Skin condition estimation method, information processing device, and program

Abstract

To provide a skin condition estimation method.SOLUTION: A skin condition estimation method comprises: a step for acquiring psychosomatic data related to the body and mind of a subject of skin condition estimation; and a step for estimating the subject's skin condition using a skin model in which the correlation between the psychosomatic data and skin conditions is described. The psychosomatic data includes at least one of a liver function-related variable, a muscle / skeleton-related variable, a heart rate / blood pressure-related variable, a blood oxidation-related variable, a blood count-related variable, a lipid metabolism-related variable, an autonomic function-related variable, a personal attribute-related variable, a renal function-related variable, a body composition-related variable, a glucose tolerance-related variable, an electrolyte-related variable, a cognitive function-related variable, an immunometabolism-related variable, and a depression / fatigue / drowsiness-related variable.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a skin condition estimation method, an information processing device, and a program. [Background technology]

[0002] There are known methods for estimating skin conditions based on various types of information about the human body.

[0003] For example, International Publication WO2022-030300 discloses a technology for predicting future skin conditions based on hormone balance.

[0004] For example, Patent Publication No. 2020-014710 discloses a technology for estimating skin condition (at least one of pores, wrinkles, pigmentation, and skin color) using muscle mass (muscle weight per body weight, or muscle volume per volume, muscle mass related to the trunk (chest and abdomen), lower body, or the total of the trunk and lower body) as an indicator. Summary of the Invention [Problem to be solved by the invention]

[0005] Various factors interact with and influence the condition of the skin. However, since the hormone balance in International Publication No. WO2022-030300 and the muscle mass in Patent Publication No. 2020-014710 are only some of the indicators of the human body, estimates based on hormone balance or muscle mass are not necessarily appropriate.

[0006] An object of the present invention is to more appropriately estimate skin conditions and factors that define the skin conditions. [Means for solving the problem]

[0007] One aspect of the present invention is acquiring mental and physical data relating to the body and mind of a subject of skin condition estimation; estimating the skin condition of the subject using a skin model that describes a correlation between the psychosomatic data and the skin condition; The physical and mental data includes at least one of liver function-related variables, muscle and bone-related variables, heart rate and blood pressure-related variables, blood oxygenation-related variables, blood count-related variables, lipid metabolism-related variables, autonomic nervous function-related variables, personal attribute-related variables, kidney function-related variables, body composition-related variables, glucose tolerance-related variables, electrolyte-related variables, cognitive function-related variables, immunometabolism-related variables, and depression, fatigue, and sleepiness-related variables. A method for estimating skin condition. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a configuration of an information processing system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a functional block diagram of the information processing system of FIG. 1. [Figure 3] FIG. 1 is an explanatory diagram of an overview of the present embodiment. [Figure 4] FIG. 2 is a diagram showing a data structure of a subject database according to the present embodiment. [Figure 5] FIG. 2 is a diagram illustrating a data structure of an estimated log database according to the present embodiment. [Figure 6] FIG. 2 is a schematic diagram illustrating the configuration of a skin model according to the present embodiment. [Figure 7] FIG. 2 is a sequence diagram of information processing according to the present embodiment. [Figure 8] 8A and 8B are diagrams showing examples of screens displayed in the information processing of FIG. 7. [Figure 9] FIG. 10 is an explanatory diagram of an overview of Modification 1. [Figure 10] FIG. 10 is a sequence diagram of information processing according to the first modification. [Figure 11] FIG. 10 is an explanatory diagram of an overview of Modification 2. [Figure 12] FIG. 10 is a sequence diagram of information processing according to the second modification. [Figure 13] FIG. 10 is an explanatory diagram of an overview of Modification 3. [Figure 14] FIG. 13 is a schematic diagram showing the configuration of a first skin model of Modification 3. [Figure 15] FIG. 10 is a schematic diagram showing the configuration of a second skin model of Modification 3. [Figure 16] FIG. 11 is a sequence diagram of information processing according to Modification 3. [Figure 17] 17A and 17B are diagrams showing examples of screens displayed in the information processing of FIG. 16. [Figure 18] FIG. 10 is an explanatory diagram of an overview of Modification 4. [Figure 19] FIG. 13 is a sequence diagram of information processing in Modification 4. [Figure 20] FIG. 10 is an explanatory diagram of an overview of Modification 5. [Figure 21] FIG. 13 is a sequence diagram of information processing according to the fifth modification. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In the drawings for explaining the embodiment, the same components are generally designated by the same reference numerals, and repeated description thereof will be omitted.

[0010] (1) Information processing system configuration The configuration of the information processing system will be described below. Fig. 1 is a block diagram showing the configuration of the information processing system of this embodiment. Fig. 2 is a functional block diagram of the information processing system of Fig. 1.

[0011] As shown in FIG. 1, the information processing system 1 includes a client device 10 and a server 30. The client device 10 and the server 30 are connected via a network (for example, the Internet or an intranet) NW.

[0012] The client device 10 is a computer (an example of an "information processing device") that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer.

[0013] The server 30 is a computer (an example of an "information processing device") that provides the client device 10 with a response in response to a request sent from the client device 10. The server 30 is, for example, a web server.

[0014] (1-1) Client device configuration The configuration of the client device 10 will be described.

[0015] As shown in FIG. 2, the client device 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14.

[0016] The storage device 11 is configured to store programs and data, and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage (for example, a flash memory or a hard disk).

[0017] The programs include, for example, the following programs: OS (Operating System) programs Applications that process information (e.g., web browsers)

[0018] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)

[0019] The processor 12 is configured to realize the functions of the client device 10 by running a program stored in the storage device 11. The processor 12 is, for example, a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

[0020] The input / output interface 13 is configured to receive user instructions from an input device connected to the client device 10 and to output information to an output device connected to the client device 10 . The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display.

[0021] The communication interface 14 is configured to control communication between the client device 10 and the server 30 .

[0022] (1-2) Server configuration The configuration of the server 30 will be described.

[0023] As shown in FIG. 2, the server 30 includes a storage device 31, a processor 32, an input / output interface 33, and a communication interface .

[0024] The storage device 31 is configured to store programs and data, and is, for example, a combination of ROM, RAM, and storage (for example, flash memory or a hard disk).

[0025] The programs include, for example, the following programs: OS programs Application programs that perform information processing

[0026] The data includes, for example, the following data: Databases referenced in information processing - Results of information processing

[0027] The processor 32 is configured to implement the functions of the server 30 by running a program stored in the storage device 31. The processor 32 is, for example, a CPU, an ASIC, an FPGA, or a combination thereof.

[0028] The input / output interface 33 is configured to receive user instructions from an input device connected to the server 30 and to output information to an output device connected to the server 30 . The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display.

[0029] The communication interface 34 is configured to control communication between the server 30 and the client device 10 .

[0030] (2) Overview of the embodiment An outline of this embodiment will be explained below with reference to Fig. 3, which is an explanatory diagram of the outline of this embodiment.

[0031] As shown in FIG. 3, the skin model M of this embodiment describes the correlation between the mind-body data X and the skin condition Y. When the subject's mental and physical data X is given to the skin model M, the skin condition Y is estimated according to the mental and physical data X. The estimated skin condition Y is presented to the subject.

[0032] (3) Database The data structure of the database of this embodiment will be described.

[0033] (3-1) Target database The data structure of the subject database of this embodiment will be described below: Fig. 4 is a diagram showing the data structure of the subject database of this embodiment.

[0034] As shown in Fig. 4, subject information is stored in the subject database. The subject information is information about subjects. The subject database includes a "subject ID" field, a "subject name" field, and a "subject attribute" field. Each field is associated with another.

[0035] The "Subject ID" field stores subject identification information. The subject identification information is information that identifies the subject.

[0036] The "subject name" field stores subject name information. The subject name information is information about the subject's name.

[0037] The "subject attribute" field stores subject attribute information. The subject attribute information is information about the subject's attributes (an example of "mental and physical data"). The "subject attribute" field includes a "gender" field and a "date of birth" field.

[0038] The "gender" field stores gender information, which is information about the gender of the subject.

[0039] The "Date of Birth" field stores date of birth information. The date of birth information is information related to the subject's date of birth. Based on the combination of the date of birth information and the date of execution of the information processing, the subject's age on the date of execution of the information processing can be determined.

[0040] (3-2) Estimated log database The data structure of the estimated log database of this embodiment will be described below with reference to Fig. 5, which is a diagram showing the data structure of the estimated log database of this embodiment.

[0041] As shown in Fig. 5, the estimation log database stores estimation log information. The estimation log information is information relating to the history of estimation results of the subject's skin condition. The estimated log database includes an "estimated log ID" field, an "estimated date and time" field, an "estimated result" field, and an "advice" field. Each field is associated with another. The inferred log database is associated with subject identification information.

