KR102532561B1 - Method for providing consulting data for personal style - Google Patents

Abstract

The present invention relates to a method of providing consulting data on personal style. The method includes obtaining one or more appearance analysis data of a target person, calculating a recommendation degree for each of a plurality of appearance styles based on the obtained one or more appearance analysis data using a recommendation calculation model, calculating The method may include generating consulting data in a preset format including a comment for each of the plurality of appearance styles based on the recommended degree, and providing the generated consulting data through a user terminal.

Description

How to provide consulting data about personal style{METHOD FOR PROVIDING CONSULTING DATA FOR PERSONAL STYLE}

The present disclosure relates to a method of generating and providing consulting data on personal style.

As the keywords of customization and personalization become the standard of consumption, consulting services for personalized styling are emerging prominently. For example, in social media such as YouTube, content related to personalized styling, such as hair styles suitable for a specific face shape, eye lines suitable for specific eyes, and personal colors, is gaining popularity. That is, it can be seen that consumers have a high interest in individual customized styling rather than simply following social trends or trends.

In accordance with the interest of these consumers, the need for personal style consulting is increasing. However, most of the personal style consulting services are conducted offline, are highly influenced by the personal discretion of service providers, and are expensive services with high entry barriers that are limited to one-time use. That is, the personal style consulting service has a problem in that consulting results may be very different for each service provider, and high cost is required because service provision manpower and time are limited.

Embodiments of the present disclosure relate to a method of generating and providing consulting data for a target person's style based on appearance analysis data of the target person in order to solve the above-mentioned problems.

Technical tasks to be achieved in various embodiments are not limited to those mentioned above, and other technical tasks not mentioned are considered by those skilled in the art from various embodiments to be described below. It can be.

The present disclosure may be implemented in a variety of ways including as a method, system, apparatus or computer program stored on a computer readable storage medium.

A method for providing consulting data on a personal style performed by at least one processor according to an embodiment of the present disclosure includes obtaining one or more appearance analysis data of a target person, using a recommendation calculation model, Calculating a recommendation level for each of a plurality of appearance styles based on the obtained one or more appearance analysis data, consulting in a preset format including a comment for each of the plurality of appearance styles based on the calculated recommendation level Generating data and providing the generated consulting data through a first user terminal.

According to various embodiments of the present disclosure, in consulting on personalized styling, it is possible to provide more objective and consistent analysis results as well as analysis results of service providers. For example, with regard to the consulting results, more objective grounds such as absolute figures and proportions of the target person's appearance may be presented together, rather than simply whether or not the target person and specific styling are harmonized from the service provider's point of view. For example, consulting results can be presented based on skeletal characteristics such as eye size, face shape, cheekbone skeleton, and square jaw skeleton.

According to various embodiments of the present disclosure, the consulting process of the service provider can be further simplified by automating the analysis of the absolute value and ratio of the external appearance of the target person. A service provider can save time and money and increase the supply of consulting services, so that many people can use the service quickly and easily.

According to various embodiments of the present disclosure, it is possible to provide consulting results with higher accuracy and satisfaction than in the case of using only the subjective analysis of the service provider by using the analysis result generated on a more objective basis. In addition, consulting data automatically generated by inputting objective analysis data may correspond to objective and consistent consulting data.

According to various embodiments of the present disclosure, a user may be recommended products such as an associated hair designer, make-up product, and clothes that can be styled according to consulting results, along with consulting results.

The effects obtainable from the various embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived to those skilled in the art based on the detailed description below. can be understood

1 is a diagram illustrating an example of providing consulting data on a personal style according to an embodiment of the present disclosure.
2 is a block diagram showing the internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure.
3 is a flowchart illustrating a method of providing consulting data on a personal style according to an embodiment of the present disclosure.
4 is a diagram illustrating an example of consulting data for a hair style according to an embodiment of the present disclosure.
5 is a diagram illustrating an example of consulting data for a makeup style according to an embodiment of the present disclosure.
6 is an example of a recommendation degree calculation model according to an embodiment of the present disclosure.
7 is an example of an appearance analysis model according to an embodiment of the present disclosure.

Hereinafter, specific details for the implementation of the present disclosure will be described in detail with reference to the accompanying drawings. However, in the following description, if there is a risk of unnecessarily obscuring the gist of the present disclosure, detailed descriptions of well-known functions or configurations will be omitted.

In the accompanying drawings, identical or corresponding elements are given the same reference numerals. In addition, in the description of the following embodiments, overlapping descriptions of the same or corresponding components may be omitted. However, omission of a description of a component does not intend that such a component is not included in an embodiment.

