KR20210084880A - Method for recommending skin care products or cosmetics based on a machine learning model - Google Patents

Abstract

Provided is a cosmetic recommendation method performed by a cosmetic recommendation server on a platform having a cosmetic recommendation server that communicates with a plurality of member terminals through a communication network. The cosmetic recommendation method of the present disclosure comprises: receiving personal information of a member on the member terminal from one or more member terminals, wherein the personal information includes at least the member's skin type, age, residential area information, and cosmetics used information; receiving and storing regional environment information for a plurality of regions, wherein among the plurality of regions, the residence region of the member is included; receiving ingredient and content information of one or more cosmetics, wherein among the ingredients and content information, information on ingredients and content of the cosmetics used by the member is included; generating one or more questions about the usage experience according to the use of the used cosmetics, and repeatedly providing the one or more questions to the member terminal according to a predetermined criterion; receiving and storing a series of answers to the provided questions from the member terminal; building or updating a cosmetic recommendation learning model through machine learning using a data set containing the member's personal information, the regional environmental information corresponding to the member's residential area information, ingredient and content information of the member's cosmetics used, and the series of answers to the questions received from the member terminal; and selecting suitable cosmetics for a predetermined member terminal on the basis of the cosmetic recommendation learning model.

Description

Cosmetic recommendation method based on machine learning model {METHOD FOR RECOMMENDING SKIN CARE PRODUCTS OR COSMETICS BASED ON A MACHINE LEARNING MODEL}

A cosmetic recommendation method performed by a cosmetic recommendation server on a platform having a cosmetic recommendation server that communicates with a plurality of member terminals through a communication network, and relates to a cosmetic recommendation method according to a suitable cosmetic recommendation model built through machine learning.

As interest in skin beauty increases, users' efforts to find the best cosmetics for themselves are increasing. As part of such efforts, users often refer to various information about the cosmetics on the Internet, for example, reviews of all cosmetics ingredients and other people, before selecting new cosmetics. Users can refer to the ingredients of a specific cosmetic product (eg, whether there are any harmful ingredients) or the reactions of other users who have used the cosmetic product, and/or which cosmetic products are mainly selected by other users with similar skin types to themselves. , often choose cosmetics. In this atmosphere, recently, platforms for collecting and presenting user reviews on cosmetics and further recommending and selling cosmetics suitable for the user's skin type are emerging.

However, these existing cosmetic review platforms simply present user reviews so that users who want to refer to them can synthesize and evaluate the review information presented above on their own, or type specific skin types (eg, dry, oily, sensitive skin, etc.) ) is limited to providing a simple recommendation based on very simple information, such as recommending cosmetics that are generally known to be suitable for skin type users. However, it is difficult to determine a user's skin condition and cosmetics suitable therefor based on only a few types of skin type information. For example, along with the user's skin type, cosmetics of the same ingredient according to environmental information surrounding the user, for example, various environmental information such as food eaten by people in the user's living area, water consumed, washing water, temperature, humidity, etc. This can lead to completely different results.

Thus, as well as the typed skin type of the user. There is a need for an automated cosmetic recommendation system that can recommend cosmetics that are most suitable for a user based on various environmental information surrounding the user and referring to reviews (reviews) of other users.

An object of the present disclosure is to provide a cosmetic recommendation system that recommends cosmetics most suitable for a user. The present disclosure relates, inter alia, to the user's typed skintype as well. It is intended to provide a cosmetic recommendation system that can recommend the most suitable cosmetics to the user based on various environmental information surrounding the user and referring to the reviews (reviews) of other users.