[0042] The "estimated log ID" field stores estimated log identification information. The estimated log identification information is information for identifying the history of the estimation result. The "Estimated Date and Time" field stores estimated date and time information. The estimated date and time information is information about the date and time when the estimation was performed.

[0043] The "estimation result" field stores estimation result information. The estimation result information is information related to the estimation result of the skin condition. The "estimation result" field includes multiple skin index fields. The skin index fields include, for example, the following: "Moisture" field: The estimated skin moisture content is stored. "Barrier strength" field: The estimated skin barrier strength is stored. "Brightness" field: The estimated skin brightness is stored. "Yellowness" field: The estimated yellowness of the skin is stored. "Firmness" field: The estimated skin firmness is stored. "Melanin" field (not shown): The estimated skin melanin is stored. "Hemoglobin" field (not shown): The estimated skin hemoglobin content is stored. "Vividness" field (not shown): Stores the estimated skin vibrancy. "Redness" field (not shown): Stores the estimated skin redness. "Texture" field (not shown): The estimated skin texture is stored. "Wrinkles" field (not shown): Stores the estimated results of skin wrinkles. "Blemish" field (not shown): Stores the estimated skin blemishes.

[0044] The "advice" field stores advice information. The advice information is advice provided to the subject and is determined based on the skin condition estimation result.

[0045] (4) Skin model The skin model of this embodiment will be described.

[0046] (4-1) Skin model configuration The configuration of the skin model will now be described. Fig. 6 is a schematic diagram showing the configuration of the skin model of this embodiment.

[0047] 6, a skin model Mi is generated for each index of a skin condition (hereinafter referred to as a “skin index”). The skin model Mi is stored in the storage device 31. Skin indices are classified into the following skin index groups, for example: Skin texture index group (hereinafter referred to as "texture index group") Skin structure indicator group (hereinafter referred to as "Structural indicator group") Skin Color Indicator Group (hereinafter referred to as "Color Indicator Group")

[0048] The texture index group includes, for example, the following indexes: - Skin moisture index (hereinafter referred to as "moisture-related index") - Indicators related to skin surface morphology (hereinafter referred to as "surface morphology-related indices")

[0049] The moisture-related indexes include, for example, the following indexes: Skin moisture -Skin barrier strength

[0050] Surface morphology-related indices include, for example, skin texture.

[0051] The structural indicator group includes, for example, the following indicators: - Skin elasticity index (hereinafter referred to as "elasticity-related index") - Skin wrinkle-related index (hereinafter referred to as "wrinkle-related index")

[0052] Elasticity-related indices include, for example, skin firmness.

[0053] Wrinkle-related indices include, for example, skin wrinkles.

[0054] The color index group includes, for example, the following indexes: Skin color-related indicators (hereinafter referred to as "skin color-related indicators") - Indicators related to spots (hereinafter referred to as "spot-related indicators")

[0055] Skin color-related indices include, for example, the following indices: Melanin in the skin Hemoglobin in the skin Brightening skin · Skin Vibrancy · Redness of the skin Yellowish skin

[0056] The blemish-related indicators include, for example, skin blemishes.

[0057] As shown in FIG. 6, the skin model Mi defines explanatory variables Xij, influence levels Kij, and objective variables Yi. The argument i (i is a natural number) is an identifier of the skin index. The argument j (j is a natural number) is an identifier of a variable related to the mind-body data.

[0058] The explanatory variables Xij are variables related to the physical and mental data.

[0059] The influence level Kij is a parameter of a variable related to the physical and mental data, and indicates the degree of influence that the physical and mental data has on the skin condition.

[0060] The objective variable Yi is the skin condition. The skin condition is expressed in at least one of the following forms, for example: Numbers ·level ·Classification

[0061] (4-2) Mental and physical data The mind-body data of this embodiment will be described.

[0062] Mind-body data is data relating to the human body and mind. Variables related to mind-body data are classified into one of the following related variables: Related variables are a set of variables related to mind-body data. Liver function-related variables Muscle-bone related variables Heart rate and blood pressure related variables Blood oxygenation-related variables Blood count-related variables Lipid metabolism-related variables Autonomic nervous function-related variables Personal attribute-related variables Renal function-related variables Body composition-related variables Glucose tolerance-related variables Electrolyte-related variables Cognitive function-related variables Immunometabolic variables Depression, fatigue, and sleepiness-related variables

[0063] The liver function-related variable is a variable related to liver function. The liver function-related variable is preferably ALT (GPT) in the blood AST (GOT) in the blood ALP in the blood γ-GTP in the blood Indirect bilirubin in the blood Total bilirubin in the blood Direct bilirubin in the blood Includes:

[0064] The muscle-bone related variables are variables related to the muscle and bone. The muscle-bone related variables are preferably Grip strength ·Bone density Includes:

[0065] The heart rate / blood pressure related variables are variables related to heart rate and blood pressure. The heart rate / blood pressure related variables are preferably: Diastolic blood pressure Systolic blood pressure Heart Rate (HR) Includes:

[0066] The blood oxygenation related variable is a variable related to blood oxygenation. The blood oxygenation related variable is preferably Blood antioxidant potential (BAP: Biological Antioxidant Potential) Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Oxidation Stress Index (OSI) Includes:

[0067] The blood count-related variable is a variable related to blood count. The blood count-related variable is preferably Blood hematocrit Hemoglobin in the blood Platelets in the blood Red blood cells in the blood White blood cells in the blood ·Mean red blood cell hemoglobin concentration in blood Mean corpuscular hemoglobin in blood ·Mean corpuscular volume of blood Includes:

[0068] The lipid metabolism-related variable is a variable related to lipid metabolism. The lipid metabolism-related variable is preferably -HDL cholesterol in the blood LDL cholesterol in the blood The ratio of LDL cholesterol to HDL cholesterol in the blood Total blood cholesterol ·Blood triglycerides Includes:

[0069] The autonomic nervous function-related variable is a variable related to autonomic nervous function. The autonomic nervous function-related variable is preferably Autonomic nervous index HF (high frequency component of the power spectrum in the time series fluctuation of heartbeat intervals) Autonomic nervous index LF (low frequency component of the power spectrum in the time series fluctuation of heartbeat intervals) Ratio of autonomic nervous index HF to autonomic nervous index LF Includes:

[0070] The person attribute related variable is a variable related to a person attribute. The person attribute related variable is preferably Exercise habits (for example, average number of steps per day) Sleep time value Duration of fatigue Average working hours Medical history Smoking experience Regularly taken medications Marital history Includes:

[0071] The renal function-related variable is a variable related to renal function. The renal function-related variable is preferably Glomerular filtration rate (eGFR) Blood urea nitrogen Includes:

[0072] The body composition related variables are variables related to body composition. The body composition related variables are preferably: BMI (Body Mass Index) Muscle mass ·height ·Body fat percentage ·body weight Skeletal muscle mass Includes:

[0073] The glucose tolerance-related variable is a variable related to glucose tolerance. The glucose tolerance-related variable is preferably Blood hemoglobin A1c (HbA1c) Blood sugar Includes:

[0074] The electrolyte-related variable is a variable related to an electrolyte. The electrolyte-related variable is preferably: Blood potassium Crawl in the blood Blood sodium Blood sodium to blood potassium ratio Includes:

[0075] The cognitive function-related variable is a variable related to cognitive function and is obtained by the performance on a cognitive function test. The cognitive function-related variable is preferably Reaction time for cognitive tasks Correct answer rate for cognitive tasks - Error rate in cognitive tasks Number of cognitive tasks completed Includes:

[0076] The immunometabolism-related variable is a variable related to immunometabolism. The immunometabolism-related variable is preferably High-sensitivity CRP (C-reactive protein) in the blood Blood amylase Albumin in the blood Creatine kinase in the blood Blood cortisol Total blood protein Lactate dehydrogenase in the blood ·Uric acid in the blood Blood IgE IgG in the blood IgA in the blood Includes:

[0077] The depression-fatigue-sleepiness related variables are variables related to depression, fatigue, and sleepiness, and are variables obtained by questionnaire survey. The depression-fatigue-sleepiness related variables are preferably: Fatigue Assessment Scale Depression and anxiety assessment scale Motivation scale Sleepiness rating scale Life Performance Status Rating Scale Includes:

[0078] (4-3) Skin model generation method A method for generating a skin model according to this embodiment will now be described.

[0079] In this embodiment, a skin model is generated using a combination of psychosomatic data and skin conditions of a plurality of subjects as training data, for example, by using one of the following methods. Examples include simple regression analysis, multiple regression analysis, Elastic NET, PLS (Partial Least Squares), neural networks, and DNN (Deep Neural Network).

[0080] (4-4) Example of skin model A specific example of the skin model of this embodiment will be described.