Advantages and features of the disclosed embodiments, and methods of achieving them, will become apparent with reference to the following embodiments in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms, but only the present embodiments make the present disclosure complete, and the present disclosure does not extend the scope of the invention to those skilled in the art. It is provided only for complete information.

The terms used in this specification have been selected from general terms that are currently widely used as much as possible while considering the functions in the present disclosure, but they may vary according to the intention of a person skilled in the related field, a precedent, or the emergence of new technology. In addition, in a specific case, there is also a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the invention. Therefore, the terms used in the present disclosure should be defined based on the meaning of the terms and the general content of the present disclosure, not simply the names of the terms.

Expressions in the singular number in this specification include plural expressions unless the context clearly dictates that they are singular. Also, plural expressions include singular expressions unless the context clearly specifies that they are plural. When it is said that a certain part includes a certain component in the entire specification, it means that other components may be further included without excluding other components unless otherwise stated.

In addition, the term 'unit' or 'module' used in the specification means a software or hardware component and performs certain roles. However, 'unit' or 'module' is not meant to be limited to software or hardware. A 'unit' or 'module' may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors.

In the present disclosure, 'appearance style' may include aesthetic elements (eg, decorative elements) that can be visually applied to the appearance of a person. For example, the appearance style may include a hair style, a makeup style, a fashion style, and the like, but is not limited thereto. 'Style' can be used interchangeably with 'external style' in the same meaning.

In the present disclosure, 'appearance analysis data' may include data on a person's appearance that may affect aesthetic harmony with an appearance style. For example, the appearance analysis data may include data on a person's face shape, lower body shape, features, neck shape, body shape, shoulder shape, upper body shape, lower body shape, pelvis shape, waist shape, height and weight, etc. there is. Here, the appearance analysis data may include data on the numerical value, ratio, type, and/or shape of the external appearance.

In the present disclosure, a 'product' may refer to goods and/or services that a user may purchase, rent, and/or use. Also, 'a product for a specific external style' may refer to a product that can be used to apply a specific external style. For example, products may refer to products such as cosmetics, clothes, shoes, hats, hair accessories, and dyes. As another example, a product may refer to a service related to styling, such as a hair styling service, a fashion styling service, and a makeup service. In one embodiment, a product may refer to goods and/or services provided by a specific provider (or a specific company). In this case, products may be classified according to providers (or companies) that provide products and/or services. For example, even in the same treatment service called 'setting perm', the setting perm of the first hair designer (or the first hair shop) and the setting perm of the second hair designer (or the second hair shop) may correspond to different products. can

Hereinafter, with reference to the accompanying drawings, embodiments will be described in detail so that those skilled in the art can easily carry out the embodiments.

1 is a diagram illustrating an example of providing consulting data on a personal style according to an embodiment of the present disclosure. The user 120 may request a personal style consulting service through the user terminal 110 . The information processing system may receive a request for a consulting service from the user terminal 110 . Here, the information processing system may include one or more electronic devices and/or one or more servers configured to provide consulting services. The user 120 may transmit data about the user's appearance to the information processing system in order to receive a consulting service on personal style.

In one embodiment, the user 120 may provide a picture including the user's appearance taken through an image input device such as a camera to the information processing system as image data for a consulting service. For example, the user 120 may transmit image data obtained by photographing the user's appearance according to the preset guide 132 to the information processing system. The user 120 may receive consulting data having higher accuracy by providing image data taken according to a preset guide 132 . Additionally or alternatively, the user 120 may select some of the pre-stored photos and provide them to the information processing system as image data for a consulting service. In this case, the information processing system may extract the appearance analysis data of the user 120 from the image data and use it to generate consulting data.

In one embodiment, the user 120 may directly input data about appearance. That is, the user 120 may provide an answer to a question related to appearance to the information processing system as appearance analysis data. For example, the user 120 may provide numerical values (eg, nose length, etc.), proportions (eg, upper/middle/lower eye ratio, long nose, etc.) and/or shape (eg, oval shape, round shape, inverted triangle, etc.) etc.) can be input and provided to the information processing system as appearance analysis data. The user 120 can increase the accuracy of personal style consulting by providing both image data including the user's appearance and data on the directly input appearance.

The user 120 may be provided with consulting data generated based on appearance analysis data. In one embodiment, the user 120 may be provided with consulting data in a preset format. For example, the user 120 may be provided with consulting data generated in a predetermined specific format (eg, PDF, JPG, WORD, PPT, mp4, etc.). Additionally or alternatively, the user 120 may be provided with consulting data composed of a predetermined table of contents (eg, greetings, appearance analysis results, appearance style information, styling tips, consulting data interpretation methods, etc.). For example, the consulting data may include a face shape analysis result (eg, heart shape) of the user 120 and a pre-stored comment on the corresponding face shape.

