KR20240000829A - Method for providing customized cosmetics using interactive artificial intelligence technology - Google Patents

Abstract

The method of providing skin diagnosis and customized skin cosmetics using artificial intelligence technology includes (A) information on various raw materials and skin cosmetics and information on the above-mentioned raw materials and skin cosmetics. Converting in vitro, in vivo, or clinical efficacy evaluation information into big data and accumulating it in a raw material information database; (B) (1) Entering the customer's skin opinion information, measuring the skin condition and entering the skin measurement information, and taking a skin image and entering the image information are performed in a predetermined order, (2) Network Accumulating the above-described information in a skin information database, (3) generating artificial intelligence-based skin diagnosis information, including performing skin diagnosis by machine learning based on artificial intelligence (AI); (C) Raw material information and skin cosmetics optimized for the skin characteristics and condition of a specific customer at that point in time through deep running in connection with the skin information database and raw material information database for optimal raw materials and skin cosmetics according to the skin diagnosis information above. providing information; and (D) providing customized skin cosmetics to customers according to the optimized raw material information and skin cosmetic information, wherein the information on the raw materials and skin cosmetics includes information on irritation and allergy, and the skin cosmetics information includes information on irritation and allergy. The information about cosmetics includes information about the composition and formulation of skin cosmetics, the acquisition of the skin opinion information and skin image information is obtained by a mobile device, and the acquisition of the skin measurement information is obtained by a mobile linked device. It is linked to the mobile app and recorded as an app, including skin information accumulated in the skin information database, skin diagnosis information generated by data processing through machine learning, skin characteristics at that point in time for a specific customer, and Raw material information and skin cosmetics information optimized for each condition are provided, updated, and stored in real time to customers, manufacturers, and sellers.

Description

Method for providing skin diagnosis and customized skin cosmetics using artificial intelligence technology {METHOD FOR PROVIDING CUSTOMIZED COSMETICS USING INTERACTIVE ARTIFICIAL INTELLIGENCE TECHNOLOGY}

The present invention relates to a method for diagnosing skin and providing customized skin cosmetics using artificial intelligence technology, and more specifically, to information on various raw materials, especially cosmetic raw materials with natural physiological activity, and the composition and formulation of skin cosmetics accordingly, and In vitro, in vivo, and clinical efficacy evaluation information is converted into big data, and customer skin diagnosis information is networked through machine learning using customer skin opinion information, skin condition measurement information, and skin image measurement information. While accumulating them into a database, big data on these cosmetic raw materials and compositions and their evaluation information and customer skin diagnosis information are provided through deep learning based on artificial intelligence to provide skin cosmetics optimized for the customer or customized. It relates to a method of providing skin cosmetics with a designed formulation and skin diagnosis and customized skin cosmetics using artificial intelligence technology.

Not only does a person's skin differ depending on age, gender, and skin type, but skin conditions such as wrinkles, roughness, skin texture, skin tone, gloss, radiance, moisture, pigmentation, elasticity, and sensitivity are also affected by internal and external environments. Because it changes depending on your skin, it is important to choose appropriate cosmetics according to your skin characteristics and condition.

When purchasing cosmetics, consumers receive recommendations from acquaintances, or refer to the brand name, price, appearance of the product container, directions for use, user reviews, etc. of the product that seems to be suitable for them on the website of a cosmetics manufacturer, shopping mall, or specialty store. It is common to choose cosmetics.

However, there are so many brands and formulations of cosmetics, and not only are there a wide variety of similar products among manufacturers' products, but cosmetics-related information is available not only offline but also online due to the development of information and communication technology (ICT). Therefore, choosing the appropriate cosmetics for oneself is not an easy problem. Other than the manufacturer's one-sided advertising campaign, consumers cannot accurately judge whether the ingredients contained in cosmetics are suitable for their skin characteristics and condition, so they often choose the appropriate ones. Im real.

Recently, in order to solve these problems, there have been attempts to provide customized information and cosmetics to individual customers with different skin characteristics and conditions in selecting cosmetics.