[0081] (4-4-1) Specific examples of skin models in texture index groups A specific example of the skin model of the texture index group of this embodiment will be described.

[0082] As an example of a skin model for moisture-related indices in the texture index group, a skin model M1 for estimating a skin index "skin moisture" Y1 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale ·body weight BMI: Body Mass Index ·Body fat percentage ·Exercise habits Duration of fatigue ·Uric acid in the blood Blood cortisol Reaction time for cognitive tasks Blood potassium Blood sodium Heart rate (HR) LDL cholesterol in the blood ·Blood triglycerides Red blood cells in the blood White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Blood antioxidant potential (BAP: Biological Antioxidant Potential) Oxidation Stress Index (OSI) Total bilirubin in the blood Indirect bilirubin in the blood Blood hematocrit Grip strength Blood IgA (Immunoglobulin A) Blood hemoglobin A1c (HbA1c)

[0083] As an example, the skin index "skin moisture" Y1 is affected by each variable as follows: Blood hematocrit shows a positive correlation with the skin index "skin moisture" Y1 (i.e., the higher the blood hematocrit, the better the skin index "skin moisture" Y1). The fatigue assessment scale shows a negative correlation with the skin index "skin moisture" Y1 (i.e., the higher the fatigue, the worse the skin index "skin moisture" Y1). The depression and anxiety assessment scale shows a negative correlation with the skin index "skin moisture" Y1 (i.e., the stronger the depression and anxiety, the worse the skin index "skin moisture" Y1).

[0084] The skin model M2 for estimating the skin index "skin barrier strength" Y2, a moisture-related index in the texture index group, includes, for example, at least one of the following variables: Here, barrier strength refers to an index that represents the strength of the skin's moisturizing function, such as the reciprocal of trans-epidermal water loss. Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale Muscle mass ·Exercise habits Duration of fatigue ·Uric acid in the blood Reaction time for cognitive tasks Blood potassium Blood hemoglobin A1c (HbA1c) Blood sugar Systolic blood pressure White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Blood antioxidant potential (BAP: Biological Antioxidant Potential) Oxidation Stress Index (OSI) γ-GTP in the blood Direct bilirubin in the blood Crawl in the blood ALT (GPT) in the blood

[0085] As an example, the skin index "skin barrier strength" Y2 is affected by each variable as follows: The fatigue assessment scale shows a negative correlation with the skin index "skin barrier strength" Y2 (i.e., the stronger the fatigue, the weaker the "skin barrier strength" Y2). - Depression / anxiety assessment scale shows a negative correlation with the skin index "skin barrier strength" Y2 (i.e., the stronger the depression / anxiety, the weaker the "skin barrier strength" Y2).

[0086] As an example of a skin model of a surface morphology-related index in the texture index group, a skin model M3 for estimating a skin index "skin texture" Y3 includes, for example, at least one of the following variables: ·body weight Lactate dehydrogenase in the blood Blood amylase Autonomic nervous index LF ·Mean corpuscular volume of blood Platelets in the blood ALT (GPT) in the blood ALP in the blood Blood sodium to blood potassium ratio Blood IgE The ratio of LDL cholesterol to HDL cholesterol in the blood Skeletal muscle mass

[0087] (4-4-2) Specific examples of skin models of structural index groups A specific example of the skin model of the structure indicator group of this embodiment will be described.

[0088] As an example of a skin model for elasticity-related indices in the structure index group, a skin model M4 for estimating a skin index "skin firmness" Y4 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale ·body weight Muscle mass Sleep time value ·Exercise habits Lactate dehydrogenase in the blood Blood hemoglobin A1c (HbA1c) Blood sugar Systolic blood pressure Glomerular filtration rate (eGFR) Ratio of autonomic nervous index HF to autonomic nervous index LF Hemoglobin in the blood Blood hematocrit White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) AST (GOT) in the blood Direct bilirubin in the blood Grip strength ALP in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) ·Body fat percentage

[0089] As an example, the skin index "skin firmness" Y4 is affected by each variable as follows: - AST in the blood shows a positive correlation with the skin index "skin firmness" Y4 (i.e., the higher the AST in the blood, the better the skin index "skin firmness" Y4). - The fatigue assessment scale shows a positive correlation with the skin index "skin firmness" Y4 (i.e., the higher the fatigue, the better the skin index "skin firmness" Y4). - Depression / Anxiety Assessment Scale: Shows a positive correlation with the skin index "skin firmness" Y4 (i.e., the higher the depression / anxiety, the better the skin index "skin firmness" Y4).

[0090] As an example of a skin model of a structure-related index of the structure index group, a skin model M5 for estimating a skin index "skin wrinkles" Y5 includes, for example, at least one of the following variables: ·body weight Systolic blood pressure Average working hours

[0091] (4-4-3) Specific examples of skin models in color index groups A specific example of the skin model of the color index group of this embodiment will be described.

[0092] As an example of a skin model for a skin color-related index in the color index group, a skin model M6 for estimating a skin index "skin melanin" Y6 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale ·body weight ·Exercise habits ·Uric acid in the blood Reaction time for cognitive tasks Blood potassium Blood hemoglobin A1c (HbA1c) Blood sugar Autonomic nervous index HF Hemoglobin in the blood Blood hematocrit Mean corpuscular hemoglobin in blood ·Mean red blood cell hemoglobin concentration in blood White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) AST (GOT) in the blood γ-GTP in the blood ALT (GPT) in the blood Total bilirubin in the blood Direct bilirubin in the blood Autonomic nervous index HF / LF ratio Red blood cells in the blood

[0093] As an example of a skin model for a skin color-related index in the color index group, a skin model M7 for estimating a skin index "skin hemoglobin" Y7 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale BMI: Body Mass Index ·Body fat percentage ·Exercise habits Duration of fatigue Reaction time for cognitive tasks Blood potassium Blood sugar Systolic blood pressure Total blood cholesterol ·Blood triglycerides Blood hematocrit ·Mean corpuscular volume of blood White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Blood antioxidant potential (BAP: Biological Antioxidant Potential) Oxidation Stress Index (OSI) γ-GTP in the blood Direct bilirubin in the blood

[0094] As an example of a skin model for a skin color-related index in the color index group, a skin model M8 for estimating a skin index "skin brightness" Y8 includes, for example, at least one of the following variables: Motivation scale ·body weight Muscle mass BMI: Body Mass Index ·Body fat percentage Sleep time value Average working hours ·Exercise habits Lactate dehydrogenase in the blood ·Uric acid in the blood High-sensitivity CRP (C-reactive protein) in the blood Reaction time for cognitive tasks Blood potassium Systolic blood pressure Diastolic blood pressure Glomerular filtration rate (eGFR) Blood urea nitrogen Ratio of autonomic nervous index HF to autonomic nervous index LF -HDL cholesterol in the blood LDL cholesterol in the blood Total blood cholesterol ·Blood triglycerides ·Mean red blood cell hemoglobin concentration in blood White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Blood antioxidant potential (BAP: Biological Antioxidant Potential) Oxidation Stress Index (OSI) Grip strength

[0095] As an example, the skin index "skin brightness" Y8 is affected by each variable as follows: Blood hematocrit shows a negative correlation with the skin index "skin brightness" Y8 (i.e., the higher the blood hematocrit, the worse the skin index "skin brightness" Y8).

[0096] As an example of a skin model for a skin color-related index in the color index group, a skin model M9 for estimating a skin index "skin vividness" Y9 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale ·Exercise habits Duration of fatigue ·Uric acid in the blood Reaction time for cognitive tasks Blood potassium Blood hemoglobin A1c (HbA1c) Blood sugar Hemoglobin in the blood Blood hematocrit White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) AST (GOT) in the blood γ-GTP in the blood ALT (GPT) in the blood Direct bilirubin in the blood

[0097] As an example of a skin model for a skin color-related index in the color index group, a skin model M10 for estimating a skin index "skin redness" Y10 includes, for example, at least one of the following variables: Fatigue Assessment Scale Sleepiness rating scale Depression and anxiety assessment scale ·Body fat percentage ·Exercise habits Duration of fatigue ·Uric acid in the blood Reaction time for cognitive tasks Blood potassium Blood hemoglobin A1c (HbA1c) Blood sugar Systolic blood pressure Blood hematocrit White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Blood antioxidant potential (BAP: Biological Antioxidant Potential) Oxidation Stress Index (OSI) γ-GTP in the blood ALT (GPT) in the blood Direct bilirubin in the blood AST (GOT) in the blood

[0098] As an example, the skin index "skin redness" Y10 is affected by each variable as follows: - ALT in the blood shows a positive correlation with the skin index "skin redness" Y10 (i.e., the higher the ALT in the blood, the better the skin index "skin redness" Y10). The fatigue assessment scale shows a positive correlation with the skin index "skin redness" Y10 (i.e., the stronger the fatigue, the better the skin index "skin redness" Y10). - It shows a positive correlation with the depression / anxiety assessment scale skin index "skin redness" Y10 (in other words, the stronger the depression / anxiety, the better the skin index "skin redness" Y10).