In one embodiment, the consulting data provided to the user 120 may include text content and/or image content (eg, tables, photos, videos, drawings, etc.) associated with an appearance style. Additionally or alternatively, the consulting data may include information about a product associated with a specific appearance style (eg, a recommended appearance style). Accordingly, the user 120 may be provided with information on products related to the recommended style (eg, cosmetics for recommended makeup, styling services of a specific hair designer for recommended hair styling, etc.) along with consulting on the style.

In one embodiment, the consulting data provided to the user 120 may include a link (eg, URL) or code (eg, QR code, etc.) connected to content for a specific appearance style. For example, a link or code may be connected to a website where a tutorial video or the like for a specific appearance style can be viewed or downloaded. Alternatively or additionally, links or code may be directed to web sites (eg, sales sites, reservation sites) and/or applications (eg, merchandise sales/reservation applications) associated with products for a particular appearance style. Accordingly, the user 120 can immediately reserve and purchase a service for applying the recommended style while being provided with a consulting result on the style.

As shown in FIG. 1 , the user 120 may take a picture of the user's face using the camera of the user terminal 110 and provide it as the user's image data. As shown on the first screen 130 , the user 120 may photograph the user's face according to a preset guide 132 . 1 shows only the position of the face as the photographing guide 132, but is not limited thereto. For example, guides may correspond to conditions such as distance between camera and person, position of features, pose, angle (e.g. front, side, 45 degree angle, etc.), background, lighting, location, clothing, camera type, etc. there is. Additionally or alternatively, the guide may include a person's condition (e.g., after washing face, before makeup, visible forehead, etc.), shooting area (e.g., upper body, lower body, full body, face, etc.), close-up area (e.g., eyes). Close-up, eyebrow close-up, mouth close-up, etc.) may correspond to the conditions.

As shown on the second screen 140 , the user 120 may be provided with consulting data on a personal appearance style through the user terminal 110 . Although FIG. 1 shows consulting data in the form of a one-page document including images, graphs, and text, the components, format, configuration, and quantity of consulting data are not limited. In addition, a time difference between a time point when the first screen 130 is displayed on the user terminal 110 and a time point when the second screen 140 is displayed is not limited.

2 is a block diagram showing the internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure. The user terminal 210 may communicate with the information processing system 230 through the network 220 . 2, one user terminal 210 is illustrated as communicating with the information processing system 230 through the network 220, but is not limited thereto. Also, the user terminal 210 and the information processing system 230 may include more components than those shown in FIG. 2 .

The network 220 may be configured to enable communication between the user terminal 210 and the information processing system 230 . Depending on the installation environment, the network 220 may be, for example, a wired network such as Ethernet, a wired home network (Power Line Communication), telephone line communication and RS-serial communication, a mobile communication network, a WLAN (Wireless LAN), Wi It may consist of a wireless network such as -Fi or a combination thereof. The communication method is not limited, and may include a communication method utilizing a communication network (eg, a mobile communication network, wired/wireless Internet, satellite network, etc.) that the network 220 may include, but is not limited thereto. For example, the network 220 may include one or more arbitrary networks among networks such as a local area network (LAN), a wide area network (WAN), and the Internet, but is not limited thereto.

The user terminal 210 may be any computing device capable of wired/wireless communication, receiving data from a user and transmitting the data to the information processing system 230 or providing consulting data to the user. As shown, the user terminal 210 may include a memory 212 , a processor 214 , a communication module 216 and an input/output interface 218 . For example, the user terminal 210 includes a mobile phone, a desktop computer, a laptop computer, a television, a tablet computer, a wearable device, a virtual reality (VR) device, and an augmented reality (AR) device. can do.

Similarly, information processing system 230 may include memory 232 , processor 234 , communication module 236 and input/output interface 238 . As shown in FIG. 2, the user terminal 210 and the information processing system 230 are configured to communicate information and/or data through the network 220 using respective communication modules 216 and 236. It can be. In addition, the input/output device 219 may be configured to input information and/or data to the user terminal 210 through the input/output interface 218 or output information and/or data generated from the user terminal 210.

The memories 212 and 232 may include any non-transitory computer readable media. In one embodiment, the memories 212 and 232 may include a permanent mass storage device such as random access memory (RAM), read only memory (ROM), solid state drive (SSD), or the like. . As another example, a non-perishable mass storage device such as a ROM or SSD may be included in the user terminal 210 or the information processing system 230 as a separate permanent storage device separate from memory. Also, an operating system and at least one program code (eg, a code for a personal style consulting service, etc.) may be stored in the memories 212 and 232 .

