a wrinkle-improving composition or group that is equal to or higher than the future wrinkle index value (more preferably equal to or one level higher) based on the subject's future skin wrinkle index value as a future wrinkle-improving composition, as described above. The control unit can set the determined wrinkle-improving composition or group as a "future recommended item" such as "a switching item from . . . years of age" for the subject. The control unit can also widen the range of the stage for "equal to or higher than the subject's skin wrinkle index value (more preferably equal to or one level higher)" from one stage higher to one stage lower, thereby widening the range of information on the wrinkle-improving composition proposed or provided and increasing the number of products, and the information with such a wide range can be proposed or provided to the operator or subject as a "widened recommended item."

[0127] A method for providing a composition for preventing, improving or treating wrinkles using the wrinkle prediction model of the present invention is shown below as Example 1 and Example 2. The wrinkle prediction model can appropriately use the wrinkle prediction models or wrinkle prediction formulas described in "1." and "2." above.

[0128] <Example 1> In step 701, the control unit inputs four values, namely, the brightness measurement value, the redness measurement value, and the sebum amount measurement value, of the subject's skin to the wrinkle prediction model. This makes it possible to set the wrinkle prediction formula a for each individual subject. In step 702, the control unit inputs the value of the subject's age into the wrinkle prediction formula a, and outputs an index value of the subject's current wrinkles. This allows the operator or the subject to understand the subject's current wrinkle risk (wrinkle grade). In step 703, the control unit can output the wrinkle standard value and the age at that time by inputting wrinkle grades 3 to 5 as the best wrinkle risk value into the wrinkle prediction formula a. Note that the lower the wrinkle grade setting, the better the wrinkle risk. The output is not particularly limited to a screen display, a voice display, etc. The operator of the wrinkle prediction model is not particularly limited to a product salesperson, a counselor, an operator, a subject, etc.

[0129] In addition, when the input screen has a numerical input field, the data of the measurement value of each skin condition of the subject (measurement value of brightness, measurement value of redness, measurement value of sebum amount) may be obtained by the operator inputting the measurement value into the numerical input field. In addition, when the input screen has an input field for selecting an image or level of a color panel, the operator or the subject may select a color panel or level that is the same as or similar to the skin condition of the subject from a plurality of color panel images or levels, and each measurement value data linked or attached to each of these data may be selected by the control unit, thereby obtaining the measurement value data. When selecting a color panel, the operator may select a color panel that is the same as or similar to the skin condition of the subject by visually inspecting the skin condition or by comparing with the captured image data, or the control unit may select a color panel that is the same as or most similar to the color tone of the image data of the captured skin of the subject.

[0130] In step 704, if the control unit determines that the subject's current wrinkle index value is equal to or greater than the wrinkle standard value (Yes), it compares the efficacy of the wrinkle improvement composition currently being used by the subject, and outputs one or more recommended wrinkle improvement compositions that have stronger efficacy. In step 705, if the subject's current wrinkle index value is not equal to or greater than the wrinkle standard value (No) (i.e., if it is less than the wrinkle standard value), the control unit outputs the predicted age at which the subject will reach the wrinkle grade (3 to 5) set as the best wrinkle risk value based on the wrinkle prediction model a. One or more types of wrinkle improving compositions recommended for use after this predicted age are output.

[0131] <Example 2> In step 801, the control unit inputs three values, namely, the measured value of the brightness of the subject's skin, the measured value of the redness of the skin, and the measured value of the amount of sebum on the skin, to the wrinkle prediction model. This makes it possible to set the wrinkle prediction formula b for each individual subject. In step 802, the control unit outputs the current wrinkle index value and also outputs one or more types of wrinkle improving compositions that are compatible with the current wrinkle grade, in addition to the wrinkle improving agent currently being used.

[0132] <Example 3> The operator selects a color panel or level that is the same as or similar to that of the subject from an image (image, video, etc.) of the subject's skin condition (brightness measurement value, redness measurement value, sebum amount measurement value) on the input screen (see FIG. 6). The control unit may also obtain measurement value data of each skin condition of the subject based on personal data such as image data of the subject. The subject's age value may be directly input by the operator or may be read by the control unit from the personal data. The control unit can obtain the data of each measurement value corresponding to the selected color panel or level (e.g., measurement value data linked to the color panel data, etc.).