[0099] As an example of a skin model for a skin color-related index in the color index group, a skin model M11 for estimating a skin index "yellowishness of skin" Y11 includes, for example, at least one of the following variables: ·body weight BMI: Body Mass Index ·Body fat percentage ·Exercise habits Grip strength Total blood protein ·Uric acid in the blood High-sensitivity CRP (C-reactive protein) in the blood Albumin in the blood Reaction time for cognitive tasks Blood potassium Blood hemoglobin A1c (HbA1c) Systolic blood pressure Diastolic blood pressure Autonomic nervous index HF LDL cholesterol in the blood Total blood cholesterol ·Blood triglycerides Hemoglobin in the blood Mean corpuscular hemoglobin in blood ·Mean red blood cell hemoglobin concentration in blood Red blood cells in the blood White blood cells in the blood Platelets in the blood Blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) Oxidation Stress Index (OSI) AST (GOT) in the blood γ-GTP in the blood ALT (GPT) in the blood Total bilirubin in the blood Direct bilirubin in the blood Indirect bilirubin in the blood Blood hematocrit

[0100] As an example, the skin index "yellowness of skin" Y11 is affected by each variable as follows: - ALT in the blood shows a positive correlation with the skin index "yellowness of the skin" Y11 (i.e., the higher the ALT in the blood, the better the skin index "yellowness of the skin" Y11). - AST in the blood shows a positive correlation with the skin index "yellowness of the skin" Y11 (i.e., the higher the AST in the blood, the better the skin index "yellowness of the skin" Y11). Blood hematocrit shows a negative correlation with the skin index "yellowness of the skin" Y11 (i.e., the higher the blood hematocrit, the worse the skin index "yellowness of the skin" Y11).

[0101] As an example of a skin model for a skin color-related index in the color index group, a skin model M12 for estimating a skin index "skin blemishes" Y12 includes, for example, at least one of the following variables: Sleepiness rating scale BMI: Body Mass Index Creatine kinase in the blood High-sensitivity CRP (C-reactive protein) in the blood Blood amylase Reaction time for cognitive tasks Diastolic blood pressure -HDL cholesterol in the blood Red blood cells in the blood IgG in the blood

[0102] For example, in the case of moisture-related indices (for example, the skin index "skin moisture" Y1 and the skin index "skin barrier strength" Y2), the following can be listed as highly influential variables.

[0103] For the skin index "skin moisture" Y1, BMI (Body Mass Index), blood antioxidant value, body fat percentage, blood hematocrit, sleepiness assessment scale, blood IgA, blood potassium, blood hemoglobin A1c (HbA1c), fatigue assessment scale, and blood cortisol have a high influence. It is preferable that the skin model M1 includes one or more of BMI (Body Mass Index), blood antioxidant value, body fat percentage, blood hematocrit, sleepiness assessment scale, blood IgA, blood potassium, blood hemoglobin A1c (HbA1c), fatigue assessment scale, and blood cortisol.

[0104] For the skin index "skin barrier strength" Y2, blood chloride, blood ALT (GPT), blood hemoglobin A1c (HbA1c), blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites), blood γ-GTP, blood platelets, blood glucose, and the sleepiness assessment scale have a high degree of influence. It is preferable that the skin model M2 includes one or more of blood chloride, blood ALT (GPT), blood hemoglobin A1c (HbA1c), blood oxidative stress level (d-ROMs: Reactive oxygen metabolites), blood γ-GTP, blood platelets, blood glucose, and a sleepiness assessment scale.

[0105] For example, in the case of surface morphology-related indices (for example, the skin index "skin texture" Y3), the following can be listed as highly influential variables:

[0106] In the skin index "skin texture" Y3, the influence of IgE in the blood, the ratio of sodium to potassium in the blood, the autonomic nervous index LF, and ALP in the blood is high. The skin model M3 preferably contains one or more of IgE in the blood, the ratio of sodium to potassium in the blood, the autonomic nervous index LF, and ALP in the blood.

[0107] For example, in the case of elasticity-related indices (for example, the skin index "skin firmness" Y4), the following can be listed as highly influential variables:

[0108] For the skin index "skin firmness" Y4, the blood oxidative stress level (d-ROMs: reactive oxygen metabolites), blood direct bilirubin, blood AST (GOT), blood ALP, blood lactate dehydrogenase, blood oxidative stress level (d-ROMs: reactive oxygen metabolites), body fat percentage, autonomic nervous system index HF / LF ratio, blood blood glucose, blood white blood cells, and grip strength have a high influence. It is preferable that the skin model M4 includes one or more of the following: blood oxidative stress level (d-ROMs: Reactive oxygen metabolites), blood direct bilirubin, blood AST (GOT), blood ALP, blood lactate dehydrogenase, blood oxidative stress level (d-ROMs: Reactive oxygen metabolites), body fat percentage, the ratio of autonomic nervous index HF to LF, blood blood glucose, blood white blood cells, and grip strength.

[0109] For example, for skin color-related indices (for example, skin index "skin melanin" Y6, skin index "skin brightness" Y8, and skin index "skin redness" Y10), the following can be listed as highly influential variables:

[0110] In the skin index "skin melanin" Y6, the autonomic nervous system index HF / LF ratio, depression / anxiety assessment scale, sleepiness assessment scale, blood uric acid, blood glucose, blood total bilirubin, blood ALT (GPT), blood white blood cells, blood red blood cells, and blood oxidative stress levels (d-ROMs: Reactive oxygen metabolites) have a high degree of influence. It is preferable that the skin model M4 includes one or more of the following: the ratio of autonomic nervous indices HF and LF, a depression / anxiety assessment scale, a sleepiness assessment scale, uric acid in the blood, blood glucose, total bilirubin in the blood, ALT (GPT) in the blood, white blood cells in the blood, red blood cells in the blood, and oxidative stress levels in the blood (d-ROMs: Reactive oxygen metabolites).

[0111] For the skin index "skin brightness" Y8, BMI (Body Mass Index), blood white blood cells, blood urea nitrogen, blood uric acid, body fat percentage, blood platelets, systolic blood pressure, blood triglycerides, blood potassium, and the motivation assessment scale have a high influence. It is preferable that model M8 includes one or more of BMI (Body Mass Index), blood white blood cells, blood urea nitrogen, blood uric acid, body fat percentage, blood platelets, systolic blood pressure, blood triglycerides, blood potassium, and a motivation assessment scale.

[0112] For the skin index "skin redness" Y10, the body fat percentage, fatigue assessment scale, blood white blood cells, depression / anxiety assessment scale, blood AST (GOT), blood hematocrit, blood platelets, blood oxidative stress level (d-ROMs: Reactive oxygen metabolites), blood uric acid, and drowsiness assessment scale have a high degree of influence.

[0113] Furthermore, it is preferable that each skin model uses an index that can be obtained non-invasively, or an index that can be obtained through a medical examination or the like. Indices that can be obtained non-invasively are not particularly limited as long as they can generally be obtained non-invasively, and examples include BMI (Body Mass Index), sleep assessment scale, fatigue assessment scale, grip strength, body fat percentage, depression / anxiety assessment scale, motivation assessment scale, and systolic blood pressure. Indicators that can be obtained through health checkups, etc. are not particularly limited as long as they can be obtained through general health checkups, comprehensive medical examinations, etc., and include blood antioxidant potential (BAP: Biological Antioxidant Potential), blood hematocrit, blood oxidative stress level (d-ROMs: Reactive oxygen metabolites), blood potassium, blood hemoglobin, blood cortisol, blood IgE, autonomic nervous index LF, and the ratio of autonomic nervous index HF to LF.

[0114] (5) Information processing The information processing of this embodiment will be described below. Fig. 7 is a sequence diagram of the information processing of this embodiment. Fig. 8 is a diagram showing an example of a screen displayed in the information processing of Fig. 7.

[0115] The process in FIG. 7 is triggered when a user logs in to the skin condition estimation service provided by the server 30 using user identification information.

[0116] As shown in FIG. 7, the client device 10 executes an estimation request (S1110). Specifically, the processor 12 displays a screen P1110 (FIG. 8) on the display. The screen P1110 includes an operation object B1110 and a field object F1110. The operation object B1110 is an object that receives a user instruction to confirm an input to the field object F1110. The field object F1110 is an object that accepts input of physical and mental data.