According to one feature of the present disclosure, there is provided a cosmetic recommendation method performed by the cosmetic recommendation server on a platform having a cosmetic recommendation server that communicates with a plurality of member terminals through a communication network. The cosmetic recommendation method of the present disclosure receives, from one or more member terminals, personal information of a member on the member terminal, wherein the personal information includes at least skin type, age, residence area information, and cosmetic use information of the member. to do; receiving and storing regional environment information on a plurality of regions - among the plurality of regions, the residence region of the member is included; Receiving ingredient and content information of one or more cosmetics, wherein the ingredient and content information includes ingredient and content information of the cosmetic used by the member; generating one or more questions about the use experience according to the use of the used cosmetics, and repeatedly providing the one or more questions to the member terminal according to a predetermined criterion; receiving and storing a series of answers to the provided questions from the member terminal; The personal information of the member, the regional environmental information corresponding to the residential area information of the member, the ingredient and content information of the member's cosmetics used, and the series of questions for the questions received from the member terminal building or updating a cosmetic recommendation learning model through machine learning using a data set including answers; and selecting suitable cosmetics for a predetermined member terminal based on the cosmetic recommendation learning model.

According to an embodiment of the present disclosure, the selecting of suitable cosmetics for the predetermined member terminal includes the personal information on the predetermined member on the predetermined member terminal and the regional environment corresponding to the residence area information of the predetermined member It may include selecting one or more cosmetics for the predetermined member based on the information.

According to an embodiment of the present disclosure, the method may further include providing information on the selected suitable cosmetics to the predetermined member terminal.

According to an embodiment of the present disclosure, the regional environmental information is received from a manager on the cosmetic recommendation server or an external server through the communication network, and the regional environmental information includes temperature, humidity, and altitude for each period of the region. , a water source, and may include at least one information of stocks of residents of the corresponding area.

According to an embodiment of the present disclosure, the series of answers to the provided questions are each expressed as a predetermined numerical value, and the step of receiving and storing the series of answers includes calculating a representative value representing the answers. and storing, wherein the step of building or updating the cosmetic recommendation learning model comprises: the member personal information, the regional environmental information corresponding to the member's residential area information, and ingredient and content information of the cosmetics used; The method may include building or updating the cosmetic recommendation learning model through machine learning using a data set including the representative value representing the series of answers received from the member terminal.

According to an embodiment of the present disclosure, the machine learning may be based on a KNN algorithm.

According to an embodiment of the present disclosure, the step of receiving and storing a series of answers to the provided questions from the member terminal may include: when each answer is received from the member terminal, a predetermined criterion for the member The method may include allocating points according to , and storing information about the allocated points.

According to an embodiment of the present disclosure, the cosmetic recommendation method may further include storing and managing suitable cosmetic information selected for each member terminal associated with each region in each region for a plurality of regions. have.

According to another feature of the present disclosure, there is provided a computer-readable recording medium having one or more instructions recorded therein, wherein the one or more instructions, when executed by a computer, cause the computer to perform any one of the methods described above. A readable recording medium is provided.

According to an embodiment of the present disclosure, as well as the typed skin type of the user. A cosmetic recommendation system capable of recommending cosmetics most suitable for a user based on various environmental information surrounding the user and referring to reviews (reviews) of other users may be provided. Therefore, as a user, it is possible to obtain a recommendation regarding a more suitable cosmetic product, and to reduce worries about cosmetic selection. In addition, the user may accumulate points and obtain economic benefits by actively providing the cosmetic use information possessed by the user on the platform according to the embodiment of the present disclosure.

1 is a diagram schematically illustrating the configuration of a cosmetic recommendation platform 100 according to an embodiment of the present disclosure.
FIG. 2 is a functional block diagram showing a schematic functional configuration of the cosmetic recommendation server 130 of FIG. 1 .
FIG. 3 is a functional block diagram showing a schematic functional configuration of the suitable cosmetic recommendation unit 270 of FIG. 2 .

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Hereinafter, when it is determined that there is a risk of unnecessarily obscuring the subject matter of the present disclosure, detailed descriptions of already known functions and configurations will be omitted. In addition, it should be understood that the contents described below are only related to one embodiment of the present disclosure, and the present disclosure is not limited thereto.