The software components may be loaded from a computer-readable recording medium separate from the memories 212 and 232 (for example, a recording medium connectable to the user terminal 210 and the information processing system 230). Alternatively, the software components may be loaded into the memories 212 and 232 through a communication module rather than a computer-readable recording medium. For example, the at least one program is a memory (eg, an appearance analysis program, a personal style consulting program, etc.) installed by developers or files provided by the file distribution system through the network 220. 212, 232).

The processors 214 and 234 may be configured to process commands of a computer program (eg, commands received according to program codes, etc.) by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to processors 214 and 234 by memory 212 and 232 or communication modules 216 and 236 . The communication modules 216 and 236 may provide configurations or functions for the user terminal 210 and the information processing system 230 to communicate with each other through the network 220, and the user terminal 210 and/or information processing. System 230 may provide configurations or functions for communicating with other user terminals or other systems (eg, separate cloud systems, etc.).

The input/output interface 218 may be a means for interfacing with the input/output device 219 . As an example, the input device may include a device such as a keyboard, a microphone, a mouse, and a camera including an image sensor, and the output device may include a device such as a display and a speaker. As another example, the input/output interface 218 may be a means for interface with a device in which a configuration or function for performing input and output is integrated into one, such as a touch screen. Although the input/output device 219 is shown not to be included in the user terminal 210 in FIG. 2, it is not limited thereto, and the user terminal 210 and the user terminal 210 may be configured as one device.

The processor 214 of the user terminal 210 may provide a request for consulting data input from the user through the input device to the information processing system 230 through the communication module 216 and the network 220 . In addition, the processor 214 of the user terminal 210 provides the user's appearance analysis data and/or image data input through the input device to the information processing system 230 through the communication module 216 and the network 220. can do.

The processor 234 of the information processing system 230 may be configured to manage, process, and/or store information and/or data received from the user terminal 210 and/or a plurality of external systems. In order to provide consulting data on personal style, the processor 234 of the information processing system 230 may include an appearance analysis unit 240, a recommendation calculation unit 242, and a consulting data generation unit 244. , but not limited thereto.

In one embodiment, the appearance analysis unit 240 may obtain one or more appearance analysis data of the target person. For example, the appearance analyzer 240 may receive appearance data input through an input device of the user terminal 210 as appearance analysis data for a target person. Additionally or alternatively, the appearance analysis unit 240 may receive one or more image data of the target person input through an input device of the user terminal 210 or stored in the memory 212 . In this case, the appearance analysis unit 240 may extract one or more appearance analysis data from one or more image data using the appearance analysis model.

The recommendation calculation unit 242 may receive one or more appearance analysis data of the target person from the appearance analysis unit 240 . The recommendation degree calculation unit 242 may calculate a recommendation degree for each of a plurality of appearance styles based on one or more appearance analysis data using a recommendation degree calculation model. Here, the plurality of appearance styles may correspond to appearance styles previously stored in the memory 232 of the information processing system 230 .

The consulting data generation unit 244 may generate consulting data in a preset format including comments for each of a plurality of appearance styles based on the recommendation level calculated by the recommendation level calculation unit 242 . Consulting data generated in this way may be provided to the user terminal 210 through the communication modules 216 and 236 and the network 220 . The processor 214 of the user terminal 210 may output the provided consulting data through an output device such as a display output device (eg, a touch screen, a display, etc.) or an audio output device (eg, a speaker).

3 is a flowchart illustrating a method of providing consulting data on a personal style according to an embodiment of the present disclosure. The method 300 for providing consulting data on personal style may be executed by at least one processor (eg, processor 234). As shown, the method 300 of providing consulting data on personal style may start with acquiring one or more appearance analysis data of a target person (S310).

In one embodiment, the processor may receive one or more appearance analysis data directly input by the first user (eg, target person) from the first user terminal. For example, the processor may receive data about the numerical value, type, shape, ratio, etc. of the target person's appearance input by the user. That is, the processor may receive data on height, weight, face shape, lower body shape, features, neck shape (eg, no neck), shoulder shape (eg, right shoulder), etc. input by the user as appearance analysis data. .

In one embodiment, the processor may receive one or more image data of the first user from the first user terminal. In this case, the processor may extract one or more shape analysis data from the received one or more image data using the shape analysis model. Here, the one or more image data may be image data captured according to a preset guide. Additionally or alternatively, the processor provides one or more image data of the first user to a second user terminal (eg, a service provider terminal) and then receives one or more appearance analysis data of the first user from the second user terminal. can do.

