Skin type determination device

Abstract

The invention relates to a skin type determination device. The skin type determination device according to one embodiment of the present invention comprises: a hue sensor for measuring the hue of the skin of a subject; the elasticity sensor is used for measuring the elasticity of the skin of the subject; one or more processors; a memory; and one or more programs stored in the memory and executed by the one or more processors, the one or more programs include determining a hue index by changing the hue data measured by the hue sensor to a value within a set range, and determining an elasticity index by changing the elasticity data measured by the elasticity sensor to a value within a set range. Instructions to delineate a skin type of the subject based on the tone indicator and the elasticity indicator.

Description

Technical Field

[0001] The present invention relates to a skin type determination device. Background Art

[0002] As the prior art, 16 Baumann type tests are being used as important questionnaire items for classifying skin types (U.S. Patent Publication US2014 / 0018634A1). The Baumann questionnaire determines each person's skin type by evaluating oiliness or dryness, sensitivity or resistance, pigmentation or non-pigmentation, and the presence or absence of wrinkles or elasticity.

[0003] However, the Baumann skin type cannot effectively serve as a basis for providing customized solutions due to reduced reliability caused by self-questionnaire evaluation and complex type classification results. Summary of the Invention

[0004] Technical Problem to be Solved

[0005] The problem to be solved by the present invention is to provide a method for accurately and quickly determining a relative skin type according to age.

[0006] The problems of the present invention are not limited to those mentioned above. For other problems not mentioned, those of ordinary skill in the art can clearly understand from the following description.

[0007] Solution to the Problem

[0008] To achieve the above object, a skin type determination device according to an embodiment of the present invention includes: a hue sensor for measuring the hue of a subject's skin; an elasticity sensor for measuring the elasticity of the subject's skin; one or more processors; a memory; and one or more programs stored in the memory and executed by the one or more processors, the one or more programs including instructions for changing hue data measured by the hue sensor to a value within a set range to determine a hue index, changing elasticity data measured by the elasticity sensor to a value within a set range to determine an elasticity index, and delineating the skin type of the subject based on the hue index and the elasticity index.

[0009] Advantages of the Invention

[0010] The skin type determination device according to the present invention can accurately and quickly determine a relative skin type considering age.

[0011] The advantages of the present invention are not limited to those mentioned above. For other advantages not mentioned, those of ordinary skill in the art can clearly understand from the following description. Brief Description of the Drawings

[0012] Figure 1 It is a block diagram of a skin type determination device according to an embodiment of the present invention.

[0013] Figure 2 It is a graph showing the results of a subject after normalizing hue data and elasticity data by a processor according to an embodiment of the present invention.

[0014] Figure 3 It is a graph shown according to the subject after normalizing oil content data and moisture data by a processor according to an embodiment of the present invention.

[0015] Figure 4 It is a graph showing the distribution of subjects after a processor according to an embodiment of the present invention determines a first evaluation index and a second evaluation index.

[0016] Figure 5a It shows an example of a processor according to an embodiment of the present invention locating a point where a reversal phenomenon of a hue index occurs.

[0017] Figure 5b It shows an example of a processor according to an embodiment of the present invention locating a point where a reversal phenomenon of an elasticity index occurs.

[0018] Figure 5c It shows an example of a processor according to an embodiment of the present invention locating a point where a reversal phenomenon of an oil content index occurs.

[0019] Figure 5d It shows an example of a processor according to an embodiment of the present invention locating a point where a reversal phenomenon of a moisture index occurs.

[0020] Figure 6a It is in Figure 5a A graph that clearly lists ratios according to age and group in the graph of.

[0021] Figure 6b It is in Figure 5b A graph that clearly lists ratios according to age and group in the graph of.

[0022] Figure 6c It is in Figure 5c A graph that clearly lists ratios according to age and group in the graph of.

[0023] Figure 6d It is in Figure 5d A graph that clearly lists ratios according to age and group in the graph of.

[0024] Figure 7a It is a graph representing the hue values of subjects as a normal distribution curve.

[0025] Figure 7b It is a graph representing the elasticity values of subjects as a normal distribution curve.

[0026] Figure 7c It is a graph representing the moisture value of the subject as a normal distribution curve.

[0027] Figure 7d It is a graph representing the oil value of the subject as a normal distribution curve.

[0028] Figure 8a It is a dot plot that shows the distinction between the high group and the low group obtained by dividing the value obtained by multiplication after normalizing the hue data and elasticity data of the subjects in the young group (10 - 34 years old).

[0029] Figure 8b It is a dot plot that shows the distinction between the high group and the low group obtained by dividing the value obtained by multiplication after normalizing the hue data and elasticity data of the subjects in the aging1 group (35 - 50 years old).

[0030] Figure 8c It is a dot plot that shows the distinction between the high group and the low group obtained by dividing the value obtained by multiplication after normalizing the hue data and elasticity data of the subjects in the old group (51 - 71 years old).

[0031] Figure 9 It is a graph that marks the distribution positions of each subject without applying the first age weight and the second age weight, divided by age, on the Figure 4 chart.