The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. For example, an element expressed in a singular should be understood as a concept including a plurality of elements unless the context clearly means only the singular. In addition, in the specification of the present disclosure, terms such as 'comprise' or 'have' are merely intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and such The use of the term is not intended to exclude the possibility of the presence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

In the embodiments described in the present specification, 'unit' means a functional part that performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware and software. In addition, the plurality of 'units' may be integrated into at least one software module and implemented by at least one processor, except for 'units' that need to be implemented with specific hardware. In addition, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It should be noted that commonly used terms defined in the dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be construed as unduly limited or expanded unless explicitly defined otherwise in the specification of the present disclosure. should know

Hereinafter, with reference to the accompanying drawings, an embodiment of the present disclosure will be described in detail.

1 is a diagram schematically illustrating the configuration of a cosmetic recommendation platform 100 according to an embodiment of the present disclosure. As shown, the cosmetic recommendation platform 100 includes a plurality of member terminals 110 , a communication network 120 , and a cosmetic recommendation server 130 .

According to an embodiment of the present disclosure, each of the plurality of member terminals 110 may be a communication capable terminal possessed by each user who has subscribed to the cosmetic recommendation platform 100 . According to an embodiment of the present disclosure, each of the plurality of member terminals 110 may be, for example, various types of electronic terminals such as a mobile phone, a smartphone, a tablet PC, a desktop, a laptop, and a voice recognition speaker of a platform subscription user. The platform subscription member may communicate with the cosmetic recommendation server 130 and the like through the communication network 120 using their member terminal 110 to provide or obtain various information. According to an embodiment of the present disclosure, each member on the member terminal 110 may be a person who provides his/her cosmetic use experience (review) information to the cosmetic recommendation platform 100 , and receives his/her own from the cosmetic recommendation server 130 . It may be a person who recommends and purchases cosmetics suitable for a person, a seller who sells cosmetics through the cosmetics recommendation server 130, or a person who serves as one or more of them (the present disclosure is not limited thereto).

According to an embodiment of the present disclosure, the communication network 120 may include any wired or wireless communication network, for example, a TCP/IP communication network. According to an embodiment of the present disclosure, the communication network 104 may include, for example, a Wi-Fi network, a LAN network, a WAN network, an Internet network, and the like, but the present disclosure is not limited thereto. According to an embodiment of the present disclosure, the communication network 104 is, for example, Ethernet, GSM, EDGE (Enhanced Data GSM Environment), CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi-MAX, Wibro and any other various wired or wireless wired or wireless Can be implemented using a communication protocol

According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may transmit/receive various types of information between each of the plurality of member terminals 110 through the communication network 120 . According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may receive predetermined information from each member terminal 110 through the communication network 120 or transmit predetermined information to each member terminal 110 . have. According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may store and manage information received from each member terminal 110 . According to an embodiment of the present disclosure, for example, the cosmetic recommendation server 130, from each member terminal 110, the member's personal information on the terminal (eg, ID, password, residence area, age, skin type, occupation, etc.) and various information), used cosmetics information, etc. can be received and stored. According to an embodiment of the present disclosure, for example, the cosmetic recommendation server 130 may continuously receive and store experience (review) information according to the use of a predetermined cosmetic product from each member terminal 110 . According to an embodiment of the present disclosure, the cosmetic recommendation server 130 also provides information input by a manager through a separate manager terminal (not shown) and/or separate external information through the communication network 120 . Information received from a server (not shown) may be stored and managed.

According to an embodiment of the present disclosure, the cosmetic recommendation server 130 collects, stores, and manages various types of information, for example, various information received from the member terminal 110, and received from an administrator and/or an external information providing server. Based on various information and the like, it is possible to build and manage a learning model for recommending the most suitable cosmetics for a user according to a situation through machine learning. According to an embodiment of the present disclosure, the cosmetic recommendation server 130 responds to a cosmetic recommendation request received from a member terminal 110 by using a cosmetic recommendation learning model built by machine learning using the above-described various information. Accordingly, it is possible to provide the most suitable cosmetic information according to the cosmetic recommendation learning model to the member terminal 110 . According to an embodiment of the present disclosure, the cosmetic recommendation server 130, irrespective of the request from the member terminal 110, based on various information accumulated in relation to each member, according to the above-mentioned recommendation learning model The most suitable cosmetics may be selected, and marketing information regarding the selected cosmetics may be provided to the member terminal 110 .