Here, the appearance analysis model may include an algorithm learned or configured to extract one or more appearance analysis data from image data including the appearance of a person, a neural network model, and/or a machine learning model. For example, the appearance analysis model may include an algorithm and/or model that is learned or configured to extract data about a face shape, a lower jaw shape, a features shape, a neck shape, a shoulder shape, and the like from image data.

Additionally or alternatively, the processor determines that the person is not included in the received image data, the appearance analysis data is not extracted from the image data, the appearance analysis data is determined to be less accurate, and/or the image data When it is determined that the difference between the appearance analysis data extracted from and the appearance analysis data input by the user is greater than a threshold value, data re-input and/or image recapture may be requested through the user terminal.

Then, in step S320, the processor may calculate a recommendation degree for each of a plurality of appearance styles based on one or more appearance analysis data by using a recommendation calculation model. Here, the plurality of appearance styles may include a plurality of hair styles, a plurality of makeup styles, and/or a plurality of fashion styles. Also, the plurality of appearance styles may include styles previously stored in a storage device such as a memory, and the plurality of appearance styles may be continuously updated.

Then, in step S330, the processor may generate consulting data in a preset format including a comment for each of the plurality of appearance styles based on the recommendation degree for each of the plurality of appearance styles. In an embodiment, the processor may receive a comment on at least one appearance style among a plurality of appearance styles from the second user terminal. To this end, the processor may provide the second user terminal with at least one of a recommendation for each of a plurality of appearance styles, image data of the first user, and appearance analysis data of the first user. The second user may directly input a comment on at least one appearance style among a plurality of appearance styles using data provided through the second user terminal and provide the comment to the processor.

Additionally or alternatively, the processor may generate consulting data including comments pre-stored in a memory according to a recommendation level for each of a plurality of appearance styles. That is, for each of the plurality of appearance styles, comments corresponding to the recommendation level and/or appearance analysis data may be pre-stored in the memory. That is, the comment for each of the plurality of appearance styles may include a comment directly input by the second user and/or a pre-stored comment.

Next, in step S340, the processor may provide the generated consulting data through the first user terminal. Additionally, the processor may determine at least one product among a plurality of products as a recommended product based on the generated consulting data. Then, the processor may provide information on the determined recommended product through the first user terminal. For example, the processor may determine a recommended hair designer from among a plurality of hair designers based on the consulting data and provide information (eg, review, reservation information, etc.) on the recommended hair designer through the first user terminal.

4 is a diagram illustrating an example of consulting data for a hair style according to an embodiment of the present disclosure. A processor (eg, the processor 234) may calculate a recommendation rate for each of a plurality of hair styles based on one or more appearance analysis data using a recommendation calculation model. Then, the processor may generate consulting data in a preset format (eg, data table) including comments for each of a plurality of hair styles. The embodiments of the hair style of FIG. 4 may also be applied to consulting data for other arbitrary styles such as makeup style and fashion style.

One or more appearance analysis data used to calculate a recommendation for a hairstyle includes facial shape (e.g., 33 face types, sunken temples, forehead width, hairline shape, upper/middle/lower face ratio, philtrum length) and parietal length), lower jaw shape (eg, including at least one of lower jaw ratio, lower jaw shape, chin angle, protruding chin, short chin, and dwarf mandible), feature shape (eg, size of features, ratio of features) , shape, nose tip width, mouth width, and mouth protrusion), neck shape (e.g., including neck length), and shoulder shape (e.g., shoulder width, trapezius presence, trapezius size, shoulder angle, and shoulder shape) data for at least one of (including at least one), but is not limited thereto, and may include all appearance data that may affect aesthetic harmony with a hair style.

A plurality of hairstyles may be classified into one or more categories. For example, a plurality of hair styles may be classified to include at least one of a 'bang hair style', a 'back hair style', a 'side hair style', and a 'bundle hair style' according to a styling area. Additionally or alternatively, the plurality of hair styles may be classified to include at least one of a 'perm style', a 'cut style', a 'bundled hair style' and a 'dyeing style' according to the procedure. In addition, a plurality of hair styles may be classified into a category including at least one of Time, Place, Occasion (TPO), age, gender, country, cost, and atmosphere, but is not limited thereto.

Hair style consulting data 400 shown in FIG. 4 includes basic information 402 about a first hairstyle (eg, 'full bangs'), mood information 404 about the first hair style, and recommendation 406 ) and comments 408 . For example, the consulting data 400 is a service provider based on the recommendation 406, the target person's image data and / or the target person's appearance analysis data. It is not recommended because it makes it look ugly.' Additionally or alternatively, the comment 408 may include a pre-stored sentence corresponding to the recommendation 406 and/or appearance analysis data.