[0133] In step 901, the control unit can input four values, namely, the brightness measurement value, the redness measurement value, and the sebum amount measurement value, of the subject's skin to the wrinkle prediction model. This makes it possible to set the wrinkle prediction formula a for each individual subject.

[0134] In step 902, the control unit inputs the subject's age value into the wrinkle prediction formula A, thereby outputting the subject's current wrinkle index value. This allows the control unit to output or provide the subject's current wrinkle risk (wrinkle grade) to the operator or the subject.

[0135] In step 903, the control unit can output the wrinkle reference value and the age at that time, in the same manner as in step 703 in Example 1 above. Furthermore, as shown in Fig. 6, the wrinkle risk of the subject can be output as the wrinkle evaluation data of the subject. For example, the current wrinkle risk and the best wrinkle risk pattern of the subject can be output, and further, the present and future facial images of the subject showing the degree of risk reduction that the subject aims to achieve can be output.

[0136] In step 904, the control unit, based on the subject's current wrinkle index value, identifies one or more wrinkle-improving compositions to which a wrinkle index value equal to or greater than this index value is linked or associated, and can output the identified wrinkle-improving composition or group to the output unit as a recommended item to the operator or subject, thereby proposing or providing it to the operator or subject. The control unit can have the operator or subject select one or more wrinkle-improving compositions from the recommended items output to the input unit, and the control unit can provide the selected wrinkle-improving composition to the subject as a product by selling, shipping, or the like.

[0137] Example 3 of the present invention can also provide the following configuration. The present invention relates to a method for determining a wrinkle index value of a subject's skin, the method comprising: estimating a wrinkle index value of the subject's skin based on a value of the subject's age, a measurement value of the skin brightness, a measurement value of the skin redness, and a measurement value of the amount of sebum; It is possible to provide a method for providing information on a wrinkle-improving composition suitable for a subject, the method including a step of identifying a wrinkle-improving composition suitable for the subject based on the estimated wrinkle index value of the subject's skin.

[0138] It is preferable that the data on the wrinkle-improving composition is linked to or attached to data on the wrinkle index value of a corresponding skin, and by selecting the data on the wrinkle index value of the corresponding skin, the control unit can determine the wrinkle-improving composition or group suitable for the subject. Furthermore, it is preferable that the method further includes outputting, proposing or providing information on the identified wrinkle-improving composition or compositions or the group thereof by an output unit.

[0139] It is more preferable that the method includes, prior to the estimation step, selecting a color panel that is the same as or similar to the subject's skin brightness, thereby selecting measurement data of skin brightness linked to the data of the color panel, and setting the selected measurement data as the measurement value of the skin brightness, and / or selecting a color panel that is the same as or similar to the subject's skin redness, thereby selecting measurement data of skin redness linked to the data of the color panel, and setting the selected measurement data as the measurement value of the skin redness.

[0140] 4. Evaluation system for wrinkle prediction An embodiment of an evaluation system for wrinkle prediction according to the present invention will be described below. In the description of this embodiment, the description of each configuration and evaluation method that overlaps with the above-mentioned "1." to "3." will be omitted as appropriate, but the description of "1." to "3." also applies to this embodiment and can be adopted as appropriate.

[0141] In the skin wrinkle evaluation system of the present invention, a wrinkle prediction model for a subject can be derived by applying the measured values ​​of the subject's age and skin condition to the wrinkle prediction model. Furthermore, the control unit can estimate the wrinkle index value of the subject's skin based on the subject's actual age. On the other hand, the control unit estimates the future wrinkle index value by setting the future age of the subject. The future age may be an age desired by the subject, or may be a future age preset in a storage unit, such as the subject's actual age +α years. This makes it possible to predict the subject's future wrinkle condition.

[0142] Furthermore, the control unit can determine the timing to start using the wrinkle-improving composition by comparing the wrinkle index value with a set wrinkle reference value in the same wrinkle prediction model.

[0143] Furthermore, it is preferable that the control unit compares the wrinkle index value with the wrinkle grade "3 to 5" of the set wrinkle standard value, thereby enabling the control unit to determine the time to start using the wrinkle-improving composition.

[0144] The wrinkle reference value may be stored and set in advance in a storage unit or the like. The control unit can estimate the wrinkle index value from the actual age of the subject using the wrinkle prediction model. On the other hand, the control unit can estimate the age of the subject when the wrinkles reach a set standard value, for example, "3 to 5," using the same wrinkle prediction model, and determines the age estimated from this standard value as the start time for using the wrinkle-improving composition.