[0032] Figure 10 It is a flowchart of a method for determining skin type according to an embodiment of the present invention.

[0033] Figure 11 It is a flowchart of a method for deriving phenotypes by age group. Detailed Description of the Invention

[0034] The advantages, features, and methods for realizing them of the present invention will become clear with reference to the embodiments described below in conjunction with the accompanying Figure 1 drawings.

[0035] However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and these embodiments are only provided to make the disclosure of the present invention complete and to fully inform those of ordinary skill in the technical field to which the present invention pertains of the scope of the invention. The present invention is only defined by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0036] Hereinafter, the present invention will be described with reference to the accompanying drawings.

[0037] Figure 1It is a block diagram of a skin type determination device according to various embodiments of the present invention. Figure 2 It is a graph showing the results of a subject after the processor 210 according to various embodiments of the present invention normalizes the hue data and the elasticity data. Figure 3 It is a graph shown for each subject after the processor 210 according to various embodiments of the present invention normalizes the oiliness data and the moisture data. Figure 4 It is a graph showing the distribution of subjects after the processor 210 according to various embodiments of the present invention determines the first evaluation index and the second evaluation index.

[0038] Refer to Figures 1 to 4 As shown in , a skin type determination device or system according to various embodiments of the present invention includes: a hue sensor 110 configured to measure the skin tone of a subject; an elasticity sensor 120 configured to measure the elasticity of the subject's skin; a memory 230 configured to store the hue data measured by the hue sensor 110 and the elasticity data measured by the elasticity sensor 120; and one or more processors 210 that normalize the hue data to determine a hue value, normalize the elasticity data to determine an elasticity value, and determine a first evaluation index for delimiting the skin type of the subject based on the hue value and the elasticity value.

[0039] The hue sensor 110 may be a color sensor or a light sensor. The hue sensor 110 measures the color of the skin surface. The hue sensor 110 receives color information from the skin.

[0040] The elasticity sensor 120 senses the elasticity of the skin. The elasticity sensor 120 senses the amount of contraction, the amount of recovery, and the recovery time of the skin. The elasticity sensor 120 may be a distance measurement sensor using laser, ultrasonic wave, or infrared ray. The elasticity sensor 120 receives information about the contraction and recovery of the skin. The recovery time may be judged by the processor 210.

[0041] The memory 230 optionally includes one or more non-transitory computer-readable storage media, and also optionally includes a high-speed random access memory, and also optionally includes one or more non-volatile memories such as a magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory devices.

[0042] One or more processors 210 drive or execute various software programs and / or instruction sets stored in the memory 230 to perform various functions for the skin type determination device and process data. The processor 210 normalizes the data. Normalization moves the range of data values to between 0 and 1. The processor 210 changes the units of all data values to the same or dimensionless numbers.

[0043] The skin type determination device or system according to various embodiments of the present invention includes an oil sensor 130, a moisture sensor 140, an elasticity sensor 120, a hue sensor 110, and a main device 200. The main device 200 includes a process and a memory 230. The various sensors 110, 120, 130, 140 are connected to the main device 200 by wire or wirelessly. The main device 200 may be provided on a cloud server. All or part of each component may be a portable mobile device.

[0044] According to Figure 2 , the color data and elasticity data are distributed differently for each subject. According to Figure 3 , the oil data and moisture data are distributed differently for each subject (H: high, M: medium, L: low). The processor 210 may normalize the hue data and elasticity data for each subject and store them in the memory 230.

[0045] The processor 210 determines a first evaluation index. The first evaluation index is an index that integrates the hue data and the elasticity data. As Figure 4 shown, the processor 210 determines one first evaluation index based on the hue data and the elasticity data.

[0046] The processor 210 operates on two or more variables. An operation refers to a mathematical, logical, or other form of calculation performed using two or more variables. For example, the processor 210 may perform a mathematical operation. Mathematical operations include the four arithmetic operations (addition, subtraction, multiplication, division), exponential operations, logarithmic operations, differentiation, integration, etc. The processor 210 may perform a multiplication operation on the hue data and the elasticity data to determine the first evaluation index and the second evaluation index described later.

[0047] As another example, the processor 210 may perform a comparison operation. The processor 210 compares with a set standard and evaluates as at least one of "greater than, less than, less than, exceeding", and returns a set value according to the result. Hereinafter, although multiplication operation, which is one of the preferred examples of the operation, is used as an example for description, as long as it can strengthen the correlation between the data for determining the skin type and is beneficial to data compression, other mathematical operations, logical operations, and comparison operations are also possible. Therefore, in the present invention, "operation" does not only refer to multiplication operation.

[0048] A skin type determination device or system according to various embodiments of the present invention includes: a hue sensor 110 configured to measure the hue of a subject's skin; an elasticity sensor 120 configured to measure the elasticity of the subject's skin; one or more processors 210; a memory 230; and one or more programs stored in the memory 230 and executed by the one or more processors 210, the one or more programs including instructions for determining a hue value by changing hue data measured by the hue sensor 110 to a value within a set range, determining an elasticity value by changing elasticity data measured by the elasticity sensor 120 to a value within a set range, and determining a first evaluation index for delimiting the skin type of the subject based on the hue value and the elasticity value (one preferred example being a multiplication operation).

