KR20240095585A - Apparatus and method for providing judgment information on fashion item purchase using virtual wardrobe - Google Patents

Abstract

This specification relates to a method, device, and program for providing decision information for purchasing fashion items using a virtual wardrobe. The method includes registering a first image of a fashion item selected by a user as a held fashion item in a virtual wardrobe; Receiving a second video of a purchased fashion item that the user wants to purchase; Comparing the first image and the second image to calculate a similarity score; and determining similarity between the purchased fashion item and the owned fashion item based on the similarity score, and if the two fashion items are determined to be similar to each other, outputting the similarity score and the first image to the user terminal to purchase the purchase. Providing purchase judgment information about a fashion item, and if it is determined that the two fashion items are not similar to each other, searching for a fashion item similar to the purchased fashion item, and then outputting coordination information related to the similar fashion item. Includes ;

Description

Apparatus and method for providing judgment information on purchasing fashion items using a virtual wardrobe {APPARATUS AND METHOD FOR PROVIDING JUDGMENT INFORMATION ON FASHION ITEM PURCHASE USING VIRTUAL WARDROBE}

This specification relates to a method and device for providing decision information helpful in purchasing a new fashion item to be purchased using a virtual closet storing owned fashion items.

People are very interested in fashion for self-satisfaction or to express themselves. To achieve this, people purchase various fashion items such as clothing, accessories, shoes, hats, and bags, and then wear these fashion items in various combinations. However, people sometimes impulsively buy fashion items or fashion items that they wear less often because they decide they do not suit them after wearing them a few times and end up being left in the closet. Additionally, because people do not know all the fashion items they own, they often repeat the mistake of purchasing similar fashion items to the fashion items they own.

To prevent these mistakes, a service is being provided to manage fashion items by providing a virtual wardrobe in the form of a smartphone app. Korea Patent Publication No. 10-2022-0105306 discloses technology related to this virtual closet service.

The content described above is only intended to help understand the background technology of the technical ideas of the present invention, and therefore, it cannot be understood as content corresponding to prior art known to those skilled in the art of the present invention.

Korean Patent Publication No. 10-2022-0105306, 2022.07.27.

This specification is intended to solve the above-described problem, and an embodiment of the present specification compares the similarity between a fashion item to be purchased using a virtual wardrobe and a fashion item already held in the virtual wardrobe to determine the user's purchase. The purpose is to provide helpful information.

In addition, an embodiment of the present specification assists the user in purchasing based on the similarity between the fashion item to be purchased using a virtual wardrobe and the fashion item already held in the virtual wardrobe, as well as the frequency of wearing similar fashion items. The purpose is to provide useful information.

In addition, an embodiment of the present specification allows the user to purchase based on the similarity between the fashion item to be purchased using the virtual wardrobe and the fashion item already held in the virtual wardrobe, as well as the user's evaluation information regarding similar fashion items. The purpose is to provide helpful information.

In addition, an embodiment of the present specification not only shows the similarity between the fashion item to be purchased using a virtual wardrobe and the fashion item already held in the virtual wardrobe, but also coordinates videos collected through SNS related to similar fashion items. The purpose is to provide information that is helpful to users in making purchases.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

This specification presents a method of providing decision information for purchasing fashion items using a virtual wardrobe. The method of providing decision information on purchasing a fashion item using the virtual wardrobe includes registering a first image of a fashion item selected by a user as a held fashion item in the virtual wardrobe; Receiving a second video of a purchased fashion item that the user wants to purchase; Comparing the first image and the second image to calculate a similarity score; and determining similarity between the purchased fashion item and the owned fashion item based on the similarity score, and if the two fashion items are determined to be similar to each other, outputting the similarity score and the first image to the user terminal to purchase the purchase. Providing purchase judgment information about a fashion item, and if it is determined that the two fashion items are not similar to each other, searching for a fashion item similar to the purchased fashion item, and then outputting coordination information related to the similar fashion item. May include ;.

The method for providing judgment information for purchasing fashion items using the virtual wardrobe and other embodiments may include the following features.

Depending on the embodiment, the step of calculating a similarity score by comparing the first image and the second image includes comparing the first image and the second image to an artificial intelligence model that extracts the characteristics of the fashion item from the image for the input fashion item. Inputting a second image and extracting features of a fashion item corresponding to the first image and features of a fashion item corresponding to the second image; and calculate a first feature value for the feature of the fashion item corresponding to the first image and a second feature value for the feature of the fashion item corresponding to the second image, and calculate the first feature value and the second feature. It may include comparing values to calculate the similarity score.

According to an embodiment, a method of providing judgment information regarding the purchase of a fashion item using the virtual wardrobe includes, when the two fashion items are determined to be similar to each other, determining whether the user is wearing the owned fashion item; The method may further include calculating a wearing frequency of the owned fashion item during a predetermined period based on a date on which wearing of the owned fashion item was confirmed and outputting the result to the user terminal.