[0145] Furthermore, when the wrinkle index value estimated by the wrinkle prediction model reaches a preset wrinkle standard value, the control unit can determine the age at which this value is reached as the time to start using the wrinkle-improving composition.

[0146] The measured value is preferably a value measured by a skin condition measuring device such as a measuring instrument or an imaging device (e.g., a digital camera, a video camera, a video image, a still image), etc. This makes it possible to reduce the variation in the measured value caused by the person who measures.

[0147] The wrinkle evaluation system of the present invention comprises: determining that the wrinkle index value estimated by the prediction model has reached a preset wrinkle reference value; It is preferable that the method includes determining the age at which the wrinkle-improving composition is to be used as the time to start using the wrinkle-improving composition. More preferably, the preset wrinkle reference value is a standard wrinkle reference value for a subject of the same age plus 5 years.

[0148] 5. Evaluation program for wrinkle prediction An embodiment of an evaluation system for wrinkle prediction according to the present invention will be described below. In the description of this embodiment, the description of each configuration and evaluation method that overlaps with the above-mentioned "1." to "4." will be omitted as appropriate, but the description of "1." to "4." also applies to this embodiment and can be adopted as appropriate. A function for inputting the subject's age and skin condition measurements; and a function of estimating a wrinkle index value of the subject's skin by using the age value and the skin condition measurement value in a wrinkle prediction model.

[0149] A function for inputting the subject's age and skin condition measurements; using the age value and the skin condition measurements in a wrinkle prediction model to estimate a wrinkle index value for the subject's skin; The estimated wrinkle index value is compared with a preset wrinkle reference value, a function of determining, when the estimated wrinkle evaluation value reaches a preset wrinkle standard value, the age at which the estimated wrinkle evaluation value reaches the preset wrinkle standard value as the time to start using a wrinkle-improving composition; A skin wrinkle evaluation program that realizes this on a computer.

[0150] 6. Trained Model Related to the Invention An embodiment of the trained model according to the present invention will be described below. In the description of this embodiment, the description of each configuration, evaluation method, etc. that overlaps with the above-mentioned "1." to "5." will be omitted as appropriate, but the description of "1." to "5." also applies to this embodiment and can be adopted as appropriate. In addition, in this embodiment, the above-mentioned skin wrinkle evaluation and wrinkle prediction model (e.g., wrinkle prediction formulas 1 to 7, etc.) can be adopted as appropriate. The wrinkle prediction model used in the present invention may be a wrinkle prediction model generated by a method for generating a trained model, and it is preferable to adopt the explanation of "1-4-2. Method for generating a wrinkle prediction model" above.

[0151] A simplified example of the processing procedure of the specialized AI used as the trained model in the present invention is as follows: (1) Training data → (2) Algorithm → (3) Training The process can be, but is not limited to, (4) input data → (3) trained model → (5) result (see Figure 7 for an example). In general, specialized AI is a mechanism in which a result can be obtained by applying any input data to a trained model that is constructed by incorporating training data (teacher data) into an algorithm that functions as a learning program.

[0152] In the present invention, subjects in the learning data (teacher data) can include participants in the above-mentioned "1-4-2. Method for creating a wrinkle prediction model." The control unit acquires at least two values, the age value and the skin brightness measurement value of the subject, for multiple or more people as learning data (teaching data). It is preferable to make at least two values, the age value and the skin brightness measurement value of the same subject, into one data set. For example, the above-mentioned "1-4-1. Prediction factor of wrinkle prediction model" can be adopted as the teaching data, and two or more types selected from age, skin brightness, skin redness, skin sebum amount, and interaction term of sebum amount and skin redness are preferable. More preferably, the control unit further acquires the two values ​​and one or two values ​​of the measurement value of the redness of the skin and / or the measurement value of the amount of sebum of the skin as data. The control unit can read out teacher data selected from two or more of these from the storage unit. The storage unit stores the age values ​​and measurement values ​​acquired from a plurality of subjects as data in advance.

[0153] Next, the control unit can build a wrinkle prediction model (trained model) by incorporating the learning data read from the storage unit into a preset algorithm. This allows the control unit to have a wrinkle prediction model. As described in "1-4. Wrinkle Prediction Model", the trained model (wrinkle prediction model) can be obtained using "statistical analysis".