[0049] The value within the set range can be between 0 and 1. As a specific example, the hue data measured by the hue sensor 110 within the set range can be between 0 and 1. As another specific example, the elasticity data measured by the elasticity sensor 120 within the set range can be between 0 and 1. The processor 210 changes the column of the data to be between 0 and 1. The processor 210 can perform machine learning.

[0050] The processor 210 can standardize the data. Standardization can be performed under the assumption that the data follows a normal distribution (bell-shaped distribution). The processor 210 can transform the data such that the mean of the data is 0 and the standard deviation is 1.

[0051] The processor 210 can easily learn the data through normalization or standardization. The processor 210 learns the columns equally rather than focusing on a certain column. The processor 210 can standardize and normalize the data and perform machine learning, and then compare the results of the two cases to determine whether to standardize or normalize the data.

[0052] A skin type determination device or system according to various embodiments of the present invention includes: an oil content sensor 130 configured to measure the oil content of a subject's skin; a moisture sensor 140 configured to measure the moisture of the subject's skin; one or more processors 210; a memory 230; and one or more programs stored in the memory 230 and executed by the one or more processors 210, the one or more programs including instructions for determining an oil content value by changing oil content data measured by the oil content sensor 130 to a value within a set range, determining a moisture value by changing moisture data measured by the moisture sensor 140 to a value within a set range, and determining a second evaluation index for delimiting the skin type of the subject based on the oil content value and the moisture value (one preferred example being a multiplication operation).

[0053] According to Figure 2 , the oil content data and the moisture content data are distributed differently according to each subject (H: high, M: medium, L: low). The processor 210 can normalize the oil content data and the moisture content data according to the subject and store them in the memory 230. The processor 210 can use the oil content data and the moisture content data to determine a second evaluation index that integrates the oil content and the moisture content.

[0054] The processor 210 determines the second evaluation index. The second evaluation index is an index that integrates the oil content data and the moisture content data. As Figure 4 shown, the processor 210 determines the first evaluation index based on the hue data and the elasticity data (one of the preferred examples is multiplication operation). The processor 210 can use the first evaluation index and the second evaluation index to display the skin state of the subject on a plane.

[0055] The moisture sensor 140 includes: a first moisture measuring device for measuring the amount of moisture loss (transepidermal water loss: TEWL) of the subject's skin; and a second moisture measuring device for measuring the moisture content (hydration, HD) of the subject's skin. One or more programs change the moisture loss amount and the moisture content to values within a set range and determine the moisture value using the following formula.

[0056]

[0057] where M is the moisture value, HD is the moisture content of the skin, and TEWL is the moisture loss amount of the skin.

[0058] To generate an index representing the skin moisture state, the processor 210 can synthesize the moisture content and the moisture loss to determine a moisture value. The processor 210 determines that the lower the skin moisture loss amount, the better the function of the skin barrier is maintained. The processor 210 determines that the lower the skin moisture loss amount, the higher the skin moisturizing ability. The processor 210 determines that the higher the moisture content (hydration) of the skin, the better the skin moisturizing ability. The processor 210 determines that the higher the numerical value of the moisture value M, the higher the skin moisturizing ability.

[0059] The first moisture measuring device measures the amount of moisture on the skin per minute and measures the amount of moisture reduction per minute. The moisture loss amount of the skin is the moisture loss amount of the skin barrier existing in the stratum corneum, which is the outermost layer of the skin. The second moisture measuring device measures the amount of moisture contained in the skin.

[0060] Figure 5a Shows an example of the processor 210 locating the point where the reversal phenomenon of the hue index occurs according to various embodiments of the present invention.Figure 5b An example is shown of a processor 210 locating a point where a reversal phenomenon of an elasticity index occurs according to various embodiments of the present invention. Figure 5c An example is shown of a processor 210 locating a point where a reversal phenomenon of an oil content index occurs according to various embodiments of the present invention. Figure 5d An example is shown of a processor 210 locating a point where a reversal phenomenon of a moisture index occurs according to various embodiments of the present invention. Figure 6a is a graph that clearly lists ratios by age and group in the Figure 5a graph. Figure 6b is a graph that clearly lists ratios by age and group in the Figure 5b graph. Figure 6c is a graph that clearly lists ratios by age and group in the Figure 5c graph. Figure 6d is a graph that clearly lists ratios by age and group in the Figure 5d graph.

[0061] A skin type determination device according to various embodiments of the present invention includes: an oil content sensor 130 for measuring the oil content of a subject's skin; and a moisture sensor 140 for measuring the moisture of the subject's skin.

[0062] The one or more programs include instructions for quantifying the skin state data of each person measured by the sensor according to set criteria to divide into groups, and selecting data of types with similar patterns of change in the proportion of groups divided by age to determine the skin state of the subject.

[0063] The pattern can be judged based on the similarity of the age ranges where a reversal phenomenon of the reverse order of the proportion of groups occurs. The data of types with similar patterns of change in the proportion of groups can be hue data and elasticity data.