According to an embodiment, a method of providing judgment information regarding the purchase of a fashion item using the virtual wardrobe includes, when the two fashion items are determined to be similar to each other, determining whether the user is wearing the owned fashion item; The method may further include calculating a wearing frequency of the owned fashion item during a predetermined period based on a date on which wearing of the owned fashion item was confirmed and outputting the result to the user terminal.

According to an embodiment, a method of providing judgment information regarding the purchase of a fashion item using the virtual wardrobe may include, when the two fashion items are determined to be similar to each other, whether the owned fashion item is eligible for resale based on the wearing frequency. It may further include determining and, when the owned fashion item is selected as a resale target, notifying the user terminal that the purchased fashion item is similar to the fashion item selected as a resale target.

According to an embodiment, a method of providing judgment information about purchasing a fashion item using the virtual wardrobe may include, when the two fashion items are determined to be similar to each other, evaluation information about the first image and the owned fashion item. It may further include outputting to a user terminal, wherein the evaluation information may include a wearing review and a wearing evaluation score for the owned fashion item.

Depending on the embodiment, coordination information related to a fashion item similar to the purchased fashion item may be obtained by inputting a third image of the fashion item collected through web crawling into the artificial intelligence model. Extract the features of the fashion item corresponding to, calculate the third feature value for the feature of the fashion item corresponding to the third image, compare the second feature value and the third feature value, and produce the second image. Calculate a second similarity score between the fashion item corresponding to and the fashion item corresponding to the third image, and if the second similarity score corresponds to a second predetermined score standard, the third image or the third image. 3 Video can be obtained as a link to the collected web page.

Meanwhile, this specification presents a device for providing decision information about purchasing fashion items using a virtual wardrobe. The device for providing decision information about purchasing fashion items using the virtual wardrobe includes: a storage unit; display; and a control unit functionally connected to the storage unit and the display, wherein the control unit registers the first image of the fashion item selected by the user as a holding fashion item in the virtual wardrobe created in the storage unit, and Receive a second image of a purchased fashion item desired to be purchased, compare the first image and the second image to calculate a similarity score between the owned fashion item and the purchased fashion item, and based on the similarity score Determine whether the purchased fashion item is similar to the owned fashion item, and if the two fashion items are determined to be similar to each other, output the similarity score and the first image to the user terminal to make a purchase decision for the purchased fashion item. If information is provided and it is determined that the two fashion items are not similar to each other, a fashion item similar to the purchased fashion item may be searched, and then coordination information related to the similar fashion item may be output.

The apparatus for providing judgment information on purchasing fashion items using the virtual wardrobe and other embodiments may include the following features.

Depending on the embodiment, the storage unit includes an artificial intelligence model that extracts features of a fashion item from an image for an input fashion item, and the control unit stores the first image and the second image in the artificial intelligence model. Input to extract the features of the fashion item corresponding to the first image and the features of the fashion item corresponding to the second image, and extract the first feature value for the feature of the fashion item corresponding to the first image and the second A second feature value for the feature of the fashion item corresponding to the image may be calculated, and the similarity score may be calculated by comparing the first feature value and the second feature value.

Depending on the embodiment, if it is determined that the two fashion items are similar to each other, the control unit determines whether the user is wearing the held fashion item, and on the date when wearing the held fashion item is confirmed. Based on this, the frequency of wearing the owned fashion item during a predetermined period can be calculated and output on the display.

According to an embodiment, if it is determined that the two fashion items are similar to each other, the control unit determines whether the owned fashion item is subject to resale based on the wearing frequency, and determines whether the held fashion item is subject to resale. When selected, the fact that the purchased fashion item is similar to the fashion item selected for resale may be output on the display.

According to an embodiment, if it is determined that the two fashion items are similar to each other, the control unit outputs evaluation information about the first image and the owned fashion item to the display, wherein the evaluation information is It may include wearing reviews and wearing evaluation scores for the item.

Depending on the embodiment, if the control unit determines that the two fashion items are not similar to each other, the control unit inputs a third image of the fashion item collected through web crawling into the artificial intelligence model. After extracting the features of the fashion item corresponding to the third image, a third feature value for the feature of the fashion item corresponding to the third image is calculated, and the second feature value and the third feature value are compared. Calculating a second similarity score between the fashion item corresponding to the second image and the fashion item corresponding to the third image, and if the second similarity score corresponds to a second predetermined score standard, the third A link to the web page where the video or the third video was collected can be output on the display.

On the other hand, this specification presents a computer program stored in a computer-readable recording medium to execute each step included in the method of providing decision information for purchasing fashion items using the above-described virtual wardrobe.

Embodiments disclosed herein include the degree of similarity between a fashion item to be purchased using a virtual wardrobe and a fashion item already held in the virtual wardrobe, the frequency of wearing similar fashion items, user evaluation information for similar fashion items, It has the effect of providing information that helps users make purchases, such as coordination videos collected through SNS related to new fashion items.