Publication Patent No. 10-2017-0117840, a customized skin diagnosis and management system (publication date: October 24, 2017) measures the skin condition with a skin condition measurement unit and determines the skin condition consisting of elasticity, moisture, pigment, antioxidant and sensitivity. A skin condition measurement control unit that calculates skin condition information for one or more categories selected from the group, a skin condition prediction control unit that calculates skin condition change prediction information for each category based on the subject's genetic information from a database or genetic measurement unit, and a skin condition prediction control unit that calculates skin condition change prediction information for each category, and A customized skin diagnosis and skin diagnosis and management information provision unit that calculates and provides skin diagnosis information and corresponding skin care information about the skin condition and skin condition change at the time of measurement based on condition information and skin condition change prediction information. A management system is presented.

However, the above-described prior art only provides skin diagnosis and management information and has nothing to do with providing customized cosmetic ingredients or cosmetics.

Meanwhile, recently, the 4th revolution based on artificial intelligence (AI) has been born, and as a field of artificial intelligence, functions similar to human learning abilities are realized on computers, and the computer creates new algorithms on its own based on data. A machine that uses Deep Neural Networks (DNN), which has at least one hidden layer between the input and output of the model to be trained, which models the patterns existing in the data as a complex multi-layer network. Deep learning as a sub-concept of learning is attracting attention.

This type of machine learning goes through a process where a computer infers and analyzes data and produces results, so it can provide high speed, economic efficiency, and accuracy through accurate prediction and analysis by securing appropriate big data, so it can also be used in the cosmetics field. Attempts are being made to provide customized information to customers.

Registered Patent No. 10-2321851, a light output device that manages the user's skin using artificial intelligence and its operating method (registration date: October 29, 2021), includes a plurality of light sources that irradiate light, and deep learning It is learned using an algorithm and is based on a memory that stores a skin care model that infers the user's facial skin condition, a camera that photographs the user's face, and a first type of facial image and skin care model captured through the camera. A light output device that manages the user's skin using artificial intelligence, including a processor that acquires the skin condition for each part of the face and controls the light output of a plurality of light sources based on the obtained skin condition. It is being proposed.

However, the above-described prior art only relates to skin care devices and has nothing to do with the provision of cosmetics as customized cosmetic ingredients or cosmetic compositions.

Registered Patent No. 10-2001337, a skin type customized service integrated service system using big data and AI (registration date: July 11, 2019), is a system where medical device products, cosmetic-related product information, and product data, which is manufacturer information, are stored. product DB; Customer information DB where customer data is stored; Knowledge service DB where skin diagnosis data and knowledge data, which is skin type information data, are stored; A skin measurement device that generates skin measurement data for a specific member; And the skin measurement data from the skin measurement device is transmitted, linked to the product DB, customer information DB, and knowledge service DB, and the consumer's skin type is calculated based on the skin measurement data to form customized analysis data for each type. Therefore, we are proposing an integrated service provision system tailored to skin type using big data and AI, including a big data artificial intelligence operation server provided to the members, the manufacturer, and the diagnostician.

However, the above-described prior art is only intended to recommend products and services suitable for one's skin type to consumers with the participation of manufacturers and dermatologists, and has nothing to do with the selection of optimized raw materials customized for customers and the provision of cosmetics containing them. do.

Publication Patent No. 10-2017-0117840, Customized skin diagnosis and management system (Publication date: October 24, 2017) Registered Patent No. 10-2321851, Light output device that manages the user's skin using artificial intelligence and its operation method (registration date: October 29, 2021) Registered Patent No. 10-2001337, integrated service provision system customized for skin type using big data and AI (registration date: July 11, 2019)

The present invention provides a method of skin diagnosis and customized skin cosmetics using artificial intelligence technology, which can provide optimally designed skin cosmetics by selecting raw materials that match the skin type and condition of each customer, especially appropriate natural bioactive raw materials. .