The basic information 402 about the style may include style characteristics, styling methods, example images, and the like. In FIG. 4 , the recommendation 406 is indicated by a star score, but is not limited thereto, and may be displayed in various ways such as a numerical value, percentage, top, middle, bottom, or ranking. Additionally, the consulting data 400 may further include at least one appearance style among a plurality of appearance styles (eg, a recommended appearance style) and a composite image of the target person.

The mood information 404 may correspond to predefined information for a corresponding style. In FIG. 4, the mood information 404 is a horizontal graph represented by eight levels of scoring for five moods (eg, including at least one of individuality, elegance/calmness, degree/chic, innocence, and lovely). It is indicated as, but is not limited thereto. For example, the mood information may include information on an arbitrary number of moods, and the mood information may be displayed through various methods such as a circle graph, each graph, numerical values, and percentages. In addition, the consulting data 400 may include image content, graph content, text content, video content, links, etc., but is not limited thereto, and may include all types of content.

5 is a diagram illustrating an example of consulting data for a makeup style according to an embodiment of the present disclosure. A processor (eg, the processor 234) may calculate a recommendation degree for each of a plurality of makeup styles based on one or more appearance analysis data of a target person using a recommendation calculation model and a recommendation weight to be described later. Then, the processor may generate consulting data in a preset format including a comment for each of a plurality of makeup styles based on the calculated recommendation. The embodiments of the makeup style of FIG. 5 can also be applied to consulting data for other arbitrary styles such as hair style and fashion style.

One or more appearance analysis data used to generate consulting data for makeup style includes face shape (face shape, face ratio, whether or not temples are sunken, forehead shape/width, upper/middle/lower face ratio, philtrum length, crown length, and At least one type data of glabellar length), lower crown shape (including lower crown ratio, lower crown shape, chin angle, angled chin, protruding chin, short chin, and dwarf mandible), eye shape (eyelids, Type data of at least one of the presence or absence of double eyelids, shape of double eyelids, shape of double eyelids, thickness of double eyelids, position of the tail of the eyes, shape of the outer corners of the eyes, shape of the front of the eyes, and whether or not there are 300 eyes), nose shape (whether the nostrils are upturned, the size of the nostrils, the nose ratio, and the bridge of the nose) It may include a plurality of shape data including at least one of height) and mouth shape (including at least one type data of lip thickness, lip color, lip shape, and lip tail shape), It is not limited thereto, and may include all appearance data that may affect aesthetic harmony with a makeup style.

Here, the aesthetic harmony with the makeup style may be different according to age, fashion, or region. In addition, when a specific type included in the appearance analysis data (eg, face shape) has a higher recommendation weight than other types, it may be determined as data affecting aesthetic harmony. For example, in an era in which the first type of eye shape (eg, 'big eyes') is the criterion for beauty, when the recommended weight assigned to the first type is set higher than the other types, the target person's eye size Based on this, a recommendation degree can be calculated. As another example, in a country where the second type (eg, 'angular chin') is the standard of beauty, a recommendation degree may be calculated based on the shape of the lower lip of the target person.

A plurality of makeup styles can be classified into one or more categories. For example, a plurality of makeup styles may include 'base makeup', 'eye makeup', 'eye line makeup', 'fore-eye makeup', 'triangular zone makeup', and 'eye makeup' according to the makeup area and/or stage. , 'eye makeup', 'lip makeup', 'mouth makeup', 'chin makeup', 'nose makeup', 'cheek makeup', 'shading/highlighting makeup', 'T-zone makeup', 'eyebrow makeup' and 'hair makeup' It can be classified to include at least one of 'line makeup'.

The makeup style consulting data 500 shown in FIG. 5 includes basic information 502, recommendation 504, and comments 506 on 'eyeline drawn in a date' classified as 'eyeline makeup' according to the makeup area. can include For example, in the 'eyeline drawn in a straight line', the straight line in the pre-stored 'thin double eyelid' corresponding to the appearance analysis data of 'thin double eyelid' and the recommendation 504 of '3 stars' is the best for the shape of the eyes. It's a line that can be saved.' A comment 506 may be provided. That is, the consulting data may include comments that are automatically matched based on appearance analysis data and a recommendation level for a specific style. Alternatively, the consulting data may include comments generated based on specific style and appearance analysis data by a model configured (or learned) to automatically generate sentences using input data. Additionally or alternatively, the consulting data may include a recommendation 406 for 'eyeline drawn in a straight line', a comment made by the service provider based on the target person's image data and/or the target person's appearance analysis data. there is.