In addition, the embodiment disclosed in this specification is to compare the similarity between the user's fashion item held in the virtual closet and the new fashion item he or she wants to purchase based on video analysis before the user purchases a new fashion item, and the new fashion item he or she wants to purchase. It has the effect of providing users with information on the frequency of wearing and user evaluation of similar fashion items, and coordination videos similar to new fashion items.

Meanwhile, the effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned above will be clearly understood by those skilled in the art from the description below. You will be able to.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and serve to further understand the technical idea of the present invention along with specific details for carrying out the invention. Therefore, the present invention is described in such drawings. It should not be interpreted as limited to the specific details.
1 is a conceptual diagram of a system for providing judgment information on the purchase of a fashion item using a virtual closet, including a device that performs a method for providing judgment information on the purchase of a fashion item using a virtual closet, according to an embodiment.
Figure 2 shows the configuration of a user terminal according to one embodiment.
Figure 3 shows the configuration of a service server according to one embodiment.
Figures 4 and 5 are flowcharts illustrating a method of providing decision information for purchasing a fashion item using a virtual wardrobe according to an embodiment.

The technology disclosed in this specification can be applied to an apparatus and method for providing decision information for purchasing fashion items using a virtual wardrobe. However, the technology disclosed in this specification is not limited to this and can be applied to all devices and methods to which the technical idea of the technology can be applied.

It should be noted that the technical terms used in this specification are only used to describe specific embodiments and are not intended to limit the spirit of the technology disclosed in this specification. In addition, the technical terms used in this specification, unless specifically defined in a different way in this specification, should be interpreted as meanings generally understood by those skilled in the art in the field to which the technology disclosed in this specification belongs. It should not be interpreted in a very comprehensive sense or in an excessively reduced sense. In addition, if the technical term used in this specification is an incorrect technical term that does not accurately express the idea of the technology disclosed in this specification, it is a technical term that can be correctly understood by a person with ordinary knowledge in the field to which the technology disclosed in this specification belongs. It should be understood and replaced with . Additionally, general terms used in this specification should be interpreted as defined in the dictionary or according to the context, and should not be interpreted in an excessively reduced sense.

Terms containing ordinal numbers, such as first, second, etc., used in this specification may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be referred to as a second component, and similarly, the second component may be referred to as the first component without departing from the scope of the present invention.

Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings. However, identical or similar components will be assigned the same reference numerals regardless of reference numerals, and duplicate descriptions thereof will be omitted.

Additionally, when describing the technology disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the technology disclosed in this specification, the detailed description will be omitted. In addition, it should be noted that the attached drawings are only intended to facilitate easy understanding of the spirit of the technology disclosed in this specification, and should not be construed as limiting the spirit of the technology by the attached drawings.

Videos or images according to an embodiment of the present invention include both still images and moving images, unless there is a special limitation.

Throughout the specification, a device or terminal includes a communication terminal or communication device capable of wired or wireless communication with a server or other device. The form of the device or terminal may be various, such as a mobile phone, smartphone, smart pad, laptop computer, desktop computer, smart TV, wearable device, mirror-shaped display device, smart mirror, etc. Wearable devices can be diverse, such as watch-type terminals, glass-type terminals, HMDs, etc. Additionally, the terminal is not limited to this form and can be implemented with various electronic devices.

Hereinafter, embodiments will be described in detail with reference to the attached drawings.

1 is a conceptual diagram of a system for providing judgment information on the purchase of a fashion item using a virtual closet, including a device that performs a method for providing judgment information on the purchase of a fashion item using a virtual closet, according to an embodiment.

Referring to FIG. 1, a system 10 for providing decision information about purchasing fashion items using a virtual wardrobe according to an embodiment may be configured to include a user terminal 100 and a service server 200.

The decision information provision system 10 for purchasing fashion items using a virtual wardrobe stores images of fashion items such as clothes, shoes, hats, and bags owned by the user in a virtually created virtual wardrobe, and allows the user to create new fashion items. If you want to purchase an item and input a video of a new fashion item, the similarity is calculated by comparing it with the fashion items owned by the user registered in the virtual wardrobe, and then purchase decision information for the new fashion item is provided based on the similarity information. It can mean a system that does.

The user terminal 100 may be implemented as a smart phone, smart pad, tablet PC, personal computer, etc., but is not limited to these forms and may be implemented as various electronic devices. The user terminal 100 can acquire images of fashion items owned by the user through an image capture device such as a camera, store the images in a virtual closet, and manage them.

Additionally, the user terminal 100 may obtain an image of a fashion item that the user wants to newly purchase, captured by the user, through an image capture device such as a camera, and transmit the image to the user server 200.