The present invention converts information on various raw materials and skin cosmetics and their in vitro, in vivo, and clinical efficacy evaluation information into big data, as well as customer skin opinion information, skin condition measurement information, and skin image measurement information. By accumulating customer skin diagnosis information through machine learning into a database and providing a specific customer's skin diagnosis information with information on natural and bioactive raw materials optimized for that, an artificial solution can be provided to each customer. It provides methods for skin diagnosis and customized skin cosmetics using intelligent technology.

The present invention provides skin cosmetics that are optimally formulated to improve skin condition while being safe with no side effects when applied to a specific customer's skin, enabling skin care optimized for each customer, skin diagnosis and customization using artificial intelligence technology. Provides a method of providing skin cosmetics.

As an example, a method of providing skin diagnosis and customized skin cosmetics using artificial intelligence technology includes: (A) information on various raw materials and skin cosmetics and the above-mentioned raw materials; and converting in vitro, in vivo, or clinical efficacy evaluation information for skin cosmetics into big data and accumulating it in a raw material information database; (B) (1) Entering the customer's skin opinion information, measuring the skin condition and entering skin measurement information, and taking a skin image and entering image information are performed in a predetermined order, (2) Network Accumulating the above-mentioned information in a skin information database, (3) generating artificial intelligence-based skin diagnosis information, including performing skin diagnosis by machine learning based on artificial intelligence (AI); (C) Raw material information and skin cosmetics optimized for the skin characteristics and condition of a specific customer at that point in time through deep running in connection with the skin information database and raw material information database for optimal raw materials and skin cosmetics according to the skin diagnosis information. providing information; and (D) providing customized skin cosmetics to customers according to the optimized raw material information and skin cosmetic information, wherein the information on the raw materials and skin cosmetics includes information on irritation and allergy, and the skin cosmetics information includes information on irritation and allergy. The information about cosmetics includes information about the composition and formulation of skin cosmetics, the acquisition of the skin opinion information and skin image information is obtained by a mobile device, and the acquisition of the skin measurement information is obtained by a mobile linked device. It is linked to the mobile app and recorded as an app, including skin information accumulated in the skin information database, skin diagnosis information generated by data processing through machine learning, skin characteristics at that point in time for a specific customer, and Raw material information and skin cosmetics information optimized for each condition are provided, updated, and stored in real time to customers, manufacturers, and sellers.

According to the method of skin diagnosis and provision of customized skin cosmetics using artificial intelligence technology according to the present invention, information on various raw materials and skin cosmetics and their in vitro, in vivo, and clinical efficacy evaluation information are converted into big data, as well as customer satisfaction. Customer skin diagnosis information is accumulated in a database through machine learning using skin opinion information, skin condition measurement information, and skin image measurement information, and provides skin diagnosis information for specific customers and information on natural and bioactive raw materials optimized for that. By doing so, we provide solutions and skin care optimized for each customer, as well as optimally designed customized skin cosmetics by selecting raw materials that match the skin type of a specific customer and their skin condition at the relevant time, especially appropriate natural bioactive raw materials. It can have an effect.

1 is a flowchart showing a skin diagnosis process based on artificial intelligence.
FIG. 2 is a flowchart illustrating a method of providing customized skin cosmetics to customers according to the present invention using the skin diagnosis information of FIG. 1, information on raw materials and skin cosmetics, and evaluation information for these.
Figure 3 is an example diagram of Figure 1.
Figure 4 is an example block diagram illustrating the image and skin condition measurement process of Figure 3.
Figure 5 is an example of the survey fingerprint of Figure 3.
Figure 6 is a schematic diagram showing the process of presenting customized optimized raw materials and skin cosmetics through machine learning using skin diagnosis information, information about raw materials and skin cosmetics, and evaluation information about them.
Figure 7 is a schematic diagram of the machine learning algorithm.

The present invention described below can be modified in various ways and can have various embodiments. Specific embodiments will be illustrated in the drawings and described in detail in the detailed description.