[0064] Explain the meaning of the reversal phenomenon.

[0065] According to Figure 5a and Figure 6a , with respect to the hue value of the subject, the proportions of the high group and the low group start to change starting from 34 years old, and this pattern is completely reversed in the late 40s age range. That is, below 34 years old, the high group is in the majority, but after 34 years old, the low group gradually becomes the majority.

[0066] Similarly, according to Figure 5b and Figure 6b , with respect to the elasticity value of the subject, the proportions of the high group and the low group start to change starting from 34 years old, and this pattern is completely reversed in the late 40s. That is, below 34 years old, the high group is in the majority, but after 34 years old, the low group gradually becomes the majority.

[0067] In this way, both the hue value and the elasticity value show a reversal phenomenon, and the age range in which this occurs is the same. Therefore, the data regarding the hue value and the elasticity value have the same pattern. The hue value and the elasticity value are data with a high degree of correlation.

[0068] Therefore, when performing a multiplication operation on the hue value and the elasticity value, the characteristics are amplified, enabling the characteristics of the data to be more clearly distinguished.

[0069] On the other hand, referring to Figure 5c and Figure 6c , the oil content value shows a reversal phenomenon, but there is a clear distinction from the hue value and the elasticity value in terms of the age range in which it occurs. Referring to Figure 5d and Figure 6d , the moisture value does not show a reversal phenomenon. The moisture value reflects the skin condition of each individual, but has a relatively low correlation with age.

[0070] Figure 7a is a graph representing the hue values of the subjects as a normal distribution curve. Figure 7b is a graph representing the elasticity values of the subjects as a normal distribution curve. Figure 7c is a graph representing the moisture values of the subjects as a normal distribution curve. Figure 7d is a graph representing the oil content values of the subjects as a normal distribution curve.

[0071] One or more programs according to various embodiments of the present invention include instructions for determining the skin condition of a subject by selecting remaining data with dissimilar group proportion change patterns. The remaining data with dissimilar group proportion change patterns are oil content data measured by the oil content sensor 130 and moisture data measured by the moisture sensor 140.

[0072] Referring to Figure 7a , Figure 7b and Figure 7c , the median and the average value are consistent. According to Figure 7d , the average value and the median of the oil content value are inconsistent. According to Figure 7d , the data distribution of the oil content value is asymmetric or has a long tail, and data with outliers or special values affect the average value.

[0073] There are people with extremely high oil content values (in the tail), and it is preferable to reduce the influence of these outliers.

[0074] According to various embodiments of the present invention, multiplying the oil content value (oil content data) by the moisture value (moisture data) can reduce the influence of outliers present in the oil content data and strengthen the pattern of normal data. Therefore, the data quality and the accuracy of judgment can be improved. In addition, multiplying the oil content value (oil content data) and the moisture value (moisture data) can be used as a judgment index for determining the skin condition of each individual regardless of age.

[0075] Figure 8a It is a dot chart that shows the distinction between the high and low groups divided by the value obtained through multiplication after normalizing the hue data and elasticity data of the subjects in the young group (aged 10 to 34). 8b is a dot chart that shows the distinction between the high and low groups divided by the value obtained through multiplication after normalizing the hue data and elasticity data of the subjects in the aging group (aged 35 to 50). Figure 8c It is a dot chart that shows the distinction between the high and low groups divided by the value obtained through multiplication after normalizing the hue data and elasticity data of the subjects in the elderly group (aged 51 to 71).

[0076] Refer to Figure 8a 、 Figure 8b and Figure 8c When the magnitude of the number obtained by multiplying the X-axis value (hue value) and the Y-axis value (elasticity value) of a certain point is greater than or equal to a certain value, it is the high group; otherwise, it is the low group.

[0077] Figure 8a It is an analysis of a relatively young group of subjects. The dividing line (dashed line) between the high and low groups is located at the upper right end and moves to the lower left end as it moves towards Figure 8b and Figure 8c move. Commonly, the result values of the subjects are concentrated around the dividing line. This indicates that there are few outliers in the multiplication results of the hue value and the elasticity value, making it suitable as a standard for judging skin condition.

[0078] On the other hand, skin condition has an absolute impact on age, so it is meaningless to judge the absolute skin condition ignoring age. This indicates that the dividing line that moves with age is a standard for judging the relative skin condition considering age. Therefore, the multiplication result of the hue value and the elasticity value becomes a standard for judging the relative skin condition considering age.

[0079] According to various embodiments of the present invention, four phenotypes can be used to judge the state of the subject considering age.

[0080] The processor 210 can divide the skin condition of the subject into four groups: HH, HL, LH, and LL using the multiplication result of the hue data and the elasticity data and the multiplication result of the oil content data and the moisture data. The processor 210 can divide the four groups into HH (the case where both hue * elasticity and oil * moisture are high), HL (the case where hue * elasticity is high but oil * moisture is low), LL (the case where both hue * elasticity and oil * moisture are low), and LH (the case where hue * elasticity is low but oil * moisture is high). The four groups have characteristic distributions on the chart.