The service server 200 receives an image of a newly purchased fashion item from the user terminal 100, compares it with the owned fashion item registered in the user's virtual wardrobe, calculates the similarity between the two fashion items, and displays the user terminal ( 100), or the user's frequency of wearing similar fashion items, user evaluation information, coordination videos related to new fashion items, etc. may be provided to the user.

Here, the user's virtual wardrobe may be created in the storage within the user terminal 100, or transmitted from the user terminal 100 to the service server 200 through the network and created and managed for each user within the service server 200. It could be.

Additionally, all functions provided by the service server 200 may be provided as application program functions on the user terminal 100. In this case, the user terminal 100 may process all data needed to perform a method of providing decision information for purchasing a fashion item using a virtual wardrobe within itself without transmitting it to the service server 200.

Therefore, the user of the service providing judgment information regarding the purchase of fashion items using a virtual wardrobe according to this embodiment can clearly identify the fashion items he or she owns at a glance through the virtual wardrobe and find fashion items similar to the fashion items he or she owns. It is possible to prevent duplicate purchases, and to reduce the holding of unnecessary fashion items by preventing the purchase of fashion items that are not worn frequently, that is, of low interest to the user.

Figure 2 shows the configuration of a user terminal according to one embodiment.

The user terminal 100 according to one embodiment can access the application market to download and install a service application, and can also connect to the service server 200 through a network to directly download and install the service application. When a service application is installed, the user terminal 100 may function as a device for providing decision information about purchasing fashion items using a virtual wardrobe while exchanging data with the service server 200 over a network.

Referring to FIG. 2, the user terminal 100 may be configured to include a camera unit 110, a communication unit 120, a control unit 130, a storage unit 140, and a display 150. The illustrated components are not essential, so a user terminal may be implemented as a device for providing decision information about purchasing fashion items using a virtual wardrobe with more components or fewer components. At least some of these components may be implemented in hardware or software, or through a combination of hardware and software.

The camera unit 110 may acquire an image of a fashion item or an image of a user wearing a fashion item through an image sensor such as a charge-coupled device (CCD) or complementary metal oxide semiconductor (CMOS). The display 150 may display an image captured by the camera unit 110 or an image generated by the control unit 130.

The communication unit 120 can connect to the network through a communication module and connect to the service server 200 through the network to exchange data. Additionally, the communication unit 120 can collect necessary data by accessing the web through a network under the control of the control unit 130.

Networks disclosed herein include, for example, wireless networks, wired networks, public networks such as the Internet, private networks, Global System for Mobilecommunication networks (GSM) networks, and General Packet wireless networks. Radio Network (GPRN), Local Area Network (LAN), Wide Area Network (WAN), Metropolitan Area Network (MAN), cellular network, Public Switched Telephone Network (PSTN) , Personal AreaNetwork, Bluetooth, Wi-Fi Direct, Near Field Communication, Ultra-Wide band, a combination of these, or any other network. It is not limited to these.

The control unit 130 extracts only the area corresponding to the fashion item by deleting the background excluding the fashion item from the image taken of the fashion item obtained through the camera unit 110 or the image separately input by the user. Videos can be created. Additionally, the control unit 130 can generate an image consisting of only the area corresponding to the fashion item by cropping and extracting only the area corresponding to the fashion item from the input image. If the image of the fashion item obtained through the camera unit 110 is an image of the user wearing the fashion item, the control unit 130 deletes the user area from the image and corresponds to the fashion item. Only the areas that fit can be extracted.

In addition, the control unit 130 extracts only the area for the fashion item from not only the fashion item image captured by the user, but also the shopping video in which the user purchases or purchases the fashion item through the user terminal 100, and generates the image for the fashion item. can be created. At this time, the control unit 130 provides detailed information about the characteristics of the fashion item, such as price, color, material, size, thickness, item name, brand name, style information, and wearing season information, from the shopping video as well as the video about the fashion item. can be obtained together. That is, when a user purchases a fashion item through the user terminal 100, the control unit 130 can automatically obtain an image and detailed information about the fashion item.

The control unit 130 may store the image of the generated fashion item in the virtual closet created in the storage unit 140 and register the fashion item as a fashion item owned by the user. The virtual closet includes the date the fashion item was created, classification information of the fashion item such as tops, bottoms, pants, long skirts, short skirts, long sleeves, short sleeves, etc., price information of fashion items, general brands, luxury brands, expensive brands, or rare brands, etc. Detailed information about fashion items, such as brand information, can be stored and managed for each item.

In particular, the user terminal 100 can receive images of fashion items through various paths. Specifically, the user terminal 100 can receive photos obtained by taking photos through the lens of the user terminal 100, and purchase fashion items. ) may include the purchase screen of a shopping mall, such as a web page accessed through , a path to download photos from SNS, and a path to download photos stored in an external storage medium such as USB memory.