[0117] When the user inputs physical and mental data into the field object F1110 and operates the operation object B1110, the processor 12 transmits estimated request data to the server 30. The estimated request data includes, for example, the following information: ·Physical data entered in field object F1110

[0118] After step S1110, the server 30 performs skin condition estimation (S1130). Specifically, the processor 32 provides the psychosomatic data X included in the estimation request data to the skin model M, and estimates the skin condition Y corresponding to the psychosomatic data X.

[0119] More specifically, the processor 32 estimates the skin condition Y1 of the skin index "skin moisture" by providing the mind-body data X included in the estimation request data to the skin model M1. The processor 32 estimates the skin condition Y2 of the skin index "barrier strength" by providing the mind-body data X included in the estimation request data to the skin model M2. The processor 32 estimates the skin condition Y3 of the skin index "skin texture" by providing the mind-body data X included in the estimation request data to the skin model M3. The processor 32 estimates the skin condition Y4 of the skin index "skin firmness" by providing the mind-body data X included in the estimation request data to the skin model M4. The processor 32 estimates the skin condition Y5 of the skin index "skin wrinkles" by providing the mind-body data X included in the estimation request data to the skin model M5. The processor 32 estimates the skin condition Y6 of the skin index "skin melanin" by providing the mind-body data X included in the estimation request data to the skin model M6. The processor 32 estimates the skin condition Y7 of the skin index "skin hemoglobin" by providing the mind-body data X included in the estimation request data to the skin model M7. The processor 32 estimates the skin condition Y8 of the skin index "skin brightness" by providing the mind-body data X included in the estimation request data to the skin model M8. The processor 32 estimates the skin condition Y9 of the skin index "skin vividness" by providing the mind-body data X included in the estimation request data to the skin model M9. The processor 32 estimates the skin condition Y10 of the skin index "skin redness" by providing the mind-body data X included in the estimation request data to the skin model M10. The processor 32 estimates the skin condition Y11 of the skin index "yellowish skin" by providing the psychosomatic data X included in the estimation request data to the skin model M11. The processor 32 estimates the skin condition Y12 of the skin index "skin blemishes" by providing the mind-body data X included in the estimation request data to the skin model M12.

[0120] After step S1130, the server 30 generates advice (S1131). Specifically, an advice model is stored in the storage device 31. The advice model describes the correlation between skin conditions and advice. Processor 32 inputs the skin condition estimation result obtained in step S1130 into the advice model, thereby generating advice according to the skin condition estimation result.

[0121] After step S1131, the server 30 updates the database (S1132). Specifically, the processor 32 adds a new record to the estimated log database (FIG. 5) associated with the target person identification information used to log in. The following information is stored in each field of the new record. "Estimated Log ID" field: New estimated log identification information "Estimated date and time" field: Information about the execution date and time of step S1130 "Estimation result" field: Estimation result information obtained in step S1130 "Advice" field: Advice information obtained in step S1131

[0122] After step S1132, the server 30 executes an estimated response (S1133). Specifically, the processor 32 transmits the estimated response data to the client device 10. The estimated response data includes, for example, the following information: The skin condition estimation result obtained in step S1130 Advice obtained in step S1131

[0123] After step S1133, the client device 10 outputs the estimation result (S1111). Specifically, the processor 12 displays a screen P1111 (FIG. 8) on the display. The screen P1111 includes display objects A1111a to A1111b.

[0124] Display object A1111a displays the skin condition estimation result included in the estimated response data.

[0125] Display object A1111b displays advice included in the estimated response data.

[0126] (6) Summary of this embodiment According to this embodiment, by providing a subject's psychosomatic data to a model that describes the correlation between the psychosomatic data and the skin condition, the skin condition corresponding to the subject's psychosomatic data can be estimated, thereby enabling more appropriate estimation of the skin condition and the factors that determine the skin condition.

[0127] According to this embodiment, the degree of influence between the mind-body data and the skin index may be defined for each combination of the mind-body data and the skin index, thereby enabling more appropriate estimation of the skin condition and the factors that determine the skin condition.

[0128] According to this embodiment, advice may be output according to the estimated skin condition, thereby providing the subject with information useful for improving their skin condition.

[0129] (7) Variations A modification of this embodiment will now be described.

[0130] (7-1) Variation 1 A description will be given of Modification 1. Modification 1 is an example in which a skin model in which the influence of human attributes is reduced is used.

[0131] For example, it can be said that the barrier function of men's cheek skin is weaker than that of women, it contains more oil than women, and it is less elastic than women. This may be due to the difference in the amount of male and female hormone secretion.

[0132] For example, as we age, our skin may develop wrinkles, lose elasticity, and lose moisture content because senescent cells formed within the skin as we age impair the function of surrounding cells, causing age-related changes in the skin.

[0133] In this way, there is a correlation between a person's attributes and their skin condition. If a person's attributes are taken into excessive consideration, the estimation result of the skin condition will be excessively influenced by the attributes in cases where the skin condition is actually determined by factors other than the attributes. Therefore, corrections that take into account the attributes of the subjects may be necessary.

[0134] (7-1-1) Overview of Modification 1 An outline of Modification 1 will be described below. Fig. 9 is an explanatory diagram of an outline of Modification 1.

[0135] As shown in FIG. 9, the skin model N of the first modification is obtained by adjusting the influence of the skin model M of the present embodiment in consideration of human attributes. When the subject's physical and mental data X (including the subject's attributes) is given to the skin model N, a skin condition Y corresponding to the physical and mental data X is estimated so that the influence of the subject's attributes is not excessively expressed (for example, at least one of the influence of deterioration due to aging and the influence of deterioration due to gender is excluded). The estimated skin condition Y is presented to the subject.

[0136] (7-1-2) Information processing of variation 1 The following describes information processing in Modification 1. Fig. 10 is a sequence diagram of information processing in Modification 1.

[0137] The trigger for the process in FIG. 10 is the same as in FIG.

[0138] As shown in FIG. 10, the client device 10 executes an estimation request (S1110) in the same manner as in FIG.

[0139] After step S1110, the server 30 executes identification of target person attributes (S2130).

[0140] In a first example of step S2130, the target attribute is age. Specifically, processor 32 references the subject database (FIG. 4) to identify the date of birth information associated with the subject identification information. Processor 32 calculates the age of the subject at the time step S2130 is executed based on the date of birth information and the date and time when step S2130 is executed.

[0141] In a second example of step S2130, the target attribute is gender. Specifically, processor 32 refers to the subject database (FIG. 4) to identify gender information associated with the subject identification information.

[0142] After step S2130, the server 30 performs skin condition estimation (S2131). Specifically, the processor 32 provides the mental and physical data X included in the estimation request data and the subject attributes (at least one of age and gender) obtained in step S2130 to the skin model N, and estimates the skin condition Y according to the combination of the mental and physical data X and the subject attributes.

[0143] After step S2131, the server 30 generates advice (S1131), updates the database (S1132), and estimates a response (S1133), similar to FIG.

[0144] After step S1133, the client device 10 outputs the estimation result (S1111) in the same manner as in FIG.

[0145] (7-1-3) Summary of Modification 1 According to the first modification, the skin condition can be estimated without excessively being affected by the subject's attributes (for example, at least one of age and gender). This makes it possible to present an estimation result of the skin condition according to the subject's age. As a result, the skin condition and the factors that determine the skin condition can be more appropriately estimated.

[0146] (7-2) Variation 2 A description will be given of Modification 2. Modification 2 is an example in which a skin model in which the influence of the subject's body composition is reduced is used.

[0147] For example, obesity is known to increase water loss, delay collagen production, increase sebum secretion, and restrict lymphatic flow. Thus, there is a correlation between body composition and skin condition. Therefore, it is necessary to consider the influence of body composition, such as physique, fat mass, and BMI.

[0148] (7-2-1) Overview of Modification 2 An outline of Modification 2 will be described below. FIG. 11 is an explanatory diagram of an outline of Modification 2.

[0149] As shown in FIG. 11, in the skin model N of the second modification, the influence of the skin model M of the present embodiment is adjusted in consideration of the body composition. When the subject's physical and mental data X (including the subject's body composition) is provided to the skin model N, the skin condition Y corresponding to the physical and mental data X is estimated so that the influence of the subject's body composition is not excessively expressed (for example, the influence of deterioration due to obesity is excluded).

[0150] The body composition may be, for example, at least one of the following: Muscle mass per unit body weight ·Body fat amount Muscle mass BMI Body fat mass by body part (e.g., arms, legs, and trunk) Muscle mass by body part (e.g., arms and legs) - Moisture content by body part (arms, legs, and trunk) Skeletal muscle mass ·Basal metabolic rate ·Lean fat mass

[0151] When the subject's physical and mental data X (including the subject's body composition) is given to the skin model N, a skin condition Y is estimated according to the physical and mental data X. The estimated skin condition Y is presented to the subject.