However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all transformations, equivalents, and substitutes included in the spirit and technical scope of the present invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Additionally, terms such as first and second may be used to separately describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

In addition, when at least two different embodiments are described in the present application, all or part of the components of each embodiment can be merged and used interchangeably without departing from the technical spirit of the present invention. .

Figure 1 is a flowchart showing a skin diagnosis process based on artificial intelligence. The customer's subjective skin opinion information, for example, past skin history or current skin, is provided by each customer through an offline or online mobile survey at the store. Skin opinion information 101 on skin condition, skin type, etc., and skin oil, moisture, and elasticity measured using offline skin measurement devices such as in stores, specifically, offline or online mobile linked skin measurement devices. Skin measurement information (102) such as pH, skin temperature, dermal thickness, dead skin cells, pigment, wrinkles, blackheads, whiteheads, etc., and erythema, dryness, sensitivity, inflammation, acne, and wrinkles as images taken offline or online. , the process of inputting image information 103 such as pigment, eczema, sebum, psoriasis, atopy, allergy, etc. is performed in a predetermined order.

The skin opinion information 101, skin measurement information 102, and image information 103 are accumulated in the skin information database 104 through a network.

The information accumulated in the skin information database 104 is linked to the neural network analysis unit 105 to perform skin diagnosis through machine learning based on artificial intelligence (AI), and artificial intelligence-based skin diagnosis for the customer's skin condition. Generates information 106.

The skin diagnosis information refers to the skin opinion information 101, and the digital image according to the skin image information 103 is divided into multiple areas and the consumer's skin type is analyzed for each area. At the same time, skin measurement information 102 is classified by type, compared with other information accumulated in the skin information database 104, analyzed and inferred to form customized analysis data for each skin type, thereby providing skin diagnosis information 106. do.

The skin image information 103, skin measurement information 102, and skin diagnosis information 106 are delivered (107) to manufacturers, sellers, and customers through the network.

For convenience of explanation, FIGS. 3 to 5 will be elaborated before FIG. 2.

Figure 3 is an example diagram showing the process of constructing artificial intelligence-based skin diagnosis information 106 through an app, Figure 4 is an example block diagram explaining the image and skin condition measurement process of Figure 3, and Figure 5 is Figure 3 As an example of a survey fingerprint, it will be mentioned together for convenience of explanation.

We collect customer skin information to select raw materials optimized for the customer's skin and provide optimized skin cosmetics.

In the example shown in FIG. 3, since the customer's skin image information 103 requires image capture, the app is run using the customer's own mobile device (specifically, a smartphone) that has a camera capable of acquiring a facial image. Run it, and if necessary, go through the login process and take images of areas such as the face, back of the hand, and arm.

The example shown is a screen where a face image is captured using the camera mode on a mobile device and the image is uploaded.

The example shown shows a case where a customer's skin condition is measured using a skin measuring device linked to a mobile device, but in some cases, a skin measuring device is placed at a store and the skin measuring information (102) is sent to the manufacturer through the network. ) can of course be provided in real time.

The skin meter is designed to measure the current state of the skin, and can measure the current skin condition by measuring skin elements such as oil, moisture, thickness, elasticity, wrinkles, pH, and dead skin cells (see Figure 4).

Meanwhile, in the illustrated example, skin opinion information 101 for diagnosing skin is obtained by conducting a survey to customers through a mobile device before or after obtaining skin image information 103 and/or skin measurement information 102. This is an example screen. This survey consists of a variety of questions consisting of several items including skin type and skin concerns, allowing the customer to identify his or her subjective skin condition (see Figure 5).

The skin opinion information 101, skin measurement information 102, and image information 103 are accumulated in the skin information database 104 through a network, and are linked to the neural network analysis unit 105 to be used for artificial intelligence (AI). Since skin diagnosis information 106 is generated by performing skin diagnosis based on machine learning as described above, further explanation thereof will be omitted.