The control unit 130 receives an image of a purchased fashion item that the user wants to purchase, compares the image of the purchased fashion item with the image of the user's owned fashion item pawned in the virtual wardrobe, and compares the owned fashion item with the purchased fashion item. Similarity scores between items can be calculated, and if the calculated similarity score corresponds to a predetermined score standard, for example, if the calculated similarity score is higher than the standard score, the similarity score and an image of the owned fashion item are displayed (150 ), so that the user can make a purchase decision about the fashion item being purchased by referring to the output video and similarity score. In other words, the user can give up purchasing if one of the fashion items he or she owns is very similar to the fashion item he or she wants to purchase.

Here, in the process of calculating the similarity score, the control unit 130 uses an artificial intelligence model learned to extract the characteristics of the fashion item from the image of the input fashion item. The artificial intelligence model may be stored in the storage unit 140 or may be stored in the service server 200 connected to a network.

The control unit 130 displays an image of a fashion item that the user wants to purchase (hereinafter referred to as 'image of a purchased fashion item') and an image of a fashion item owned by the user that is pawned in the virtual closet (hereinafter referred to as 'image of a purchased fashion item'). (referred to as a 'video about a fashion item') is input into the artificial intelligence model to extract the characteristics of the fashion item corresponding to the video of the purchased fashion item and the characteristics of the fashion item corresponding to the video of the owned fashion item, and then extract the purchased fashion item. Calculate the feature value for the feature of the fashion item corresponding to the video for the item and the feature value for the feature of the fashion item corresponding to the video for the owned fashion item, and compare the two calculated feature values to determine the difference between the two fashion items. A similarity score is calculated. Here, the features of the fashion item can be extracted through a feature extraction deep learning model that outputs the features of the input image as a latent vector in the latent space, and the feature value can be calculated as an operation value using the extracted latent vector. Accordingly, similarity can be calculated based on the difference in calculation values between latent vectors representing the characteristics of images for different fashion items. On the other hand, the similarity may be calculated based on the distance at which different latent vectors representing the characteristics of images for different fashion items are located within the latent space. For example, within a latent space, if the distance between latent vectors is close, the similarity can be considered high, and if the distance between latent vectors is far, the similarity can be considered low.

Feature values for the features of the above-described fashion item are not limited to the above-described latent vector acquisition model, and may be obtained through various other methods.

Meanwhile, the characteristics of fashion items can be divided into the color, pattern, material, and style of the fashion item. Patterns can be divided into solid, striped, dot, floral, check, etc. Styles can be further divided into top, bottom, outer, etc. The top can be classified by fit, arm length, sleeve size, neck/collar style, length, etc., and the bottom can be classified by the type of pants or skirt, waist size, fastening method (button, zipper), and pocket location. , It can be divided into rise length, thigh size, fit, hem circumference, and length. Outerwear can be classified by length, neck/collar style, fastening method (button, zipper), and type (padding, coat, jumper, windbreaker, puffer, jacket, vest, etc.). According to the characteristics of the above-described fashion item, the artificial intelligence model can output a latent vector having a unique position in the latent space for each feature when an image of a fashion item with each feature is input. .

The control unit 130 may crop and pre-process a portion representing the characteristics of the fashion item described above from the image of the fashion item, and then input the image into the artificial intelligence model described above to extract the characteristics of the fashion item.

Meanwhile, the control unit 130 may determine whether the user is wearing fashion items stored in the virtual wardrobe created in the storage unit 140 and then calculate the wearing frequency of the worn fashion items. . Specifically, the control unit 130 may receive a user's wearing confirmation input for a specific fashion item from a list of fashion items stored in the virtual wardrobe and determine whether to wear the fashion item. Additionally, the control unit 130 may determine whether the user is wearing the fashion item from an image of the user wearing the fashion item captured through the camera unit 110. For example, when the user selects and inputs worn items from among the fashion items in the virtual wardrobe displayed on the display 150, the control unit 130 recognizes that the user is wearing the selected fashion items. In addition, when a video of a user actually wearing fashion items is input or an image of a user actually wearing fashion items is photographed through the camera unit 110, fashion items are extracted from the wearing video, and the extracted fashion items and virtual You can determine whether to wear a specific fashion item by comparing it with the fashion items stored in your closet. At this time, the control unit 130 may recognize the date on which wearing of the fashion item stored in the virtual wardrobe was confirmed and then calculate the number of wears during a certain period, that is, the wearing frequency. A certain period can be set to a week, a month, a quarter, a half year, a year, a season, etc., and can also be set to a specific period set by the user. The date on which the wearing of the fashion item was confirmed can be confirmed from the shooting date of the video for the fashion item, or from the date directly entered by the user. Accordingly, the control unit 130 can determine how often a specific fashion item is worn during a certain period of time or a specific season set by the user, and through this, determine the user's preference for the specific fashion item.