[0152] (7-2-2) Information processing of variation 2 The following describes information processing in Modification 2. Fig. 12 is a sequence diagram of information processing in Modification 2.

[0153] The trigger for the process in FIG. 12 is the same as in FIG.

[0154] As shown in FIG. 12, the client device 10 executes an estimation request (S1110) in the same manner as in FIG.

[0155] After step S1110, the server 30 executes the calculation of the body composition (S3130). Specifically, processor 32 calculates body composition based on the physical and mental data included in the estimation request data.

[0156] After step S3130, the server 30 executes skin condition estimation (S3131). Specifically, the processor 32 provides the psychosomatic data X included in the estimation request data to the skin model N, and estimates the skin condition Y corresponding to the psychosomatic data X.

[0157] After step S3131, the server 30 generates advice (S1131), updates the database (S1132), and estimates a response (S1133), similar to FIG.

[0158] After step S1133, the client device 10 outputs the estimation result (S1111) in the same manner as in FIG.

[0159] (7-2-3) Summary of Variation 2 According to the second modification, the skin condition can be estimated without excessively being affected by the subject's body composition, thereby making it possible to further improve the skin condition and the factors that define the skin condition.

[0160] (7-3) Variation 3 A description will be given of Modification 3. Modification 3 is an example in which two types of skin models are used depending on the invasiveness of the mind-body data.

[0161] (7-3-1) Overview of Variation 3 An outline of Modification 3 will be described below. Fig. 13 is an explanatory diagram of an outline of Modification 3.

[0162] As shown in FIG. 13, the skin model of the third modification includes a first skin model MA and a second skin model MB. The first skin model MA describes the correlation between the non-invasive data XA that can be obtained by a non-invasive test and the first skin condition YA. The second skin model MB describes the correlation between the invasive data XB and non-invasive data XA that can be obtained by invasive testing and the second skin condition YB. In other words, the second skin model MB is similar to the skin model M of this embodiment. When the subject's physical and mental data X is provided to the first skin model MA, a first skin condition YA is estimated according to the non-invasive data XA of the physical and mental data X. The estimated first skin condition YA is presented to the subject. When the subject's physical and mental data X is provided to the second skin model MB, a second skin condition YB is estimated according to the physical and mental data X (i.e., the non-invasive data XA and the invasive data XB). The estimated second skin condition YB is presented to the subject.

[0163] The second skin model MB has more parameters for estimating the second skin condition YB than the first skin model MA has for estimating the first skin condition YA. Therefore, the estimation accuracy of the second skin model MB is higher than that of the first skin model MA.

[0164] (7-3-2) Skin model of variation 3 The skin model of the third modification will be described.

[0165] (7-3-2-1) Configuration of the first skin model of Modification 3 The following describes the configuration of the first skin model of Modification 3. Fig. 14 is a schematic diagram showing the configuration of the first skin model of Modification 3.

[0166] As shown in FIG. 14, the first skin model MAi is defined with an explanatory variable Xiit, an influence Kiit, and a response variable YAi. The argument t (t is a natural number) is an identifier of the physical and mental data (hereinafter referred to as "non-invasive data") collected by a non-invasive test (hereinafter referred to as "non-invasive test").

[0167] The explanatory variable Xiit is a variable related to non-invasive data.

[0168] The influence level Kiit indicates the degree of influence that non-invasive data has on skin condition.

[0169] The objective variable YAi is the skin condition.

[0170] (7-3-2-2) Configuration of the second skin model of Modification 3 The following describes the configuration of the second skin model of Modification 3. Fig. 15 is a schematic diagram showing the configuration of the second skin model of Modification 3.

[0171] As shown in FIG. 15, the second skin model MBi is defined with an explanatory variable Xiit, an influence Kiit, a response variable YBi, an explanatory variable Xinu (u is a natural number), an influence Kiiu, and a response variable YBi.

[0172] As shown in FIG. 15, the second skin model MBi is defined with an explanatory variable Xinu, an influence degree Kinu, and a response variable YBi. The argument u (u is a natural number) is an identifier of the physical and mental data (hereinafter referred to as "invasive data") collected by an invasive test (hereinafter referred to as "invasive test").

[0173] The explanatory variable Xinu is a variable related to the invasive data.

[0174] The influence level Kinu indicates the degree of influence that the invasive data has on the skin condition.

[0175] The response variable YBi is the skin condition.

[0176] (7-3-3) Information processing of variation 3 A description will be given of information processing in Modification 3. Fig. 16 is a sequence diagram of information processing in Modification 3. Fig. 17 is a diagram showing an example of a screen displayed in the information processing in Fig. 16.

[0177] The trigger for the process in FIG. 16 is the same as in FIG.

[0178] As shown in FIG. 16, the client device 10 executes an estimation request (S6110). Specifically, the processor 12 displays a screen P6110 (FIG. 17) on the display. The screen P6110 includes operation objects B6110a to B6110b and a field object F1110. The operation object B6110a is an object that confirms an input to the field object F1110 and receives a user instruction to request estimation in the first estimation mode. The first estimation mode is a mode in which estimation is performed using a first skin model. Mode identification information "MODE1" that identifies the first mode is assigned to the operation object B6110a. The operation object B6110b is an object that confirms an input to the field object F1110 and receives a user instruction to request estimation in the second estimation mode. The second estimation mode is a mode in which estimation is performed using a second skin model. Mode identification information "MODE2" that identifies the second mode is assigned to the operation object B6110b. The field object F1110 is the same as in FIG.

[0179] When the user inputs physical and mental data into the field object F1110 and operates the operation object B6110a or B6110b, the processor 12 transmits estimated request data to the server 30. The estimated request data includes, for example, the following information: ·Physical data entered in field object F1110 Mode identification information "MODE1" or "MODE2" corresponding to the operated operation object B6110a or B6110b

[0180] After step S6110, the server 30 selects a skin model (S6130). Specifically, a first skin model MAi and a second skin model MBi are stored in the storage device 31. The first skin model MAi corresponds to the mode identification information "MODE1." The second skin model MBi corresponds to the mode identification information "MODE2." The processor 32 selects the skin model (the first skin model MAi or the second skin model MBi) corresponding to the mode identification information included in the estimation request data.

[0181] After step S6130, the server 30 performs skin condition estimation (S6131). Specifically, when the first skin model MAi is selected in step S6130, the processor 32 assigns the psychosomatic data X (hereinafter referred to as "non-invasive data") that is assigned the label "non-invasive" from the psychosomatic data X included in the estimation request data to the first skin model MAi selected in step S6130, thereby estimating the first skin condition YAi corresponding to the non-invasive data. When the second skin model MBi is selected in step S6130, the processor 32 estimates the second skin condition YBi corresponding to the mind-body data X included in the estimation request data (i.e., the non-invasive data assigned the label "non-invasive" and the invasive data assigned the label "invasive") by providing the second skin model MBi selected in step S6130 with the mind-body data X.

[0182] After step S6131, the server 30 generates advice (S1131), updates the database (S1132), and estimates a response (S1133), similar to FIG.

[0183] After step S1133, the client device 10 outputs the estimation result (S1111) in the same manner as in FIG.

[0184] (7-3-4) Summary of Variation 3 According to the third modification, the determination using the first skin model MAi and the determination using the second skin model MBi are switched in response to an instruction from the subject. The first skin model MAi is configured to estimate the skin condition using non-invasive data of the subject, and therefore imposes less burden on the subject for estimating the skin condition than the second skin model MBi. The second skin model MBi is configured to estimate the skin condition using non-invasive data and invasive data of the subject, and therefore has higher estimation accuracy than the first skin model MAi. This makes it possible to provide skin condition estimation results using a skin model appropriate to the needs of the subject.

[0185] (7-4) Variation 4 A description will be given of Modification 4. Modification 4 is an example in which a skin model in which the influence of the subject's habits is reduced is used.

[0186] For example, morning and evening people have different peak body temperature rises and secretions of cortisol and melatonin from the endocrine system. They also have different circadian rhythms of blood factors.

[0187] For example, exposure to ultraviolet rays causes collagen decomposition and melanin secretion, resulting in changes in skin elasticity and color.

[0188] In this way, there is a correlation between a person's habits and their skin condition. If a person's habits are taken into excessive consideration, the estimated results of the skin condition will be excessively influenced by habits in cases where the skin condition is actually determined by factors other than habits.

[0189] (7-4-1) Overview of Variation 4 An outline of Modification 4 will be described below. Fig. 18 is an explanatory diagram of an outline of Modification 4.