In one embodiment, the consulting data may include information (eg, a styling method, etc.) about an appearance style (eg, a custom shading style) configured by a second user (ie, a service provider) as a custom configuration for the first user. To this end, the processor provides at least one of image data of the first user and/or appearance analysis data of the first user to the second user terminal, and then receives an appearance style customized for the first user from the second user terminal. can do.

6 is an example of a recommendation degree calculation model according to an embodiment of the present disclosure. The recommendation calculation model may correspond to one or more neural network models 601 . In an embodiment, the recommendation calculation model may correspond to a neural network model 601 trained and/or unsupervised to calculate a recommendation 603 for an appearance style according to an input of the appearance analysis data 600 . can For example, the recommendation calculation model may correspond to a supervised neural network model 601 using one or more learning appearance analysis data and corresponding answer data (eg, a recommendation score for appearance style, etc.). . This neural network model 601 may be stored in the memory of the information processing system 230 and/or an external storage device.

In one embodiment, the information processing system 230 uses one or more neural network models 601 to recommend a plurality of appearance styles 603 based on one or more appearance analysis data 600 of the target person. ) can be calculated. Here, the appearance analysis data 600 input according to the type of appearance style may be partially different. Also, the recommendation calculation model may include a neural network model 601 learned using different learning data according to the type of appearance style.

For example, the appearance analysis data 600 input to calculate the recommendation 603 for each of a plurality of fashion styles includes a face shape, a lower crown shape, a features shape, a neck shape (eg, neck length/thickness and trapezius muscle) including at least one of presence/size), body shape (e.g., hourglass shape, rectangle, triangle, and inverted triangle, etc.), shoulder shape (e.g., shoulder width, etc.), upper body shape (e.g., arm circumference and presence/absence of arm flesh), at least (including one), lower body and pelvis shape (e.g., including at least one of the following: presence/width of femur, presence/width of pelvis, and presence/absence of equestrian ribs), other lower body characteristics (e.g., thigh size, calf shape, ankle size, etc.), waist Shape (e.g. presence/absence of full waist, etc.), upper/lower body and body proportions (e.g. waist length, ratio of waist to upper body, leg length, ratio of legs to total height, calf length, ratio of calves to lower body, etc.) ) may include data on at least one of height and weight. Here, a plurality of fashion styles may be classified into one or more categories (eg, top/bottom).

Additionally, the information processing system 230 uses a recommendation rate calculation model to calculate the recommendation rate 603 for each of a plurality of appearance styles, the basic information of the target person (eg, gender, age, occupation, place of residence, etc.), Image data, additional information (eg, complex information, etc.) can be further used. For example, the information processing system 230 may assign a weight or priority to appearance analysis data associated with a complex of a target person among a plurality of appearance analysis data in calculating the recommendation level 603 . In this case, a high recommendation rate of a style that can complement the appearance complex of the target person can be calculated.

Referring to FIG. 6 , a neural network model 601 may be implemented after one or more appearance analysis data 600 of a target person are obtained. The neural network model 601 according to the embodiments may be referred to as an artificial intelligence model. A neural network model 601 according to embodiments may include one or more hidden layers 602 . For example, one or more hidden layers may be simple linear layers, and may be formed by convolutional neural networks (CNNs), recurrent neural networks (RNNs), and/or long short-term memory models (LSTMs). It may be a set of configured layers.

In one embodiment, the recommendation calculation model may correspond to an algorithm model configured to determine a plurality of appearance styles according to priority of a plurality of logics with respect to a plurality of appearance analysis data. The model used to calculate the recommendation level 603 is not limited to the above example.

7 is an example of an appearance analysis model according to an embodiment of the present disclosure. The appearance analysis model may correspond to one or more neural network models 701 . In an embodiment, the appearance analysis model may correspond to a neural network model 701 trained and/or unsupervised to extract one or more appearance analysis data 703 from one or more image data 700 including a person. can For example, the appearance analysis model may correspond to a neural network model 701 trained using one or more training image data and corresponding answer data. Here, the training image data may correspond to a plurality of image data captured according to a preset guide. This neural network model 701 may be stored in the memory of the information processing system 230 and/or an external storage device.

In one embodiment, the information processing system 230 may extract one or more appearance analysis data 703 from one or more image data 700 including the target person by using the neural network model 701 . Here, the extracted appearance analysis data 703 may be different according to the type of consulting data (that is, the type of appearance style) that the information processing system 230 intends to generate. Here, one or more image data 700 including the target person is captured according to a preset guide, and may be captured according to the same guide as the training image data.