According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may allocate points according to each member's activity on each member terminal 110 and manage them. According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may provide a cosmetic sales service through communication with each member terminal 110 . According to an embodiment of the present disclosure, the cosmetic recommendation server 130 may provide a cosmetic sales service by having a cosmetic information database and a payment processing function by itself, and interworking with a separate cosmetic sales server (not shown). Cosmetics sales service may also be provided through the According to an embodiment of the present disclosure, the points allocated to each member by the aforementioned cosmetic recommendation server 130 may be utilized for a cosmetic sales service through the cosmetic recommendation server 130 .

FIG. 2 is a functional block diagram illustrating a schematic functional configuration of the cosmetic recommendation server 130 of FIG. 1 . As shown, the cosmetic recommendation server 130 includes an information transmission/reception unit 210 , a member information management unit 220 , a local environment information data management unit 230 , a cosmetic ingredient management unit 240 , a review information management unit 250 , It includes a member point management unit 260 , a suitable cosmetic recommendation unit 270 , a cosmetics sales unit 280 , and a marketing management unit 290 .

According to an embodiment of the present disclosure, the information transceiver 210 enables the cosmetic recommendation server 130 to communicate with the outside through the communication network 120 of FIG. 1 . According to an embodiment of the present disclosure, the information transmitting/receiving unit 210 may allow the cosmetic recommendation server 130 to transmit information to the outside or to receive information from the outside according to the protocol of the communication network 120 of FIG. 1 . do. According to an embodiment of the present disclosure, the information transmitting/receiving unit 210 may perform information encryption and decryption functions as necessary when transmitting/receiving information with the outside.

According to an embodiment of the present disclosure, the member information management unit 220 receives various member information transmitted from each member terminal 110 through the communication network 120 of FIG. 1 and the information transmitting and receiving unit 210 described above. and can be stored. For example, when a user on each member terminal 110 joins the cosmetic recommendation platform 100, various personal information, for example, ID, password, residence area, age, skin type, occupation, etc., including various information provided and the member information management unit 220 of the cosmetic recommendation server 130 may store and manage such information for each member account. According to an embodiment of the present disclosure, the residence area information of each member on the member information management unit 220 is linked with each area environment information stored and managed in the area environment information data management unit 230 to be described later, and the respective area Environmental information can be used as information for each member. According to an embodiment of the present disclosure, the member information management unit 220 is also based on information received from the member terminal 110 and/or cosmetic sales information regarding the member terminal 110 made on the cosmetic recommendation platform 100, etc. You can store and manage cosmetic usage history information for each member account. According to an embodiment of the present disclosure, the member information management unit 220, based on the information received from the member terminal 110 and/or cosmetics sales information regarding the member terminal 110 made on the cosmetic recommendation platform 100, etc. You can store and manage the cosmetic information currently in use for each member account.

According to an embodiment of the present disclosure, the local environmental information data management unit 230 may collect and manage environmental information data for each region where the cosmetic recommendation platform 100 is used, for example, each country/region and region. According to an embodiment of the present disclosure, the environmental information for each region includes, for example, various environmental information including temperature, humidity, altitude, water source, and stocks of residents (rice, wheat, corn, etc.) may include According to an embodiment of the present disclosure, the environment information for each region may be input and managed by a manager through a separate manager terminal (not shown), and a separate external information providing server ( not shown) may be received. According to an embodiment of the present disclosure, the environment information for each region may be re-collected and updated every predetermined period and/or whenever appropriate according to the judgment of an administrator. According to an embodiment of the present disclosure, temperature or humidity information among environment information for each region may be periodically obtained in connection with an external weather information providing server.