[0190] As shown in FIG. 18, the skin model N of the fourth modification is obtained by adjusting the influence of the skin model M of this embodiment in consideration of human habits. When the subject's mental and physical data X and habits are input to the skin model N, a skin condition Y corresponding to the mental and physical data X is estimated so as not to excessively affect the subject's habits. The estimated skin condition Y is presented to the subject.

[0191] For example, the subject's habits include at least one of the following: Sleeping habits (e.g., morning or evening type) Lifestyle habits (for example, tendency to expose to ultraviolet rays)

[0192] (7-4-2) Information processing of variation 4 The following describes information processing in Modification 4. Fig. 19 is a sequence diagram of information processing in Modification 4.

[0193] The trigger for the process in FIG. 19 is the same as in FIG.

[0194] As shown in FIG. 19, the client device 10 executes an estimation request (S1110) in the same manner as in FIG.

[0195] After step S1110, the server 30 executes identification of the subject's habits (S7130). Specifically, subject habit information (not shown) is stored in association with subject identification information in the storage device 31. The subject habit information is information relating to the habits of the subject. The subject habit information is acquired, for example, by at least one of the following methods. Survey of the target audience -Wearable device worn by the subject - Mobile phone carried by the subject (e.g., smartphone)

[0196] The processor 32 determines subject habit information associated with the subject identification information. The processor 32 identifies the subject's habits at the time step S7130 is executed, based on the subject's habit information and the execution date and time of step S2130.

[0197] After step S7130, the server 30 executes skin condition estimation (S7131). Specifically, the processor 32 provides the mental and physical data X included in the estimation request data and the subject habit information obtained in step S7130 to the skin model N, and estimates the skin condition Y according to the combination of the mental and physical data X and the subject habit information.

[0198] After step S7131, the server 30 generates advice (S1131), updates the database (S1132), and estimates a response (S1133), similar to FIG.

[0199] After step S1133, the client device 10 outputs the estimation result (S1111) in the same manner as in FIG.

[0200] (7-4-3) Summary of Variation 4 According to the fourth modification, the skin condition can be estimated without excessively being influenced by the habits of the subject, thereby making it possible to more appropriately estimate the skin condition and the factors that determine the skin condition.

[0201] (7-5) Variation 5 A description will be given of Modification 5. Modification 5 is an example in which a skin model in which the influence of the estimation time is reduced is used.

[0202] For example, skin is greatly affected by ultraviolet rays, humidity, and temperature, and the moisture content, skin color, and sebum secretion amount change with the seasons. Furthermore, since metabolism and vitamin production in the body are also affected by temperature and ultraviolet rays, skin condition fluctuates with the seasons.

[0203] As such, there is a correlation between the time of year and skin condition. If the time of year is taken into excessive consideration, the skin condition estimation result will be excessively influenced by the time of year in cases where the skin condition is actually determined by factors other than the time of year.

[0204] (7-5-1) Overview of Variation 5 An outline of Modification 5 will be described below. Fig. 20 is an explanatory diagram of an outline of Modification 5.

[0205] 20, the skin model N of the fifth modification is obtained by adjusting the influence of the skin model M of the present embodiment in consideration of the estimation time. The estimation time is a time specified from the date of execution of skin condition estimation. When the subject's physical and mental data X is provided to the skin model N, the skin condition Y is estimated according to the physical and mental data X so that the influence of the estimation time is not excessively apparent. The estimated skin condition Y is presented to the subject.

[0206] For example, the estimated time may include at least one of the following: - The season estimated from the date of skin condition estimation (for example, spring, summer, autumn, or winter) - The date, month, or day on which skin condition estimation is to be performed

[0207] (7-5-2) Information processing of variant 5 The following describes information processing in Modification 5. Fig. 21 is a sequence diagram of information processing in Modification 5.

[0208] The trigger for the process in FIG. 21 is the same as in FIG.

[0209] As shown in FIG. 21, the client device 10 executes an estimation request (S1110) in the same manner as in FIG.

[0210] After step S1110, the server 30 executes specification of the estimated time (S8130). Specifically, a rule for specifying the estimated time (hereinafter referred to as an "estimated time specifying rule") is stored in the storage device 31. The estimated time specifying rule describes the correspondence between the execution date and time of step S8130 and the estimated time. Processor 32 specifies the estimation time corresponding to the execution date and time of step S8130 by providing the execution date and time of step S8130 (that is, the timing at which the skin condition is estimated) to the estimation time specification rule.

[0211] After step S8130, the server 30 performs skin condition estimation (S8131). Specifically, the processor 32 provides the psychosomatic data X included in the estimation request data and the estimated time obtained in step S8130 to the skin model N, and estimates the skin condition Y according to the combination of the psychosomatic data X and the estimated time.

[0212] After step S8131, the server 30 generates advice (S1131), updates the database (S1132), and estimates a response (S1133), similar to FIG.

[0213] After step S1133, the client device 10 outputs the estimation result (S1111) in the same manner as in FIG.

[0214] (7-5-3) Summary of Variation 5 According to the fifth modification, the skin condition can be estimated without excessively being affected by the estimation time, thereby making it possible to more appropriately estimate the skin condition and the factors that determine the skin condition.

[0215] (8) Other variations Other modifications will be described.

[0216] The storage device 11 may be connected to the client device 10 via a network NW. The storage device 31 may be connected to the server 30 via the network NW.

[0217] Each step of the above information processing can be executed by either the client device 10 or the server 30. For example, if the client device 10 is capable of executing all of the steps of the above-described information processing, the client device 10 functions as an information processing device that operates standalone without transmitting a request to the server 30 .

[0218] In this embodiment, an example of output is shown in which a screen is displayed on a display, but the scope of this embodiment is not limited to this. This embodiment can also be applied to the following examples. - Audio output of estimation results -Printing out the estimation results Light output of estimated results

[0219] Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited to the above-described embodiments. Furthermore, the above-described embodiments can be improved or modified in various ways without departing from the spirit of the present invention. Furthermore, the above-described embodiments and modifications can be combined. [Explanation of symbols]

[0220] 1: Information processing system 10: Client device 11:Storage device 12: Processor 13: Input / output interface 14: Communication interface 30: Server 31:Storage device 32: Processor 33: Input / output interface 34: Communication interface

Claims

1. A skin condition estimation method for estimating skin condition using a computer, comprising: The computer acquires psychosomatic data relating to the body and mind of a subject of skin condition estimation, the computer estimates the skin condition of the subject using a skin model that describes a correlation between the psychosomatic data and the skin condition; the estimating step estimates the skin condition by providing psychosomatic data including the attributes of the subject to a skin model in which the influence of one or more of a person's attributes, a person's body composition, a person's habits, and a time period is reduced; A skin condition estimation method, wherein the mind and body data includes at least one of liver function related variables, muscle and bone related variables, heart rate / blood pressure related variables, blood oxygenation related variables, blood count related variables, lipid metabolism related variables, autonomic nervous function related variables, personal attribute related variables, renal function related variables, body composition related variables, glucose tolerance related variables, electrolyte related variables, cognitive function related variables, immunometabolism related variables, and depression / fatigue / drowsiness related variables.

2. The attribute of the subject is age. The skin condition estimation method according to claim 1 .

3. The attribute of the subject is gender. The skin condition estimation method according to claim 1 .

4. A skin condition estimation method for estimating skin condition using a computer, comprising: The computer acquires psychosomatic data relating to the body and mind of a subject of skin condition estimation, the computer estimates the skin condition of the subject using a skin model that describes a correlation between the psychosomatic data and the skin condition; the skin model includes a first skin model generated using only non-invasive data measured by a non-invasive test that does not involve invasiveness, and a second skin model generated using invasive data measured by an invasive test that involves invasiveness and the non-invasive data; A skin condition estimation method, wherein the mind and body data includes at least one of liver function related variables, muscle and bone related variables, heart rate / blood pressure related variables, blood oxygenation related variables, blood count related variables, lipid metabolism related variables, autonomic nervous function related variables, personal attribute related variables, renal function related variables, body composition related variables, glucose tolerance related variables, electrolyte related variables, cognitive function related variables, immunometabolism related variables, and depression / fatigue / drowsiness related variables.

5. The liver function-related variables include at least one of blood ALT (GPT), blood AST (GOT), blood ALP, blood γ-GTP, blood indirect bilirubin, blood total bilirubin, and blood direct bilirubin. The skin condition estimation method according to any one of claims 1 to 4.

6. The muscle-bone related variables include at least one of grip strength and bone mineral density. The skin condition estimation method according to any one of claims 1 to 4.

7. The heart rate / blood pressure related variable includes at least one of diastolic blood pressure, systolic blood pressure, and heart rate. The skin condition estimation method according to any one of claims 1 to 4.

8. The blood oxidation-related variables include at least one of a blood antioxidant potential value, a blood oxidative stress value, and an oxidative stress level. The skin condition estimation method according to any one of claims 1 to 4.