If the similarity score between the above-described first image and the second image corresponds to a predetermined score standard, that is, if it is determined that the purchased fashion item is similar to the owned fashion item, the control unit 130 video) and the wearing frequency of owned fashion items are output on the display 150, allowing the user to confirm the user's preference for owned fashion items similar to the fashion item the user wishes to purchase, thus helping the user's purchase decision. You can.

In addition, the control unit 130 may select a fashion item to be resold based on a result of calculating the frequency of wearing of the fashion item owned by the user. For example, if it is determined that the user's frequency of wearing a specific fashion item is very low, the control unit 130 may select the item as a resale target for disposal. If the similarity score between the image for the above-described purchased fashion item and the image for the owned fashion item meets a predetermined score standard, that is, if the purchased fashion item is determined to be similar to the owned fashion item, the controller 130 determines that the purchased fashion item is similar to the owned fashion item. After confirming whether the item has been selected for resale, if the owned fashion item has been selected for resale, it outputs on the display 150 that the purchased fashion item is similar to the fashion item selected for resale, so that the user wishes to purchase It can help the user's purchasing decision by allowing the user to confirm that the fashion item is similar to a fashion item for which the user's preference was low enough to be selected for resale in the past.

In addition, when the above-mentioned similarity score corresponds to a predetermined score standard, the control unit 130 displays an image of a fashion item in possession that is determined to be similar to the fashion item to be purchased and user evaluation information on the fashion item in possession. It can be output at (150). The user evaluation information displayed on the display 150 includes the user's evaluation record for the owned fashion item entered along with the wearing history after wearing the owned fashion item, a star rating for wearing, and an evaluation score for wearing (e.g., It may be expressed as a star rating out of 5 stars or a score out of 100 points.) may be included. Meanwhile, the user evaluation information may be input by the user himself as described above, but may also be evaluation information of an acquaintance of the user who input the information after seeing the user's wearing image.

In addition, if the above-described similarity score does not correspond to the predetermined score standard, that is, if it is determined that none of the fashion items held are similar to the fashion item to be purchased, the control unit 130 operates the Internet blog Coordination images containing fashion items similar to the fashion item you wish to purchase from social networking services (SNS) such as shopping malls, Facebook or Instagram can be collected through crawling and output on the display 150. there is. Specifically, the control unit 130 collects images of fashion items through web crawling, inputs the coordination images for fashion items extracted from these images into the aforementioned artificial intelligence model, and generates images corresponding to the coordination images. Extract features of fashion items. Next, the control unit 130 calculates feature values (feature values of the coordination video) for the features of the fashion item corresponding to the coordination video, and combines the feature values of the calculated coordination video with the image of the purchased fashion item calculated previously. By comparing the feature values for the characteristics of the corresponding fashion item, a similarity score is calculated between the fashion item corresponding to the video of the purchased fashion item and the fashion item corresponding to the coordination video, and the calculated similarity score corresponds to the predetermined score standard. In this case, the coordination video or a link to the web page where the coordination video is collected can be output on the display 150.

Therefore, the user terminal 100 according to the embodiment, that is, a device for providing decision information about purchasing fashion items using a virtual wardrobe, provides the user with not only a similarity score based on the result of analyzing the similarity between the fashion item he or she wants to purchase and the fashion item he or she owns. , in similar cases, frequency of wearing, resale target, and wearing evaluation information of the owned fashion items are provided. In case of dissimilarity, coordination information that can be worn with the purchased fashion items is provided through internet search to enable the user's purchase. It can provide information that is helpful in making decisions.

Figure 3 shows the configuration of a service server according to one embodiment.

The service server 200 is connected to the user terminal 100 through a network and provides a service for providing decision information about purchasing fashion items using a virtual wardrobe.

Referring to Figures 1 to 3, the service server 200 may be configured to include a communication unit 210, a control unit 220, and a storage unit 230. The illustrated components are not essential, and a service server may be implemented with more components or fewer components. At least some of these components may be implemented in hardware or software, or through a combination of hardware and software.

The communication unit 210 is connected to the user terminal 100 through a network and transmits data. The network is the same as the network described above.

The control unit 220 creates a resale market using an application program stored in the storage unit 230, and provides a resale brokerage service for fashion items registered as resale products between a plurality of user terminals 100. can do.

Additionally, the control unit 220 may transmit coordinating book data between the user terminals 100 so that a coordinating book composed of images of fashion items worn by each user can be shared between permitted users. Coordinating book data may include wearing evaluation information about fashion items owned by the user.

The storage unit 230 may store applications related to resale market services. In addition, the storage unit 230 may store an artificial intelligence model that extracts features from images of fashion items and a deep learning model that calculates feature values. In the description of FIG. 2, the feature extraction and feature value calculation processes are described. The necessary data may be received through the communication unit 210, then performed by the service server 200, and the resulting value may be transmitted back to the user terminal 100.