According to an embodiment of the present disclosure, the cosmetic ingredient management unit 240 may collect and store ingredient information of various cosmetics. For example, various domestic cosmetics are to announce all components and contents according to the law, and according to an embodiment of the present disclosure, the cosmetic component management unit 240 is a separate external providing such cosmetic components and contents. It may collect and store such information from a server (not shown) (the present disclosure is not limited thereto). According to an embodiment of the present disclosure, an administrator may register all ingredients and contents of each cosmetic through the manager terminal, but the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the review information management unit 250 provides cosmetics for each member terminal 110 based on currently used cosmetic information stored and managed for each member account on the member information management unit 210 . You can create and send queries about user experience. According to an embodiment of the present disclosure, the above-described inquiry about the use experience can easily and easily provide information on the experience after each member uses a predetermined cosmetic (eg, changes that occur in the skin after using the predetermined cosmetic). In order to provide it, it may be a question generated and provided by the cosmetic recommendation server 130 . For example, the question and answer criteria generated and provided by the review information management unit 250 may be predetermined for each item (eg, moisturizing item, whitening item, etc.). For example, the question generated and provided by the review information management unit 250 is a numerical answer (1: very dry - 10: very moist) about the moisturizing state of the skin after using the prescribed cosmetics, after using the prescribed cosmetics Numerical answers about how much the skin feels lightened (1: no change - 10: very bright) may be included, and the present disclosure is not limited thereto. According to one embodiment of the present disclosure, the review information management unit 250, in relation to the same cosmetic for the same member terminal 110, asks about the experience of using the above-described cosmetics over time (eg, after one week of use). , after 1 month of use, etc.), it is possible to repeatedly provide and collect answers about it. According to an embodiment of the present disclosure, the review information management unit 250 receives, from each member terminal 110 , each answer to a query related to the use experience provided to each member terminal 110 described above, and , it can be stored and managed. According to an embodiment of the present disclosure, a predetermined point may be provided to each member whenever an answer to the above-described user experience-related query is provided. The points provided for each member may be managed by the member point management unit 260, which will be described later.

According to an embodiment of the present disclosure, the member point management unit 260 collects and manages each point information given to each member according to an activity on the cosmetic recommendation platform 100 through the cosmetic recommendation server 130 . can do. According to an embodiment of the present disclosure, the cosmetic recommendation server 130 is provided as a reward for active activities by each member on each member terminal 110 (eg, providing a sincere answer to the above-described usage experience related query, etc.) , points may be awarded according to a predetermined criterion. According to an embodiment of the present disclosure, as described above, the points accumulated and managed for each member may be utilized for a cosmetic sales service through the cosmetic recommendation server 130 .

According to an embodiment of the present disclosure, the suitable cosmetic recommendation unit 270 may include personal information for each member on the aforementioned member information management unit 220, such as residence area, age, skin type, occupation, use cosmetic history information, etc.; Local environmental information on the local environmental information data management unit 230 corresponding to the above residential area information, each cosmetic ingredient and content information stored on the cosmetic ingredient management unit 230, each collected and stored by the aforementioned review information management unit 250 Cosmetics through machine learning using each member's cosmetic use experience information (the above-mentioned, accumulated answers collected from each member terminal to a query related to the cosmetic use experience provided by the review information management unit 250), etc. Build and update recommended learning models. According to an embodiment of the present disclosure, the suitable cosmetic recommendation unit 270 may utilize, for example, a KNN algorithm as a machine learning algorithm for building a cosmetic recommendation learning model, and the present disclosure is not limited thereto. According to an embodiment of the present disclosure, the suitable cosmetic recommendation unit 270 uses the above-described cosmetic recommendation learning model, and personal information (eg, residence area, age, skin type, occupation, use cosmetic history information) of a predetermined member etc.), according to the local environmental information corresponding to the personal information, etc., it is possible to select the cosmetic ingredients and contents most suitable for the member, and the optimal cosmetics to match them. According to an embodiment of the present disclosure, the suitable cosmetic recommendation unit 270 responds to the cosmetic recommendation request received from the member terminal 110 as described above, and uses the member terminal 110 according to the cosmetic recommendation learning model. The most suitable cosmetic information may be provided (the present disclosure is not limited thereto).