[0154] The above-mentioned algorithm can function as, for example, a machine learning algorithm. The type of the machine learning algorithm is not particularly limited, and may be, for example, an algorithm using a neural network such as an RNN (Recurrent Neural Network), a CNN (Convolutional Neural Network), or an MLP (Multilayer Perceptron), or may be any algorithm.

[0155] Next, the control unit can input the input data from the operator ((4) input data (input layer)) into the constructed wrinkle prediction model (trained model) to generate data regarding wrinkle evaluation to be output from the display ((5) result (output layer)). The trained model may be a trained model generated by, for example, deep learning. For example, the trained model may be a multi-layer neural network, for example, a deep neural network (DNN), and more specifically, a convolutional neural network (CNN). A multi-layer neural network may be used as the trained model, and the multi-layer neural network may have an input layer to which a subject inputs age values ​​and measurement values, an output layer to which a wrinkle evaluation result of the subject is output, and at least one intermediate layer provided between the input layer and the output layer.

[0156] The control unit can realize a method for generating a trained model, a method for evaluating skin wrinkles of a subject using the trained model, or a method for providing an evaluation of skin wrinkles, as described below. A trained model generating method comprising: (a) acquiring a plurality of training data including at least two values, namely, a subject's age and a measured value of skin brightness, as data; (b) using the training data, inputting at least two values, namely, the age and the measured value of skin brightness, of each subject; and (c) generating a trained model from the input data, which outputs a wrinkle prediction model for estimating an index value of wrinkles on the subject's skin.

[0157] (d) acquiring at least two values, namely, the subject's age and the measured value of skin brightness, as data; (e) applying at least these two values, namely, the subject's age and the measured value of skin brightness, to a trained model generated by the trained model generation method using the at least these two values, namely, the subject's age and the measured value of skin brightness, thereby generating an index value for estimated skin wrinkles of the subject; and (f) using the generated index value as an evaluation of skin wrinkles or providing it as an evaluation of skin wrinkles. A program for causing a computer to execute the method for evaluating skin wrinkles or the method for providing the method as an evaluation of skin wrinkles, or a recording medium for storing the program. A skin wrinkle evaluation device or a skin wrinkle evaluation system including the program or the recording medium.

[0158] The present technology can also employ the following configuration. (1) A method for assessing skin wrinkles, or a method for providing an assessment of skin wrinkles, comprising estimating an index value of a subject's skin wrinkles based on at least two values: the subject's age and a measurement of the subject's skin brightness. The method described in [1] above is preferably used by one or more selected from an operator, a provider of evaluation results to a third party, a subject, an end user, a product purchaser, a professional (counselor, operator, product salesperson, etc.), etc. The method described in [1] above may be a method for assisting in the evaluation of skin wrinkles, including presenting, displaying, or providing an estimated result of the wrinkle index value. The method described in [1] above may be a method executed by a computer.

[0159] [2] The evaluation method or method for providing an evaluation described in [1], which estimates an index value for wrinkles on the subject's skin based on the two values ​​and one or two values ​​of a measurement value of skin redness and / or a measurement value of the amount of sebum on the skin. [3] The evaluation method or method for providing an evaluation according to [1] above, wherein an index value for wrinkles in the subject's skin is estimated by using two values, the subject's age and a measurement value of skin brightness, in a wrinkle prediction model. [4] The evaluation method or method for providing an evaluation according to [2] above, wherein an index value of wrinkles on the subject's skin is estimated by using two values ​​of measurements of the subject's age and skin brightness, and one or two values ​​of measurements of skin redness and / or measurements of the amount of sebum on the skin, in a wrinkle prediction model. [5] The method for evaluating or the method for providing an evaluation according to [3] or [4] above, wherein the wrinkle prediction model is a model obtained by deriving the model using a linear mixed effects model including, as explanatory variables, at least the measured values ​​of an individual's age and skin brightness, with the individual's wrinkle index value as a dependent variable. [6] The evaluation method or method for providing an evaluation described in [5], wherein the parameters of the linear mixed effects model are obtained using a maximum likelihood method or a restricted maximum likelihood method. [7] A step of estimating a wrinkle index value of the skin of a subject administered with a test substance by using the wrinkle evaluation method according to any one of [1] to [6] above; and A method for evaluating or searching for a composition for improving wrinkles, or a method for providing evaluation or searching results, comprising a step of identifying the test substance as being for improving wrinkles if the estimated skin wrinkle index value is lower than the wrinkle index value of the subject's skin before administration. [8] A step of estimating a wrinkle index value of the subject's skin based on at least two values ​​of the subject's age and the measured value of the skin brightness, and A method for providing information on a wrinkle-improving composition suitable for a subject, comprising: a step of identifying a wrinkle-improving composition suitable for a subject based on the estimated wrinkle index value of the subject's skin. The estimation step may be performed using the wrinkle evaluation method according to any one of [1] to [6] above.