[0081] The skin type determination device according to various embodiments of the present invention can classify the skin types of subjects by age group. That is, it can judge the relative skin state according to age group, rather than the absolute skin state. Since skin state is absolutely affected by age, a judgment without considering age may be meaningless.

[0082] Figure 9 It is a graph in which the distribution positions of each subject in the state where the first age weight and the second age weight are not applied are marked by age on Figure 4 the chart.

[0083] The first evaluation index is the multiplication result of the hue value and the elasticity value, and the second evaluation index is the multiplication result of the oil content value and the moisture value.

[0084] Referring to Figure 9 , it can be seen that according to the age groups of teenagers, twenties, thirties, forties, fifties, and sixties, the result values (inverted triangle graphs) of the subject groups form clusters and gradually move. This is because the first evaluation index and the second evaluation index compare the skin states of the subjects with those of the groups in the same age group and intuitively show the relative results.

[0085] According to various embodiments of the present invention, even if it is LL based on the young group, it can be HH or HL based on the old group, and a skin prescription suitable for it can be provided.

[0086] The region or boundary of the center or cluster that divides the phenotype moves with the age group. After judging the characteristics of the center or cluster, the processor 210 can distinguish the relative skin states of each subject.

[0087] One or more programs according to various embodiments of the present invention calculate (one of the preferred examples is multiplication) the first age weight set based on the subject's age and the first evaluation index to determine the first phenotype.

[0088] One or more processors 210 calculate (one of the preferred examples is multiplication) the second age weight set based on the subject's age and the second evaluation index to determine the second phenotype.

[0089] For example, the processor 210 can classify the subjects into three stages, namely, a young group (Younggroup) under 34 years old, an aging I group (Aging I group) from 35 to 50 years old, and an old group (Old group) over 51 years old. The first age weight and the second age weight can also be different according to gender. The processor 210 can apply the first age weight and the second age weight differently according to age.

[0090] The processor 210 can determine the first age weight and the second age weight differently according to age through machine learning. The first age weight and the second age weight can also be preset. The first age weight and the second age weight can be stored in the memory 230.

[0091] The processor 210 can compare the hue indexes of multiple collected subjects to judge the age at which the reversal phenomenon occurs. For example, the processor 210 can judge that in the case of subjects under 35 years old, most subjects have a hue index exceeding 0.5, but in the case of subjects over 35 years old, most subjects have a hue index below 0.5 (in Figure 5a , Figure 5b , Figure 5c and Figure 5d , most are marked as high, and few are marked as low, and the arrow is the point where the reversal phenomenon occurs).

[0092] At this time, in the case of the hue index, the processor 210 judges that 35 years old is the age at which the reversal phenomenon occurs. At this time, the processor 210 can determine the first age weight when over 35 years old as 1, and the first age weight when under 35 years old as 0.7. In the same way, in the case of the elasticity index, the processor 210 judges that 35 years old is the age at which the reversal phenomenon occurs.

[0093] The processor 210 can compare the oil scores of multiple collected subjects to judge the age at which the reversal phenomenon occurs. For example, the processor 210 can also divide the subjects into three groups: under 30 years old, over 30 years old and under 50 years old, and over 50 years old to judge the second age weight.

[0094] For example, the processor 210 can also judge that in the case of subjects under 15 years old, most subjects have an oil score exceeding 0.5, in the case of subjects over 15 years old and under 50 years old, most subjects have an oil score below 0.5, and in the case of subjects over 50 years old, most subjects have an oil score above 0.5.

[0095] At this time, the processor 210 judges that the ages at which the reversal phenomenon occurs are 15 years old and 50 years old. The processor 210 sets different second age weights around 15 years old and 50 years old.

[0096] The processor 210 applies the first age weight and the second age weight to consider the relative differences caused by age. The processor 210 applies the first age weight and the second age weight to determine the skin state of the subject compared with the same age.

[0097] Referring to FIG. 6, according to age groups, the skin states of the subjects are concentrated in a certain area. However, the skin state needs to be relatively judged within the same age range. Therefore, the processor 210 needs to consider the distribution according to age.

[0098] For example, when the processor 210 determines that the objective skin condition of a teenage subject is better than that of a septuagenarian subject, but the elasticity is reduced compared to the same other teenage subjects, the processor 210 may compare the phenotype of the teenage subject with the same age group and assign a symbol indicating that the first phenotype is low, insufficient, or poor. Conversely, the processor 210 may compare the phenotype of the septuagenarian subject with the same age group and assign a symbol indicating that the first phenotype is high, sufficient, or excellent.

[0099] The processor 210 may also determine a second age weight and a second phenotype in the same manner as determining the first age weight and the first phenotype.

[0100] According to an embodiment, the memory 230 may also pre-store information on the first age weight and the second age weight.