According to an embodiment of the present disclosure, the cosmetic sales unit 280 may provide a cosmetic sales service through communication with each member terminal 110 through the communication network 120 . According to an embodiment of the present disclosure, the cosmetic sales unit 280 may have a cosmetic information database and a payment processing function, and may provide a cosmetic sales service through information transmission/reception with each member terminal 110 . According to another embodiment of the present disclosure, the cosmetic sales unit 280 may provide a link with a separate cosmetic sales server to support cosmetic sales service by transmitting and receiving information between the cosmetic sales server and the member terminal 110 . have.

According to an embodiment of the present disclosure, the marketing management unit 290 may select suitable cosmetics for each member and provide marketing information on the selected cosmetics to the corresponding member terminal 110 . According to an embodiment of the present disclosure, the marketing management unit 290 may select suitable cosmetics for each member based on the cosmetic recommendation learning model on the above-described suitable cosmetic recommendation unit 270 . According to an embodiment of the present disclosure, the marketing management unit 290 may provide marketing information regarding the above-selected cosmetics to each member terminal 110 , and at this time, the reason for selecting the cosmetics (eg, introduction of cosmetic ingredients) etc.) can be provided. According to an embodiment of the present disclosure, the marketing management unit 290 may extract and manage cosmetic ingredients/content and information on each cosmetic that are mainly selected to be suitable for members of the country/region for each country/region. According to an embodiment of the present disclosure, such information may be provided to, for example, a cosmetic company that intends to enter a specific country/region and used to help determine a business direction.

FIG. 3 is a functional block diagram showing a schematic functional configuration of the suitable cosmetic recommendation unit 270 of FIG. 2 . As illustrated, the suitable cosmetic recommendation unit 270 includes a fitness value calculation unit 310 , a fitness learning model unit 320 , and a product recommendation unit 330 .

According to an embodiment of the present disclosure, the suitability value calculation unit 310 provides a series of answers (eg, numerical answers) from a predetermined member to a question repeatedly provided for each item by the review information management unit 230 . ), a representative fitness value can be calculated. According to an embodiment of the present disclosure, the fitness value calculation unit 310 is, for example, given to a certain member a question about the moisturizing item n times as a question about the experience of using a certain cosmetic, and n answers (numerical answers) therefrom. ), it is possible to calculate the fitness value for the moisturizing item in a simple manner as follows (the present disclosure is not limited thereto). Similarly, the fitness value calculation unit 310, for example, when a question about a whitening item is given to a certain member n times as a question about the experience of using a certain cosmetic to a certain member and n answers (numerical answers) are obtained therefrom, the following It is possible to calculate the fitness value for the moisturizing item in a simple manner as shown in (the present disclosure is not limited thereto).

According to an embodiment of the present disclosure, the fitness learning model unit 320 includes at least one or more of personal information for each member on the member information management unit 220 , for example, residence area, age, skin type, occupation, and cosmetic history information used. At least one of information, local environmental information on the local environmental information data management unit 230 corresponding to the above residential area information, and each cosmetic ingredient and content information stored on the cosmetic ingredient management unit 230 as input values, Correspondingly, each member's respective cosmetic use experience information collected and stored by the above-described review information management unit 250 (above, each member terminal for a query about the cosmetic use experience provided by the review information management unit 250) Based on the accumulated answers collected from the above), the data using each fitness value calculated by the fitness value calculation unit 310 as an output value is used as training data to build a cosmetic recommendation learning model through machine learning based on them. and update. According to an embodiment of the present disclosure, the fitness learning model unit 320 may manage the cosmetic recommendation learning model by repeatedly performing learning based on accumulated data at a predetermined time period. According to an embodiment of the present disclosure, the fitness learning model unit 320 may utilize, for example, the KNN algorithm as a machine learning algorithm for building a cosmetic recommendation learning model, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the product recommendation unit 330 uses the cosmetic recommendation learning model built and managed by the fitness learning model unit 320 to provide personal information (eg, residence area, age, Skin type, occupation, information on at least one of history of cosmetics used), local environmental information corresponding to the personal information, etc., the cosmetic ingredient and content most suitable for the member, and the optimal cosmetic product corresponding thereto, can be selected. According to an embodiment of the present disclosure, the product recommendation unit 330, in response to the cosmetic recommendation request received from the member terminal 110, provides the most suitable cosmetic information according to the cosmetic recommendation learning model to the member terminal 110. may be provided (but the present disclosure is not limited thereto).