[0160] [9] A skin wrinkle evaluation device that causes a computer to execute the skin wrinkle evaluation method or the method for providing a skin wrinkle evaluation according to any one of [1] to [6] above. The wrinkle evaluation device is preferably equipped with (a) a skin wrinkle evaluation program and / or (b) a recording medium having the program recorded or stored therein, which is configured to execute the method according to any one of [1] to [6] above. The wrinkle evaluation device is preferably configured to access the program or the medium present outside the device and execute the method according to any one of [1] to [6] above. The recording medium may be a computer recording medium having instructions executable by a computer.

[0161]

[10] A method for evaluating skin wrinkles or a method for providing a skin wrinkle evaluation, comprising: (a) causing a computer to create a wrinkle prediction model using a trained model; and (b) using the resulting wrinkle prediction model to estimate an index value for wrinkles on the subject's skin based on at least two values, the subject's age and a measured value of skin brightness. The wrinkle prediction model is preferably any one of the above [3] to [6].

[11] Obtaining a plurality of training data including at least two values ​​of a subject's age and a measured value of skin brightness; A trained model generating method for generating a trained model that uses the training data to input at least two values, namely, the age value and the measured value of the skin brightness of each subject, and outputs a wrinkle prediction model that estimates an index value of wrinkles on the subject's skin. It is preferable that the data further includes one or two values ​​of a measured value of redness of the skin and / or a measured value of the amount of sebum on the skin. (12) Obtaining at least two data items, namely, the subject's age and a measured value of the skin's brightness; At least two values, namely, the age value and the measured value of the skin brightness of each subject, are input, and a wrinkle prediction model that estimates the wrinkle index value of the subject's skin is output. A learning model trained using training data. A method for assessing skin wrinkles or a method for providing an assessment of said skin wrinkles, estimating an index value of skin wrinkles of a subject based on at least two values ​​of the subject's age and a measured value of skin brightness, preferably further comprising one or two values ​​of a measured value of skin redness and / or a measured value of skin sebum content.

[13] A program for causing a computer to execute the method for evaluating skin wrinkles or the method for providing an evaluation of skin wrinkles according to

[11] above, or a recording medium storing the program. A skin wrinkle evaluation device or a skin wrinkle evaluation system including the program or the recording medium. EXAMPLES

[0162] The present invention will be described in more detail below based on test examples, etc. Note that the test examples, etc. described below are examples of typical test examples, etc. of the present invention, and are not to be construed as narrowing the scope of the present invention.

[0163] <Test Example 1: Wrinkle Prediction Model> Study Example 1-1. Study Participants A total of 48 Japanese women who participated in wrinkle and skin condition evaluation studies conducted at KOSÉ Research Institute, Inc. from 2011 to 2013 were included as participants in this study. All subjects signed informed consent forms prepared by KOSÉ Research Institute in accordance with the Helsinki Convention. This was a longitudinal repeated study, and participants were assessed for wrinkles and skin characteristics annually from 2011 to 2017. The ages of participants (female) ranged from 22 to 60 years old throughout the entire study period. As of the end of 2017, the age distribution was as follows: 20s: 6 people, 30s: 15 people, 40s: 13 people, 50s: 13 people, and 60s: 1 person. Participants participated in the study a maximum of six times, at least three times, and the majority of subjects participated in the study five times.

[0164] Test Example 1-2. Evaluation of wrinkles and skin condition using various instruments After washing their faces with the same facial cleanser, participants were allowed to acclimate for 30 minutes in a controlled environment of 20-22°C and 50±5% humidity, and then all of the following evaluations (wrinkles, stratum corneum moisture content, transepidermal water loss, sebum content, skin color, etc.) were performed. Each evaluation except for wrinkle evaluation was measured using the general measuring device and at the measurement site described below.