The skin image information 103, skin measurement information 102, and skin diagnosis information 106 are converted into various visual screens, such as bar graphs or radial graphs, through appropriate data processing procedures, if necessary. It can be delivered to customers, as well as sellers and manufacturers.

Next, FIG. 2 illustrates a method of providing customized skin cosmetics according to the present invention using the skin diagnosis information 106 of FIG. 1, information 108 about raw materials and skin cosmetics, and evaluation information 109 thereof. As a flow chart, a biologically active substance with biological activity related to antibacterial, antioxidant, anti-aging, anti-allergic, anti-acne, regeneration, whitening, wrinkle improvement, pigment removal, moisturizing, soothing, erythema relief, dryness improvement, sensitivity improvement, or atopic dermatitis improvement. Alternatively, information on raw materials such as natural extracts (108) and in vitro, in vivo, or clinical efficacy evaluation information (109) on these raw materials and the composition and formulation of skin cosmetics containing these raw materials are converted into big data to provide raw material information. It is accumulated in the database 110.

Here, the above-mentioned raw materials include biological activities related to antibacterial, antioxidant, anti-aging, anti-allergic, anti-acne, regeneration, whitening, wrinkle improvement, pigment removal, moisturizing, soothing, alleviating erythema, improving dryness, improving sensitivity, and/or improving atopic dermatitis. It may be a substance or a natural extract, and may also include those widely used as excipients, stabilizers, dispersants, preservatives, and flavoring agents in skin cosmetics such as cosmetics.

Meanwhile, the information 108 about the raw materials and skin cosmetics may include information about irritation and allergies, and the information about the skin cosmetics includes information about the composition and formulation of the skin cosmetics.

Next, based on the artificial intelligence-based skin diagnosis information 106 about the customer's skin condition, a neural network analysis unit ( 105), deep running provides raw material information and skin cosmetics information (111) optimized for the skin characteristics and condition of a specific customer at that point in time.

Next, Figure 6 is a schematic diagram showing the process of presenting customized optimized raw materials and skin cosmetics through machine learning of the neural network analysis unit using skin diagnosis information, information about raw materials and skin cosmetics, and evaluation information about them, and Figure 7 is This is a schematic diagram of the machine learning algorithm.

Figure 6 shows the process of inputting a customer's individual skin information and deriving results after processing, and can be divided into Area A, Area B, and Area C.

In Area A, skin information is obtained by performing the following processes in a random order: entering the customer's skin opinion information, measuring the skin condition and entering skin measurement information, and taking skin images and entering image information. Information can be collected through photography using the image sensor of a mobile device, customer skin diagnosis through a mobile survey, or a skin measurement device linked to a mobile device, and these can be linked to a mobile app and recorded as an app. It's like a bar.

Meanwhile, when using an app to capture images of video information about the face, there are portrait rights issues, so the customer's consent to the use of video information is required.

From video information, color information, skin disease information based on facial features, etc. can be obtained, and information that is difficult to obtain from this can be obtained through skin opinion information in the form of a questionnaire. You can learn about ways to improve your skin, and more objective and specific skin information can be obtained from skin measurement information.

If this information is collected using a mobile device, it can become customer-based information for data classification, such as age, gender, and inclination of users using the app.

The information obtained in area A is diagnosed using artificial intelligence (Al)-based machine learning in the neural network analysis department in area B, and the skin diagnosis information is stored, compared with big data, and segmented by type to provide accurate analysis for each type. Perform, accumulate results, and update.

As an example of the above segmentation, information similar to the acne group among the information obtained in area A is compared with information on the group diagnosed with acne accumulated in the existing database, and information on pigmentation is derived from the information in area A. Compare information to that of the group to be diagnosed. Likewise, the information in Area A is compared with the information in the group that was diagnosed with skin conditions such as wrinkles, dryness, atopy, etc. to identify any problems with the skin information in Area A.

Through this segmentation, the accuracy of information and solutions can be increased. In segmentation of this information, it is not cross-sectional and fragmentary about skin type, but information and evaluation information about appropriate raw materials and skin cosmetics suitable for skin type and condition, and customer Information such as user reviews is also repeatedly compared and analyzed.