As will be appreciated by those skilled in the art, the present disclosure is not limited to the examples described herein, and various modifications, reconstructions, and substitutions may be made without departing from the scope of the present disclosure. For example, the various techniques described herein may be implemented by hardware or software, or a combination of hardware and software.

A computer program according to an embodiment of the present disclosure includes a storage medium readable by a computer processor or the like, such as EPROM, EEPROM, non-volatile memory such as flash memory device, magnetic disk such as built-in hard disk and removable disk, magneto-optical disk, and It may be implemented in a form stored in various types of storage media including a CDROM disk. In addition, the program code(s) may be implemented in assembly language or machine language, and may be implemented in a form transmitted through electric wiring, cabling, optical fiber, or any other type of transmission medium. All modifications and variations falling within the true spirit and scope of the present disclosure are intended to be embraced by the following claims.

Claims (9)

A cosmetic recommendation method performed by the cosmetic recommendation server on a platform having a cosmetic recommendation server communicating with a plurality of member terminals through a communication network, the method comprising:
receiving personal information of a member on the member terminal from one or more member terminals, wherein the personal information includes at least skin type, age, residential area information, and cosmetic use information of the member;
receiving and storing regional environment information on a plurality of regions - among the plurality of regions, the residence region of the member is included;
Receiving ingredient and content information of one or more cosmetics, wherein the ingredient and content information includes ingredient and content information of the cosmetic used by the member;
generating one or more questions about the use experience according to the use of the used cosmetics, and repeatedly providing the one or more questions to the member terminal according to a predetermined criterion;
receiving and storing a series of answers to the provided questions from the member terminal;
The personal information of the member, the regional environmental information corresponding to the residential area information of the member, the ingredient and content information of the member's cosmetics used, and the series of questions for the questions received from the member terminal building or updating a cosmetic recommendation learning model through machine learning using a data set including answers; and
and selecting suitable cosmetics for a predetermined member terminal based on the cosmetic recommendation learning model. According to claim 1,
The selecting of suitable cosmetics for the predetermined member terminal may include selecting the predetermined member based on the personal information on the predetermined member on the predetermined member terminal and the regional environment information corresponding to the residence area information of the predetermined member. A cosmetic recommendation method comprising the step of selecting one or more cosmetics for. According to claim 1,
The method of recommending cosmetics further comprising the step of providing information on the selected suitable cosmetics to the predetermined member terminal. According to claim 1,
The regional environment information is received from a manager on the cosmetic recommendation server or an external server through the communication network,
The regional environmental information includes at least one information of temperature, humidity, altitude, water source, and stocks of residents of the region for each period of the region, cosmetic recommendation method. According to claim 1,
The series of answers to the provided questions are each expressed as a predetermined numerical value, and receiving and storing the series of answers includes calculating and storing representative values representing the answers,
In the step of building or updating the cosmetic recommendation learning model, the member personal information, the regional environmental information corresponding to the member residence information, and ingredient and content information of the cosmetic used, and the series received from the member terminal Through machine learning using a data set including the representative value representing the answers of , the cosmetic recommendation method comprising the step of building or updating the cosmetic recommendation learning model. According to claim 1,
The machine learning, based on the KNN algorithm, cosmetic recommendation method. According to claim 1,
The step of receiving and storing, from the member terminal, a series of answers to the provided questions, when each of the answers is received from the member terminal, allocates points according to a predetermined criterion to the member and assigns the allocated points to the member. A cosmetic recommendation method comprising the step of storing information about the points. According to claim 1,
The method further comprising the step of storing and managing suitable cosmetic information selected for each member terminal associated with each region in each region for a plurality of regions. A computer-readable recording medium embodied in one or more instructions, wherein the one or more instructions, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8.

Images