In the above-described embodiment, it has been described that a specific user's virtual wardrobe is created in the storage unit 140 of the user terminal 100, and data related to the user's fashion items is stored in the storage unit 140. However, depending on the embodiment, , a virtual wardrobe may be created for each user in the storage unit 230, and at this time, user fashion item data may be transmitted between the service server 200 and the user terminal 100 through the network.

Figures 4 and 5 are flowcharts illustrating a method of providing decision information for purchasing a fashion item using a virtual wardrobe according to an embodiment.

The method of providing judgment information about purchasing fashion items using a virtual wardrobe can be implemented by a computer program stored in a storage medium combined with computer hardware and performed by computer hardware. For example, a computer program may be stored in the storage unit 140 of the user terminal 100 of FIG. 2 and then executed by a processor such as the control unit 130. For another example, this computer program may be stored in the storage unit of the service server 200 of FIG. 1 and then executed by a processor provided in the service server 200. At this time, information output to the user may be output to the display device of the user terminal 100.

Referring to FIG. 4, the method of providing decision information about purchasing a fashion item using a virtual wardrobe first registers an image of the fashion item selected by the user as a owned fashion item in the virtual wardrobe (S410). Owning fashion items is a process of registering fashion items that a user normally purchases in a virtual wardrobe, and registration of owned fashion items is done at any time.

Next, an image of the purchased fashion item that the user wants to purchase is input through the user terminal (S420). This video can be obtained from the purchase screen of the online shopping mall during the online shopping process using the user terminal.

The method of providing judgment information about the purchase of a fashion item using a virtual wardrobe compares the video of the purchased fashion item and the video of the owned fashion item to calculate a similarity score between the two fashion items (S430).

Referring to FIG. 5, in the method of providing decision information for purchasing a fashion item using a virtual wardrobe, the process of calculating the similarity score between two fashion items (S430) involves extracting the characteristics of the fashion item from the image of the input fashion item. By inputting the video of the purchased fashion item and the video of the owned fashion item into the artificial intelligence model, the features of the fashion item corresponding to each video are extracted (S431), and then the feature value for the feature of each fashion item is calculated, This can be done by comparing the two calculated feature values and calculating a similarity score (S432).

Referring again to FIG. 4, the method of providing judgment information for purchasing a fashion item using a virtual wardrobe determines whether the purchased fashion item is similar to the owned fashion item based on the calculated similarity score (S440), and the similarity score is If two fashion items are judged to be similar to each other according to a predetermined score standard (for example, if the similarity score is calculated to be higher than the score at which the two fashion items are judged to be similar to each other), the user receives purchase judgment information about the purchased fashion item. The calculated similarity score and the image of the owned fashion item judged to be similar to the purchased fashion item are output to the user terminal (S450) so that the similarity score does not correspond to the predetermined score standard, so the two fashion items are similar to each other. If it is determined that this is not the case, a fashion item similar to the purchased fashion item is searched, and coordination information related to the similar fashion item is output (S490).

If it is determined that the two fashion items are not similar to each other because the similarity score does not meet the predetermined score standard, a fashion item similar to the purchased fashion item is searched, and coordination information related to the similar fashion item is output in the process (S490). , Coordination information related to fashion items similar to the purchased fashion item is obtained by inputting images of fashion items collected through web crawling into the aforementioned artificial intelligence model to extract the characteristics of fashion items corresponding to the collected images. Calculate the feature values for the features of the fashion item corresponding to the collected video, and compare the feature values for the fashion item to be purchased and the feature values for the fashion item in the collected video to compare the fashion item to be purchased and the collected video. A similarity score (hereinafter referred to as a second similarity score) is calculated between the fashion items in This may correspond to a link to the web page where the video was collected. Videos about collected fashion items or links to web pages where videos about collected fashion items are collected include fashion items judged to be similar to fashion items to be purchased and coordination images including these fashion items.

In addition, a method of providing judgment information about the purchase of a fashion item using a virtual wardrobe includes, when the two fashion items are judged to be similar to each other, receiving a user's wearing confirmation input for the owned fashion item and determining whether or not the owned fashion item is worn. After determining whether or not the owned fashion item is worn or not from a fashion item wearing video captured by the user, the wearing frequency of the held fashion item is calculated during a predetermined period based on the date on which wearing of the held fashion item was confirmed. and output to the user terminal (S460).

In addition, the method of providing judgment information on the purchase of a fashion item using a virtual wardrobe is that, if the two fashion items are judged to be similar to each other, the owned fashion item that is the subject of comparison for the purchased fashion item is eligible for resale based on the frequency of wear calculated above. After determining recognition, if the owned fashion item is selected for resale, the user is notified through the user terminal that the purchased fashion item is similar to the fashion item selected for resale (S470).

