KR-102961548-B1 - AI-BASED COSMETICS CURATION METHOD USING NON-FACE-TO-FACE SKIN TYPE ANALYSIS

Abstract

The present invention relates to a method for curating cosmetics through artificial intelligence-based non-face-to-face skin type analysis. The method of the present invention may be characterized by comprising the steps of: a user terminal transmitting image data and non-image data to a main server; the main server analyzing the image data to generate first skin characteristic data; the main server analyzing the non-image data to generate second skin characteristic data; the main server classifying the user's skin type using the first skin characteristic data and the second skin characteristic data; and the main server selecting a cosmetic product by matching the user's skin type with a pre-established database of cosmetic ingredients and efficacy and transmitting it to the user terminal.

Inventors

• 이준석

Assignees

• 주식회사 에프유피글로벌파트너스

Dates

Publication Date

20260507

Application Date

20250530

Claims (1)

1. A step in which the user terminal transmits image data and non-image data to the main server; A step in which the main server analyzes image data to generate first skin characteristic data; A step in which the main server analyzes non-image data to generate second skin characteristic data; A step in which the main server classifies the user's skin type using first skin characteristic data and second skin characteristic data; A step in which the main server selects a cosmetic product by matching the user's skin type with a pre-established database of cosmetic ingredients and efficacy, and transmits it to the user terminal; and The above main server includes a step of determining the sales price of the cosmetic selected by the user by analyzing the skin type similarity value, the cosmetic positive review value, and the cosmetic sales volume value. Image data is data regarding an image of the user's face captured by the camera module of the user terminal, and non-image data is data regarding work time, sleep time, and recovery time after skin trouble occurs that the user inputs through the user terminal. The first skin characteristic data is data regarding the user's oiliness, pore area, and degree of elasticity, and The secondary skin characteristic data is data regarding the user's fatigue level, and The main server processes the first skin characteristic data and the second skin characteristic data to embedding vectorize the user's oiliness, pore area, elasticity, and fatigue, and the main server has a center vector for skin type pre-set, so the main server classifies the user's skin type into dry, oily, combination, and sensitive based on the similarity value between the user's embedding vector and the center vector of the skin type set by the main server. The above main server determines the selling price by arithmetically multiplying the default value of the cosmetic selected by the user by a weight, and the first to fourth weights have sequentially lower values, with the first weight having the highest value and the fourth weight having the lowest value. The value of positive cosmetic reviews is the value obtained by arithmetically dividing the number of positive reviews for the cosmetic selected by the user within the platform by the total number of reviews for the cosmetic selected by the user, and The value of cosmetic sales volume is the value obtained by arithmetically dividing the number of sales of the cosmetic selected by the user within the platform by the total number of sales of all cosmetic products within the platform, and The above main server is, If the skin type similarity value is greater than or equal to the first specific value, and the cosmetic positive review value is greater than or equal to the second specific value, the weight is set to the first weight regardless of the cosmetic sales volume, and If the skin type similarity value is greater than or equal to the first specific value, and the value of positive cosmetic reviews is less than the second specific value, the weight is set to the fourth weight regardless of the value of cosmetic sales volume, and If the skin type similarity value is less than the first specific value, and the cosmetic sales volume value is greater than or equal to the third specific value, the weight is set to the third weight regardless of the value of positive cosmetic reviews, and A method characterized by setting the weight to a second weight regardless of the value of positive cosmetic reviews when the value of skin type similarity is less than a first specific value and the value of cosmetic sales volume is less than a third specific value.

Description

AI-Based Cosmetics Curation Method Using Non-Face-to-Face Skin Type Analysis The present invention relates to a method for curating cosmetics through artificial intelligence-based non-face-to-face skin type analysis. Existing skin type analysis and cosmetic recommendations have been based on skin measurement equipment, visual assessment by experts, or surveys, but these methods have limitations in terms of repeatability and accuracy. Furthermore, as consumers often select marketing-driven products without understanding their skin condition and suitable ingredients, the need for efficient personalized cosmetic recommendation methods is emerging. With the recent advancement of artificial intelligence technology, skin condition prediction technologies based on skin image analysis are being developed; however, there is a problem in that such technologies rarely integrate user environment and lifestyle information to define skin types in a multidimensional manner and link this to practical cosmetic recommendations. FIG. 1 is a conceptual diagram showing a system in which the method for curating cosmetics through artificial intelligence-based non-face-to-face skin type analysis of the present invention is performed. Figure 2 is a flowchart illustrating the method of cosmetic curation through artificial intelligence-based non-face-to-face skin type analysis according to the present invention. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims. The terms used in this specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and/or "comprising" used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and/or" includes each of the mentioned components and all combinations of one or more. Although terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention. Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Hereinafter, the method for curating cosmetics (1000) through artificial intelligence-based non-face-to-face skin type analysis according to the present invention will be described with reference to the drawings. FIG. 1 is a conceptual diagram showing a system in which the method for curating cosmetics through artificial intelligence-based non-face-to-face skin type analysis according to the present invention is performed, and FIG. 2 is a flowchart showing the method for curating cosmetics through artificial intelligence-based non-face-to-face skin type analysis according to the present invention. The method (1000) of the present invention can be performed within a system including a user terminal (10), a network (20), and a main server (30). The user terminal (10) is a terminal used by a user who wants to receive recommendations for cosmetics, and may be a terminal that provides a web page, an app page (app list), a program, or an application related to the method (1000) of the present invention. The user terminal (10) can be implemented as a computer that can access and connect to a main server (30) at a remote location via a network (20). Specifically, the user terminal (10) is a wireless communication device and may include all types of handheld-based wireless communication devices such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, sma