[0165] The participants' wrinkle condition was visually evaluated by trained experts in accordance with the guidelines published by the Japan Cosmetic Industry Association (Journal of Japanese Cosmetic Science Society, "Cosmetic Function Evaluation Method Review Committee Report: Cosmetic Function Evaluation Method Guidelines", Vol. 30, No. 4, pp. 316-332 (2006)). The wrinkle condition of the right corner of the eye was graded in 0.25 point increments from "0, 1, 2, 3, 4, 5, 6, 7" according to the wrinkle grade standard table. For example, the wrinkle grade standard table states that grade 0 means "no wrinkles" and grade 7 means "significantly deep wrinkles are observed." The moisture content of the participants' stratum corneum was measured using the stratum corneum capacitance measured on the upper right cheek of each participant using a SKICON-200EX (manufactured by IBS Corporation). Transepidermal water loss was similarly measured on the right cheek using a Vapometer (Delfin Technologies). The amount of sebum in the participants' skin was measured at the center of the forehead using a Sebumeter (manufactured by Courage +Khazaka electronic GmbH). The participants' skin color was measured using a Spectrophotometer CM-700d (KONICA MINOLTA) by measuring the L* value (brightness index), a* value (redness index), and b* value (yellowness index) of the upper right cheek of the participants.

[0166] Test Example 1-3. Statistical analysis for developing a wrinkle prediction model Using the data obtained in "Test Example 1-1" and "Test Example 1-2", the following wrinkle prediction model (Equations 1 to 7) was obtained.

[0167] In order to verify a model for predicting wrinkle conditions due to aging, which was the main objective of this study, we confirmed the distribution of the obtained wrinkle grades and the relationship between age and wrinkle grade. Next, we decided to add as candidates for wrinkle predictors the average of all measurement points for each evaluation device, in addition to age and skin condition measurements at all time points obtained by instrumental evaluation, as these would be important characteristic values ​​indicating an individual's skin condition. For prediction, we decided to avoid dividing the data into validation data and test data because the number of data was small, and to use all the data. Furthermore, we decided to use a generalized linear mixed-effects model for the prediction model, which can express unpredictable inter-individual differences in repeated data over time as random effects.

[0168]

number

[0169] To select the wrinkle predictors, a stepwise method using elimination of variables (algorithm) was used, and the model with the smallest AIC (Akaike Information Criterion) was determined to be the best model. (Algorithm: Mallows (1973) Technometrics 15, 661-675.; Steyerberg (2009) Statistics in Medicine 19(8), 1059-1079.; Akaike (1973) In 2nd International Symposium on Information Theory and an Extension of the Maximum Likelihood Principle, BN Petrov, and F. Csaki (eds), 267-281.) In selecting the wrinkle predictors, we first considered the full model that used all the wrinkle predictors. Finally, sensitivity analyses were performed using the obtained wrinkle predictors. All analyses were performed using R ver.3.5.2 statistical software (R Foundation for Statistical Computing, Vienna, Austria).

[0170] Test Example 1-4. Results and Discussion [Study Example 1-4.1 Participants] The mean age of participants during the study ranged from 38.64 years (95% CI: 35.47-41.81) at the start of the study to 44.24 years (95% CI: 41.47-47.34) at the end of the study. Next, the change in wrinkle grade over time for each individual was found to have a strong linear relationship, with the wrinkle grade increasing with increasing age, and large inter-individual differences in the average wrinkle grade for each individual. Based on this, a linear mixed effects model that introduces a random effect for the intercept was selected as the wrinkle prediction model for this study.

[0171] [Test Example 1-4.2 Development of a wrinkle prediction model] The final wrinkle prediction model was estimated to include five wrinkle predictors: (1) age, 2) sebum volume (amount of sebum on the skin), 3) a* value (redness of the skin), 4) average L* value (skin brightness) for each individual across all measurement years, and 5) interaction term between sebum volume and a* value (Table 1). In order to verify the accuracy of the wrinkle prediction model of the present invention, R 2 (%) and the RMSE, which shows the difference between the predicted value and the observed value (R 2 = 84.75, RMSE = 0.685), and these results showed that the wrinkle prediction model showed good prediction accuracy.

[0172] [Table 1]

[0173] [Test Example 1-4.3 Wrinkle prediction model (Equation 1)] Furthermore, the following wrinkle prediction model (Equation 1) is presented using the five wrinkle predictor factors derived above and a linear mixed effects model.