On the other hand, by using customer skin opinion information based on customer questionnaire responses, it is possible to appropriately select products with the highest purchase probability and lowest return probability.

In this way, it provides an overall solution for skin diagnosis and its results from the results obtained by subdividing the information. In order to derive these results, skin opinion information, captured image information, basic information accumulated in the database, raw materials and skin Compare and analyze topical drug information, evaluation information, marketing information, etc. in three dimensions.

The analyzed results are saved and used as data for the next information analysis. In this way, the accuracy of information increases dramatically over time by repeating itself infinitely through an organic analysis algorithm (machine learning).

Skin diagnosis information and corresponding solutions are shared with customers, used to update data within AI, and the stored data is encrypted to restrict use other than customer viewing and analysis data within the algorithm.

As a result, the information obtained in Area A is diagnosed using AI (Machine earning) technology in Area B, and then in Area C, raw materials and external skin preparation information optimized for skin diagnosis information are provided, as well as customized skin cosmetics. .

As described in detail above, according to the method of skin diagnosis and provision of customized skin cosmetics using artificial intelligence technology according to the present invention, information on various raw materials and skin cosmetics and their in vitro, in vivo, and clinical efficacy evaluation information are provided. In addition to big data, customer skin diagnosis information is accumulated in a database through machine learning using customer skin opinion information, skin condition measurement information, and skin image measurement information, and the skin diagnosis information of a specific customer and optimized for that information are accumulated in a database. By providing information on natural and bioactive raw materials, we provide solutions and skin care optimized for each customer, as well as selecting raw materials that match the skin type of a specific customer and the skin condition at the time, especially appropriate natural bioactive raw materials. It is effective in providing optimally designed, customized skin cosmetics to customers.

Meanwhile, the embodiments disclosed in these drawings are merely provided as specific examples to aid understanding, and are not intended to limit the scope of the present invention. It is obvious to those skilled in the art that in addition to the embodiments disclosed herein, other modifications based on the technical idea of the present invention can be implemented.

101...Skin opinion information 102...Skin measurement information
103...Image information 104...Skin information database
105...Neural network analysis department 106...Skin diagnosis information

Claims (1)

In the method of skin diagnosis and provision of customized skin cosmetics using artificial intelligence technology,
(A) converting information on various raw materials and skin cosmetics and in vitro, in vivo, or clinical efficacy evaluation information on the raw materials and skin cosmetics into big data and accumulating them in a raw material information database;
(B) (1) Entering the customer's skin opinion information, measuring the skin condition and entering the skin measurement information, and taking a skin image and entering the image information are performed in a predetermined order, (2) Network Accumulating the above-described information in a skin information database, (3) generating artificial intelligence-based skin diagnosis information, including performing skin diagnosis by machine learning based on artificial intelligence (AI);
(C) Raw material information and skin cosmetics optimized for the skin characteristics and condition of a specific customer at that point in time through deep running in connection with the skin information database and raw material information database for optimal raw materials and skin cosmetics according to the skin diagnosis information above. providing information; and
(D) comprising providing customized skin cosmetics to customers according to the optimized raw material information and skin cosmetics information,
The information on the above-mentioned raw materials and skin cosmetics includes information on irritation and allergies, and the information on the above-mentioned skin cosmetics includes information on the composition and formulation of the skin cosmetics,
The acquisition of the above-mentioned skin opinion information and skin image information is obtained by a mobile device, and the above-mentioned skin measurement information is obtained by a mobile linked device and linked with the mobile app and recorded as an app,
Skin information accumulated in the skin information database, skin diagnosis information generated by data processing through machine learning, raw material information and skin cosmetics information optimized for the skin characteristics and condition of a specific customer at that point in time. , A method of providing skin diagnosis and customized skin cosmetics using artificial intelligence technology that is provided and updated in real time to customers, manufacturers, and sellers.