9. the blood count-related variables include at least one of blood hematocrit, blood hemoglobin, blood platelets, blood red blood cells, blood white blood cells, blood mean corpuscular hemoglobin concentration, blood mean corpuscular hemoglobin, and blood mean corpuscular volume; The skin condition estimation method according to any one of claims 1 to 4.

10. The lipid metabolism-related variables include at least one of HDL cholesterol in blood, LDL cholesterol in blood, total cholesterol in blood, a ratio of LDL cholesterol in blood to HDL cholesterol in blood, and neutral fat in blood. The skin condition estimation method according to any one of claims 1 to 4.

11. The autonomic nervous function-related variables include at least one of an autonomic nervous index HF, an autonomic nervous index LF, and a ratio of the autonomic nervous index HF to the autonomic nervous index LF. The skin condition estimation method according to any one of claims 1 to 4.

12. The personal attribute-related variables include at least one of exercise habits, sleep time values, fatigue duration, average working hours, medical history, smoking history, regular medication, and marital history. The skin condition estimation method according to any one of claims 1 to 4.

13. 5. The method for estimating a skin condition according to claim 1, wherein the renal function-related variables include at least one of a glomerular filtration rate and blood urea nitrogen.

14. The body composition-related variables include at least one of BMI (Body Mass Index), muscle mass, height, body fat percentage, skeletal muscle mass, and body weight. The skin condition estimation method according to any one of claims 1 to 4.

15. The glucose tolerance-related variables include at least one of hemoglobin A1c (HbA1c) in blood and blood glucose in blood; The skin condition estimation method according to any one of claims 1 to 4.

16. The electrolyte-related variables include at least one of blood potassium, blood chloride, blood sodium to blood potassium ratio, and blood sodium; The skin condition estimation method according to any one of claims 1 to 4.

17. The cognitive function-related variables include at least one of a reaction time of a cognitive task, a correct answer rate of a cognitive task, an incorrect answer rate of a cognitive task, and a number of completed cognitive tasks. The skin condition estimation method according to any one of claims 1 to 4.

18. The immunometabolism-related variables include at least one of high-sensitivity CRP in blood, amylase in blood, albumin in blood, creatine kinase in blood, cortisol in blood, total protein in blood, lactate dehydrogenase in blood, IgE in blood, IgG in blood, and uric acid in blood. The skin condition estimation method according to any one of claims 1 to 4.

19. The depression / fatigue / sleepiness related variables include at least one of a fatigue assessment scale, a depression / anxiety assessment scale, a motivation assessment scale, a sleepiness assessment scale, and a life performance status assessment scale. The skin condition estimation method according to any one of claims 1 to 4.

20. the step of estimating the skin condition estimates skin moisture by referring to a combination of the body composition-related variable, the blood oxygenation-related variable, the blood count-related variable, the depression / fatigue / drowsiness-related variable, the electrolyte-related variable, the glucose tolerance-related variable, and the immunometabolism-related variable; The skin condition estimation method according to any one of claims 1 to 4.

21. the step of estimating the skin condition estimates the skin barrier strength by referring to a combination of the electrolyte-related variable, the liver function-related variable, the glucose tolerance-related variable, the blood oxygenation-related variable, the blood count-related variable, the glucose tolerance-related variable, and the depression / fatigue / drowsiness-related variable; The skin condition estimation method according to any one of claims 1 to 4.

22. the step of estimating the skin condition estimates skin texture by referring to a combination of the immunometabolism-related variable, the electrolyte-related variable, the autonomic nervous function-related variable, and the liver function-related variable; The skin condition estimation method according to any one of claims 1 to 4.

23. the step of estimating the skin condition estimates skin firmness by referring to a combination of the blood oxidation-related variables, the liver function-related variables, the immunometabolism-related variables, the blood oxidation-related variables, the body composition-related variables, the glucose tolerance-related variables, the blood count-related variables, the muscle-and-bone-related variables, and the autonomic nervous function-related variables; The skin condition estimation method according to any one of claims 1 to 4.

24. the step of estimating the skin condition estimates skin melanin by referring to a combination of the autonomic nervous function-related variable, the depression / fatigue / drowsiness-related variable, the immunometabolism-related variable, the glucose tolerance-related variable, the liver function-related variable, the blood count-related variable, and the blood oxidation-related variable; The skin condition estimation method according to any one of claims 1 to 4.

25. the step of estimating the skin condition estimates skin brightness by referring to a combination of the body composition-related variables, the blood count-related variables, the renal function-related variables, the immunometabolism-related variables, the heart rate / blood pressure-related variables, the lipid metabolism-related variables, the electrolyte-related variables, and the depression / fatigue / drowsiness-related variables; The skin condition estimation method according to any one of claims 1 to 4.

26. the step of estimating the skin condition estimates skin redness by referring to a combination of the body composition-related variable, the depression / fatigue / drowsiness-related variable, the blood count-related variable, the liver function-related variable, the blood count-related variable, the blood oxygenation-related variable, and the immunometabolism-related variable; The skin condition estimation method according to any one of claims 1 to 4.

27. In the skin model, a degree of influence between the psychosomatic data and the skin index is defined for each combination of the psychosomatic data and the skin index. The skin condition estimation method according to any one of claims 1 to 4.

28. The computer further comprises a step of generating advice according to the skin condition, a step of the computer outputting the skin condition and the advice. The skin condition estimation method according to any one of claims 1 to 4.

29. a means for acquiring mental and physical data relating to the body and mind of a subject of skin condition estimation; means for estimating the skin condition of the subject using a skin model that describes a correlation between the psychosomatic data and the skin condition; the estimating means estimates the skin condition by providing psychosomatic data including the attributes of the subject to a skin model in which the influence of one or more of a person's attributes, a person's body composition, a person's habits, and a time period is reduced; The mind-body data includes at least one of liver function-related variables, muscle-and-bone-related variables, heart rate / blood pressure-related variables, blood oxygenation-related variables, blood count-related variables, lipid metabolism-related variables, autonomic nervous function-related variables, personal attribute-related variables, renal function-related variables, body composition-related variables, glucose tolerance-related variables, electrolyte-related variables, cognitive function-related variables, immunometabolism-related variables, and depression / fatigue / drowsiness-related variables.

30. a means for acquiring mental and physical data relating to the body and mind of a subject of skin condition estimation; means for estimating the skin condition of the subject using a skin model that describes a correlation between the psychosomatic data and the skin condition; the skin model includes a first skin model generated using only non-invasive data measured by a non-invasive test that does not involve invasiveness, and a second skin model generated using invasive data measured by an invasive test that involves invasiveness and the non-invasive data; The mind-body data includes at least one of liver function-related variables, muscle-and-bone-related variables, heart rate / blood pressure-related variables, blood oxygenation-related variables, blood count-related variables, lipid metabolism-related variables, autonomic nervous function-related variables, personal attribute-related variables, renal function-related variables, body composition-related variables, glucose tolerance-related variables, electrolyte-related variables, cognitive function-related variables, immunometabolism-related variables, and depression / fatigue / drowsiness-related variables.

31. Computer, It functions as a means for acquiring mental and physical data relating to the body and mind of a subject of skin condition estimation, a program for causing the program to function as a means for estimating the skin condition of the subject using a skin model that describes the correlation between the psychosomatic data and the skin condition, the estimating means estimates the skin condition by providing psychosomatic data including the attributes of the subject to a skin model in which the influence of one or more of a person's attributes, a person's body composition, a person's habits, and a time period is reduced; The mind and body data includes at least one of liver function related variables, muscle and bone related variables, heart rate and blood pressure related variables, blood oxygenation related variables, blood count related variables, lipid metabolism related variables, autonomic nervous function related variables, personal attribute related variables, kidney function related variables, body composition related variables, glucose tolerance related variables, electrolyte related variables, cognitive function related variables, immunometabolism related variables, and depression, fatigue, and sleepiness related variables.

32. Computer, It functions as a means for acquiring mental and physical data relating to the body and mind of a subject of skin condition estimation, a program for causing the program to function as a means for estimating the skin condition of the subject using a skin model that describes the correlation between the psychosomatic data and the skin condition, the skin model includes a first skin model generated using only non-invasive data measured by a non-invasive test that does not involve invasiveness, and a second skin model generated using invasive data measured by an invasive test that involves invasiveness and the non-invasive data; The mind and body data includes at least one of liver function related variables, muscle and bone related variables, heart rate and blood pressure related variables, blood oxygenation related variables, blood count related variables, lipid metabolism related variables, autonomic nervous function related variables, personal attribute related variables, kidney function related variables, body composition related variables, glucose tolerance related variables, electrolyte related variables, cognitive function related variables, immunometabolism related variables, and depression, fatigue, and sleepiness related variables.

Images