[0101] The skin type determination device according to various embodiments of the present invention, as a device of a skin type determination device using a hue sensor 110, an elasticity sensor 120, a moisture sensor 140, an oil sensor 130, and one or more processors 210, includes: a step of measuring the hue, elasticity, oil, and moisture of a subject's skin; and a step of determining a first evaluation index and a second evaluation index by one or more processors 210, wherein the first evaluation index is determined by the processor 210 changing the hue data to a value within a set range to determine a hue value, changing the elasticity data to a value within a set range to determine an elasticity value, and performing an operation (one of the preferred examples is a multiplication operation) on the hue value and the elasticity value, and the second evaluation index is determined by the processor 210 changing the oil data to a value within a set range to determine an oil value, changing the moisture data to a value within a set range to determine a moisture value, and performing an operation (one of the preferred examples is a multiplication operation) on the oil value and the moisture value.

[0102] The skin type determination device or system according to various embodiments of the present invention includes: an oil sensor 130 for measuring the oil of a subject's skin; a moisture sensor 140 for measuring the moisture of a subject's skin; a memory 230 for storing the oil data measured by the oil sensor 130 and the moisture data measured by the moisture sensor 140; and one or more processors 210 for normalizing the oil data to determine an oil value, normalizing the moisture data to determine a moisture value, and determining a second evaluation index for delimiting the skin type of the subject based on the oil value and the moisture value (one of the preferred examples is a multiplication operation).

[0103] A skin type determination device or system according to various embodiments of the present invention includes: a hue sensor 110 configured to measure the hue of a subject's skin; an elasticity sensor 120 configured to measure the elasticity of the subject's skin; one or more processors 210; a memory 230; and one or more programs stored in the memory 230 and executed by the one or more processors 210, the one or more programs including instructions for determining a hue value by changing the hue data measured by the hue sensor 110 to a value within a set range, determining an elasticity value by changing the elasticity data measured by the elasticity sensor 120 to a value within a set range, and performing an operation (one preferred example is a multiplication operation) on the hue value and the elasticity value to determine a first evaluation index for defining the skin type of the subject.

[0104] The value within the set range may be between 0 and 1. The one or more programs perform an operation (one preferred example is a multiplication operation) on a first age weight set based on the subject's age and the first evaluation index to determine a first phenotype, and store the first phenotype and a second phenotype in the memory 230.

[0105] A skin type determination device or system according to various embodiments of the present invention includes: a moisture sensor 140 configured to measure the moisture of a subject's skin; one or more processors 210; a memory 230; and one or more programs stored in the memory 230 and executed by the one or more processors 210, the one or more programs changing the moisture data measured by the moisture sensor 140 to a value within a set range to determine a moisture value, the moisture sensor 140 including: a first moisture measurement device configured to measure the moisture loss of the subject's skin; and a second moisture measurement device configured to measure the moisture content of the subject's skin, the one or more programs including instructions for changing the moisture loss and the moisture content to values within a set range and using the following formula to determine the moisture value and judge the skin state.

[0106]

[0107] Where M is the moisture value, HD is the moisture content of the skin, and TEWL is the moisture loss of the skin.

[0108] A skin type determination device or system according to various embodiments of the present invention includes: a hue sensor 110 configured to measure the hue of a subject's skin; an elasticity sensor 120 configured to measure the elasticity of the subject's skin; an oiliness sensor 130 configured to measure the oiliness of the subject's skin; a moisture sensor 140 configured to measure the moisture of the subject's skin; a memory 230 configured to store the hue data measured by the hue sensor 110 and the elasticity data measured by the elasticity sensor 120; and one or more processors 210,

[0109] One or more processors 210 that change the hue data to a value within a predetermined range to determine a hue value; change the elasticity data to a value within a set range to determine an elasticity value; perform a multiplication operation on the hue value and the elasticity value to determine a first evaluation index for defining the skin type of the subject; change the oiliness data to a value within a set range to determine an oiliness value; change the moisture data to a value within a set range to determine a moisture value; and determine a second evaluation index for defining the skin type of the subject based on the oiliness value and the moisture value (one preferred example is a multiplication operation).

[0110] The memory 230 stores a standardization or normalization program executed by one or more processors 210 so that it can be changed to a value within a set range.

[0111] Figure 10 It is a flowchart of a skin type determination method according to various embodiments of the present invention.

[0112] Referring to Figure 10 , a skin type determination method according to various embodiments of the present invention, as a method of using a skin type determination device having a hue sensor 110, an elasticity sensor 120, a moisture sensor 140, an oiliness sensor 130, and one or more processors 210, includes: a step (S100) of measuring the hue, elasticity, oiliness, and moisture of a subject's skin; and a step of determining a first evaluation index and a second evaluation index by one or more processors 210. The first evaluation index is determined by the processor 210 changing the hue data to a value within a set range to determine a hue value, changing the elasticity data to a value within a set range to determine an elasticity value (S110), and performing an operation (one preferred example is a multiplication operation) on the hue value and the elasticity value to determine (S130). The second evaluation index is determined by the processor 210 changing the oiliness data to a value within a set range to determine an oiliness value, changing the moisture data to a value within a set range to determine a moisture value (S210), and performing an operation (one preferred example is a multiplication operation) on the oiliness value and the moisture value to determine (S230).