[0174] Wrinkle grade i =0.1469×Age + 0.7540×Ln(sebum) + 0.3270×Skin color a* + 0.1654×Mean[Skin color L*] - 0.1044×[Ln(sebum)×Skin color a*] - 15.90 + b 0,i (Formula 1) b 0,i ~N(0, 0.4847) Final equation for prediction of wrinkle grade in Japanese women aged 22-60 years

[0175] Considering the above-mentioned Test Example 1 and the following Test Examples 2 to 5, at least two of the five wrinkle prediction factors, namely, age and skin brightness measurement values, were important in the wrinkle prediction model of the present invention. Therefore, it was considered that a subject who wishes to evaluate the wrinkles of his / her skin can estimate the wrinkle index value of the subject with good prediction accuracy based on these two factors.

[0176] Generally, wrinkle grades increase with age, and moisturizing is said to be effective in preventing wrinkles. For this reason, in the past, age and measurements related to moisturizing (e.g., skin moisture content, transepidermal water loss) were considered to be the most important values. However, in the wrinkle prediction model of this study, it was completely unexpected for the inventor that measurements of skin moisture content and transepidermal water loss were not necessary, and that age and skin brightness were the most important values. By accumulating data on age and values ​​indicating skin condition (skin evaluation and measurements, etc.) for each individual over a long period of time and using multivariate analysis (especially linear mixed effects model), we have succeeded in deriving unprecedented results and ideas.

[0177] Furthermore, it was confirmed that a wrinkle prediction model consisting of five wrinkle predictor factors - age, skin brightness, skin redness, skin sebum amount, and the interaction term between sebum amount and skin redness - had particularly good prediction accuracy. For example, if the subject (female) has an "age value" of 35, a "skin brightness measurement" of 68, a skin redness measurement of 8.3, and a skin sebum measurement of 6.0, then substituting these values ​​into "age value" in "Age," "skin brightness measurement" in "Skin color L*," "skin redness measurement" in "Skin color a*," and "sebum measurement" in "sebum" in the above (Formula 1) will result in the skin wrinkle grade being 3.0 as shown below.

[0178] Furthermore, this study also made it possible to obtain the wrinkle prediction model Equation 1 and Equations 2 to 7 described later. Conventionally, wrinkle evaluation (wrinkle grade) relies on human visual inspection, and therefore requires the assistance of an experienced expert, which is not convenient. However, this technology makes it possible to quantify wrinkle grades more easily and objectively. Moreover, the measured values ​​of the skin condition used in this study can be obtained more easily by a skin condition measuring device such as a measuring instrument. Therefore, according to the present invention, even if the person is not an experienced expert, the wrinkle grade value can be obtained more easily and with higher accuracy. Furthermore, according to the present invention, the wrinkle grade can be quantified by using the camera function and video function of a smartphone or a computer with a web camera, so that the present invention makes it possible to objectively and accurately evaluate wrinkles with simpler operations regardless of time and place. Furthermore, by executing the wrinkle prediction model of the present invention on a computer including a CPU, it is possible to easily use wrinkle evaluation with higher prediction accuracy for each individual on a mobile terminal or the like. Therefore, the present invention can provide a technique that can evaluate skin wrinkles more easily and accurately for each individual.

[0179] <Test Example 2: Wrinkle Prediction Model (Formula 2)> Using the data obtained in Test Example 1, and further when each intercept in the wrinkle prediction model (Equation 1) was within the following range, the wrinkle prediction accuracy at the individual level was good, at 60% or more. Therefore, it was confirmed that the following Equation 2 can be used as the wrinkle prediction model (Equation 2). Therefore, by using Wrinkle Prediction Formula 1 or Wrinkle Prediction Formula 2, the present invention can accurately and simply estimate the wrinkle index value of a subject's skin based on four values: age, measured value of skin brightness, measured value of skin redness, and measured value of skin sebum amount.

[0180] Wrinkle grade i = 0.1200~0.2053×Age + 0.2200~1.280×Ln(sebum) + 0.050~0.5710×Skin color a* + 0.050~0.4000×Mean[Skin color L*] - 0.030~0.1800×[Ln(sebum)×Skin color a*] - 25.00~7.600 (Formula 2)

[0181] <Test Example 3: Number of wrinkle predictors> Using the data obtained in Test Example 1, in addition to the values ​​(age, sebum amount, skin redness, skin brightness) adopted for the above wrinkle predictors, instrumental evaluation of the skin condition was performed. For example, instrumental evaluation of the skin moisture content, transepidermal water loss, and skin yellowness was performed. However, the wrinkle grade predicted using all the measured values ​​as predictors was compared with the best model, and the prediction accuracy was about 60%, or the RMSE value was about 1.5, so it did not show good prediction accuracy. For this reason, it is considered that the prediction accuracy will decrease if other wrinkle predictors (e.g., skin moisture content, transepidermal water loss, etc.) are added to the above five wrinkle predictors (age, sebum amount, skin redness, skin brightness, and interaction term between sebum amount and a* value). For this reason, it is considered that the wrinkle prediction model using the above five wrinkle predictors is the best model.