The neural network model 701 shown in FIG. 7 may be implemented after one or more image data 700 are received. The neural network model 701 according to the embodiments may be referred to as an artificial intelligence model. A neural network model 701 according to embodiments may include one or more hidden layers 702 . For example, one or more hidden layers may be a simple linear layer or a set of layers composed of CNNs, RNNs, and/or LSTMs.

The above method may be provided as a computer program stored in a computer readable recording medium to be executed on a computer. The medium may continuously store programs executable by a computer or temporarily store them for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or combined hardware, but is not limited to a medium directly connected to a certain computer system, and may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROM and DVD, magneto-optical media such as floptical disks, and ROM, RAM, flash memory, etc. configured to store program instructions. In addition, examples of other media include recording media or storage media managed by an app store that distributes applications, a site that supplies or distributes various other software, and a server.

The methods, acts or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or combinations thereof. The various illustrative logical blocks, modules, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and the design requirements imposed on the overall system.

In a hardware implementation, the processing units used to perform the techniques may include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs) ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, and other electronic units designed to perform the functions described in this disclosure. , a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be incorporated into a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed in any combination of things designed to perform the described functions. A general purpose processor may be a microprocessor, but in the alternative may be any conventional processor, controller, microcontroller or state machine.

In firmware and/or software implementation, the techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), PROM ( on a computer readable medium, such as programmable read-only memory (EPROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage device, or the like. It can also be implemented as stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

Although the embodiments described above have been described as utilizing aspects of the presently-disclosed subject matter in one or more stand-alone computer systems, the disclosure is not limited thereto and may be implemented in conjunction with any computing environment, such as a network or distributed computing environment. .

Although the present disclosure has been described in relation to some embodiments in this specification, various modifications and changes may be made without departing from the scope of the present disclosure that can be understood by those skilled in the art. Moreover, such modifications and variations are intended to fall within the scope of the claims appended hereto.

Claims (7)

A method for providing consulting data on personal style performed by at least one processor, comprising:
obtaining one or more appearance analysis data including a plurality of shape data of the target person;
The plurality of shape data includes at least one type data in which a recommendation weight of one type is set higher than the other types, and based on the one or more appearance analysis data obtained by using a recommendation calculation model and the recommendation weight Calculating a recommendation degree for each of a plurality of appearance styles;
generating a comment for each of the plurality of appearance styles based on the calculated recommendation level;
generating consulting data in a preset format including the calculated recommendation degree and the comment; and
Providing the generated consulting data through a first user terminal;
In the step of obtaining the one or more appearance analysis data,
The appearance analysis data,
Lower body characteristics including thigh thickness, calf shape and ankle thickness, waist shape including presence or absence of waist, waist length, waist to upper body ratio, calf length, leg to total height, and calf to lower body include the ratio,
The step of calculating the recommendation degree,
receiving basic information, image data, and complex information of the target person;
assigning priority to appearance analysis data associated with complex information of the target person among the plurality of shape data; and
The recommendation rate of a style that can complement the appearance complex of the target person is determined by using the recommendation calculation model configured to determine the recommendation order of a plurality of appearance styles according to the priority of the appearance analysis data. step that yields higher than
Characterized in that it further comprises, the method. According to claim 1,
Obtaining one or more appearance analysis data of the target person,
receiving one or more image data of the target person; and
Extracting the one or more appearance analysis data from the received one or more image data using an appearance analysis model;
The received one or more image data is image data captured according to a preset guide. According to claim 1,
The plurality of appearance styles include a plurality of hairstyles classified into one or more categories,
The one or more appearance analysis data includes data on at least one of a face shape, a lower crown shape, a features shape, a neck shape, and a shoulder shape. According to claim 1,
The plurality of appearance styles include a plurality of makeup styles classified into one or more categories,
The one or more appearance analysis data includes data on at least one of a face shape, a lower lip shape, an eye shape, and a mouth shape. According to claim 1,
The plurality of appearance styles include a plurality of fashion styles classified into one or more categories,
The one or more appearance analysis data includes data on at least one of face shape, lower body shape, features shape, neck shape, body shape, shoulder shape, upper body shape, lower body shape, pelvis shape, body proportion, height and weight, method. According to claim 1,
determining at least one product among a plurality of products as a recommended product based on the generated consulting data; and
The method further comprising providing information on the recommended product through the first user terminal. According to claim 1,
The step of generating consulting data in a preset format including the calculated recommendation and comments,
receiving a comment on at least one of the plurality of appearance styles from a second user terminal; and
and generating consulting data in a preset format including a comment on the received at least one appearance style.

Images