[0113] According to various embodiments of the present invention, the processor 210 performs the step (S150) of determining a first phenotype by multiplying a first age weight set based on the age of the subject by a first evaluation index. According to various embodiments of the present invention, the processor 210 performs the step S250 of determining a second phenotype by multiplying a second age weight set based on the age of the subject by a second evaluation index. One or more processors 210 may change the water loss amount and the water content to values within a set range and use them to determine the water value. The formula for determining the water value is the same as that described above.

[0114] The skin type determination device and / or system according to various embodiments of the present invention may mark the first phenotype and the second phenotype by attaching age symbols as follows, rather than multiplying the age weights.

[0115]

[0116] 1 st phenotype 2 nd phenotype

[0117] The memory 230 may store the skin state of the subject by classifying it into phenotypes such as H / H, H / L, L / H, and L / L. In the phenotype, the prefix H or L may refer to high or low, or excellent or insufficient skin tone and elasticity. In the phenotype, the suffix H or L may refer to high or low, or excellent or insufficient oil and water. The phenotype is used as data for improving the skin state of the subject. The above description can be organized into the following formula.

[0118] Refer to Figure 11 , step A involves an age-group derivation algorithm (female & 5 parameters, N = 775).

[0119] Although there can be various criteria for high or low age, in the above embodiments, young is based on 34 years old or less, aging 1 is based on 35 years old or more and 50 years old or less, and old is based on 51 years old or more.

[0120] Then, five parameters, namely skin tone, elasticity, oil, water, and water loss amount, are measured using a sensor. In Figure 11 , step B distinguishes high and low through color and elasticity values (clinical data & survey, N = 705). In Figure 11 , step C distinguishes high and low through oil and water values.

[0121] According to the present invention, the formula for standardizing various data is as follows.

[0122] SS Function: Standard Scalar (mean = 100, std = 20)

[0123]

[0124] The above formula is used to change the data to a value within the range of 0 to 200.

[0125] Tone and Elasticity value(TE ss )

[0126]

[0127] The above formula represents multiplying the standardized or normalized data related to tone and elasticity.

[0128] Oil and Moist value(OM ss )

[0129]

[0130] The above formula represents multiplying the standardized or normalized data related to oil and moisture.

[0131]

[0132] The above formula represents the formula for deriving oil content data, which uses the average value after collecting oil from the forehead, nose, and cheeks respectively.

[0133]

[0134] The above formula represents the formula for deriving moisture content data, which uses the average value after collecting moisture from the forehead and cheeks respectively.

[0135]

[0136] The above formula represents the formula for deriving moisture loss data, which uses the average value after collecting moisture from the forehead and cheeks respectively.

[0137] Hereinafter, a method for dividing into aging groups will be described.

[0138]

[0139] Q 1 = Quanttile(x ss , 1), Q3 = Quanttile(x ss , 3)

[0140] Quantile (quartile) is a three - quartile group used to very clearly distinguish the median group greyzone, the remaining upper group (H) and lower group (L).

[0141] Explain the above formula. First, perform GRP(x) on SS(x) of color, elasticity, oil content, and moisture ss ).

[0142] GRP(Color.ITA ss ), GRP(Elasticity.R7 ss )

[0143] GRP(oil ss ), GRP(Moist ss )

[0144] Next, extract the age

[0145] Among the clinical measurement values, confirm the percentage (%) of GRP(x) according to age. Then, confirm the age at which the H-type sample ratio decreases compared to the L-type sample ratio

[0146] Examples of derivation are as follows

[0147] Age ITA = 35, Age R7 = 36, Age Oil = 51

[0148]

[0149] The following is a formula that is marked as high when it is higher than the set value and marked as low when it is lower than the set value

[0150]

[0151] The following lists that the phenotypes related to hue-elasticity (TE) can be expressed as H or L as described above

[0152] TE group = SP(TE ss )

[0153] The following lists that the phenotypes representing those related to oil-moisture (OM) can be expressed as H or L

[0154]

[0155] The following lists together the groups corresponding to age and the phenotypes related to hue-elasticity (TE). In the following example, the subjects are in the young group

[0156] Young.TE grop = TE group (TE ss in Young samples)

[0157] The groups corresponding to age and the phenotypes related to oil-water (OM) are listed together below. In the following example, the subjects are in the young group.

[0158]

[0159] Information on tone-elasticity (TE), oil-water (OM), and age can be expressed as follows.

[0160] Young.KSC = Young.TE grop + Young.OM grop

[0161]

[0162] TE type OM type

[0163] The effects according to the present invention are as follows.

[0164] According to the present invention, the processor 210 can obtain a first evaluation index and a second evaluation index by performing multiplication on the four types of data again.

[0165] In addition, according to the present invention, the processor 210 can group the subjects by determining the first evaluation index and the second evaluation index, and use them as data for machine learning through normalization or standardization.

[0166] In addition, the processor 210 according to the present invention can apply a first age weight and a second age weight to perform a relative evaluation of tone, elasticity, oil, and moisture considering age.

[0167] In addition, according to the present invention, the processor 210 can objectively evaluate the skin condition by processing only four types of data. Elasticity shows a high correlation with pores and wrinkles. Therefore, the first phenotype and the second phenotype as shown below can basically be regarded as including all six types of indicators including pores and wrinkles.