[0182] <Test Example 4: In the case of the above two wrinkle predictors (age and skin brightness)> Of the five wrinkle predictors mentioned above, "age" and "skin brightness" were selected, and a wrinkle prediction model (Equation 3) using these two wrinkle predictors is shown below. The wrinkle prediction accuracy at the individual level was good, at over 80%. The wrinkle prediction model and wrinkle prediction accuracy were calculated using the R 2 was used. Therefore, by using wrinkle prediction equation 3, the present invention can more easily and accurately estimate the wrinkle index value of a subject's skin based on two values, that is, the age value and the measurement value of the skin brightness.

[0183] Wrinkle grade i = 0.1484×Age + 0.1844×Mean[Skin color L*] - 14.80 (Formula 3)

[0184] <Test Example 5: In the case of the above two wrinkle predictors + wrinkle predictor (sebum amount)> Using the data obtained in Test Example 1, of the five wrinkle predictors mentioned above, "age" and "skin brightness" were selected, and further "amount of sebum" was selected. A wrinkle prediction model (Formula 4) using these three wrinkle predictors is shown below. The wrinkle prediction accuracy at the individual level was good, at over 80%. The wrinkle prediction model and wrinkle prediction accuracy were calculated using the R 2 was used. Therefore, by using wrinkle prediction formula 4, the present invention can accurately and easily estimate the wrinkle index value of a subject's skin based on three values: age, measured skin brightness, and measured sebum amount.

[0185] Wrinkle grade i = 0.1504×Age + 0.1880×Mean[Skin color L*] +0.044×Ln(sebum) - 15.28 (Formula 4)

[0186] <Test Example 6: In the case of the above two wrinkle predictors + wrinkle predictor (redness, sebum amount)> Using the data obtained in Test Example 1, of the five wrinkle predictive factors above, "age" and "skin brightness" were selected, and further "redness" and "amount of sebum" were selected. A wrinkle prediction model (Formula 5) using these four wrinkle predictive factors is shown below. The wrinkle prediction accuracy at the individual level was good, at over 80%. The wrinkle prediction model and wrinkle prediction accuracy were calculated using the R 2 was used. Therefore, by using wrinkle prediction formula 5, the present invention can accurately and easily estimate the wrinkle index value of a subject's skin based on four values: age, measured skin brightness, and measured redness and sebum amount.

[0187] Wrinkle grade i = 0.1460×Age + 0.035×Ln(sebum) + 0.013×Skin color a* + 0.1812×Mean[Skin color L*] (Formula 5)

Claims

1. A method for evaluating wrinkles on the skin, which estimates an index value of wrinkles on the subject's skin by using at least the subject's age, a measurement value of skin brightness, a measurement value of skin redness, and a measurement value of the amount of sebum on the skin in a wrinkle prediction model.

2. The method for evaluating wrinkles on the skin according to claim 1 , further comprising the step of: adding an interaction term between sebum amount and redness of the skin to the wrinkle prediction model.

3. The wrinkle prediction model is The wrinkle index value of an individual is used as the objective variable, and a linear mixed effects model including at least the measured values ​​of the age and skin brightness of the individual is used as the explanatory variable. The method for evaluating skin wrinkles according to claim 1 or 2, wherein the model is obtained.

4. The method for evaluating skin wrinkles according to claim 3 , wherein the parameters of the linear mixed effects model are obtained using a maximum likelihood method or a restricted maximum likelihood method.

5. A step of estimating a wrinkle index value of the skin of a subject administered a test substance by using the method for evaluating skin wrinkles according to any one of claims 1 to 4; and A method for evaluating or searching for a composition for improving wrinkles, comprising a step of discriminating the test substance as being for improving wrinkles if the estimated skin wrinkle index value is lower than the wrinkle index value of the subject's skin before administration.

Images