[0168] In addition, according to the present invention, the processor 210 can also independently judge the moisture state of the skin using the moisture value without considering the age group.

[0169] As mentioned above, although the preferred embodiments of the present invention have been described with reference to the drawings, the present invention is not limited to the above specific embodiments. Of course, without departing from the gist of the present invention claimed in the scope of the claims, those of ordinary skill in the art to which the present invention pertains can make various modifications, and these modifications should not be understood separately from the technical idea or perspective of the present invention.

Claims

1. A skin type determination device, Among them, including: a hue sensor for measuring the hue of a subject's skin; an elasticity sensor for measuring the elasticity of a subject's skin; one or more processors; a memory; and one or more programs stored in the memory and executed by the one or more processors, the one or more programs including: instructions for determining a hue index by changing hue data measured by the hue sensor to a value within a set range, determining an elasticity index by changing elasticity data measured by the elasticity sensor to a value within a set range, and delineating a skin type of the subject based on the hue index and the elasticity index.

2. The skin type determination device according to claim 1, wherein the value within the set range is between 0 and 1.

3. The skin type determination device according to claim 1, wherein the one or more programs calculate a first phenotype based on a first age weight set according to the age of the subject and a first evaluation index obtained based on the hue index and the elasticity index.

4. The skin type determination device according to claim 1, wherein further including: an oil content sensor for measuring the oil content of a subject's skin; and a moisture sensor for measuring the moisture of a subject's skin, the one or more programs further including: instructions for quantifying skin state data of each person measured by the sensors according to set criteria to divide into groups, and selecting data of types with similar patterns of change in the proportion of the groups divided according to age to determine the skin state of the subject.

5. The skin type determination device according to claim 4, wherein the pattern is the similarity of the age range where a reverse phenomenon of the reverse order of the proportion of the groups occurs.

6. The skin type determination device according to claim 4, wherein the data of types with similar patterns of change in the proportion of the groups are the hue data and the elasticity data.

7. The skin type determination device according to claim 6, wherein the one or more programs further include: instructions for selecting the remaining data with dissimilar patterns of change in the proportion of the groups to determine the skin state of the subject.

8. The skin type determination device according to claim 7, wherein the remaining data with dissimilar patterns of change in the proportion of the groups are the oil content data measured by the oil content sensor and the moisture data measured by the moisture sensor.

9. The skin type determination device according to claim 4, wherein the one or more programs include: instructions for determining an oil content index by changing the oil content data to a value within a set range, determining a moisture index by changing the moisture data to a value within a set range, and delineating a skin type of the subject based on the oil content index and the moisture index.

10. A skin type determination device, Among them, including: an oil content sensor for measuring the oil content of a subject's skin; a moisture sensor for measuring the moisture of a subject's skin; a memory storing the oil content data measured by the oil content sensor and the moisture data measured by the moisture sensor; and one or more processors, The one or more processors normalize the oil content data to determine an oil content index, normalize the moisture data to determine a moisture index, and perform a multiplication operation on the oil content index and the moisture index to determine the skin type of the subject.

11. The skin type determination device according to claim 10, wherein, the memory stores a standardization or normalization program executed by the one or more processors to change the data of each measured subject into a value within a set range.

12. A skin type determination device, Wherein, comprising: an oil content sensor for measuring the oil content of the subject's skin; a moisture sensor for measuring the moisture of the subject's skin; a hue sensor for measuring the hue of the subject's skin; an elasticity sensor for measuring the elasticity of the subject's skin; one or more processors; a memory; and one or more programs stored in the memory and executed by the one or more processors, the one or more programs comprising: instructions for changing the oil content data measured by the oil content sensor into a value within a set range to determine an oil content index, changing the moisture data measured by the moisture sensor into a value within a set range to determine a moisture index, changing the hue data measured by the hue sensor into a value within a set range to determine a hue index, changing the elasticity data measured by the elasticity sensor into a value within a set range to determine an elasticity index, performing a multiplication operation on the hue index and the elasticity index to determine the skin type of the subject, and performing a multiplication operation on the oil content index and the moisture index to determine the skin type of the subject.

13. The skin type determination device according to claim 12, wherein, the one or more programs multiply a first age weight set based on the subject's age by a first evaluation index obtained by performing a multiplication operation on the hue index and the elasticity index to determine a first phenotype, multiply a second age weight set based on the subject's age by a second evaluation index obtained by performing a multiplication operation on the oil content index and the moisture index to determine a second phenotype, and store the first phenotype and the second phenotype in the memory.

14. The skin type determination device according to claim 12, wherein, the moisture sensor includes: a first moisture measurement device for measuring the moisture loss of the subject's skin; and a second moisture measurement device for measuring the moisture content of the subject's skin, the one or more programs change the moisture loss and the moisture content into values within a set range, and determine the moisture index using the following formula, where M is the moisture index, HD is the moisture content of the skin, and TEWL is the moisture loss of the skin.

15. The skin type determination device according to claim 12, wherein, the memory stores a standardization or normalization program executed by the one or more processors to change the data of each measured subject into a value within a set range.

Images