In addition, the method of providing judgment information about the purchase of a fashion item using a virtual wardrobe includes, when the two fashion items are judged to be similar to each other, an image of the owned fashion item and evaluation information about the owned fashion item to the user terminal. Print (S480). Here, the evaluation information may include the user's wearing review and wearing evaluation score for the owned fashion item, and the evaluation review and wearing evaluation score of the user's acquaintances.

In the above description, the steps, processes or operations S410 to S490 may be further divided into additional steps, processes or operations, or may be combined into fewer steps, processes or operations, depending on the implementation of the present invention. . Additionally, some steps, processes, or operations may be omitted, or the order between steps or operations may be switched, as needed. In addition, each step or operation included in the method of providing decision information for purchasing fashion items using the above-described virtual wardrobe may be implemented as a computer program and stored in a computer-readable recording medium, and each step, A process or operation may be executed.

The term “unit” (e.g., control unit, etc.) used herein may mean, for example, a unit including one or a combination of two or more of hardware, software, or firmware. “Part” may be used interchangeably with terms such as unit, logic, logical block, component, or circuit, for example. The “part” may be the minimum unit of an integrated part or a part thereof. “Part” may be the minimum unit or part of one or more functions. The “part” may be implemented mechanically or electronically. For example, a “part” may be at least one of Application-Specific Integrated Circuits (ASICs) chips, Field-Programmable Gate Arrays (FPGAs), or programmable-logic devices, known or to be developed in the future, that perform certain operations. It can contain one.

At least a portion of the device (e.g., modules or functions thereof) or method (e.g., operations) according to various embodiments may be stored in a computer-readable storage media, e.g., in the form of a program module. It can be implemented with instructions stored in . When the instruction is executed by a processor, the one or more processors may perform the function corresponding to the instruction. Computer-readable media includes all types of recording devices that store data that can be read by a computer system. Computer-readable storage media/computer-readable recording media include hard disks, floppy disks, magnetic media (e.g. magnetic tape), optical media (e.g. CD-ROM (compact disc read only memory (DVD), digital versatile disk (DVD), magneto-optical media (e.g. floptical disk), hardware devices (e.g. readonly memory (ROM), random access memory (RAM), or flash memory, etc.), and may also include those implemented in the form of a carrier wave (e.g., transmission via the Internet), as well as machine code such as that created by a compiler. The above-described hardware device may include high-level language code executable by a computer, etc., and may be configured to operate as one or more software modules to perform the operations of various embodiments.

A module or program module according to various embodiments may include at least one of the above-described components, some of them may be omitted, or may further include other additional components. Operations performed by modules, program modules, or other components according to various embodiments may be executed sequentially, in parallel, iteratively, or in a heuristic manner. Additionally, some operations may be executed in a different order, omitted, or other operations may be added.

As used herein, the term “one” is defined as one or more than one. Additionally, the use of introductory phrases such as “at least one” and “one or more” in a claim may mean that the same claim contains introductory phrases such as “at least one” and “one or more” and ambiguous phrases such as “an.” The introduction, if any, of another claim element by the ambiguous phrase "one" shall be construed to mean that any particular claim containing the claimed element so introduced is limited to an invention containing only one such element. It shouldn't be.

In this document, expressions such as “A or B” or “at least one of A and/or B” may include all possible combinations of the items listed together.

Unless otherwise specified, terms such as “first” and “second” are used to optionally distinguish between the elements described by such terms. Accordingly, these terms are not necessarily intended to indicate temporal or other priority of such elements, and the mere fact that particular means are recited in different claims does not indicate that a combination of such means cannot be advantageously used. . Accordingly, these terms are not necessarily intended to indicate temporal or other priority of such elements. The mere fact that a particular measure is cited in different claims does not indicate that a combination of these measures cannot be used usefully.

The arrangement of components to achieve the same function is effectively “related” so that the desired function is achieved. Accordingly, any two components combined to achieve particular functionality may be considered to be “related” to each other such that the desired functionality is achieved, regardless of structure or intervening components. Likewise, two such associated components may be considered “operably connected” or “operably coupled” to each other to achieve a desired function.

Additionally, those skilled in the art will recognize that the boundaries between the functionality of the foregoing operations are illustrative only. Multiple operations may be combined into a single operation, a single operation may be distributed into additional operations, and the operations may be executed at least partially overlapping in time. Additionally, alternative embodiments may include multiple instances for a particular operation, and the order of the operations may vary in various other embodiments. However, other modifications, variations and alternatives are also possible. Accordingly, the detailed description and drawings are to be regarded in an illustrative rather than a restrictive sense.

The phrase “may be X” indicates that condition X may be met. This phrase also indicates that condition For example, a reference to a system containing a specific component should also include scenarios in which the system does not contain the specific component. For example, a reference to a method that includes a specific behavior should also include scenarios in which the method does not include that specific component. However, as another example, a reference to a system configured to perform a specific action should also include scenarios in which the system is not configured to perform a specific task.

The terms “comprising,” “having,” “consisting of,” “consisting of,” and “consisting essentially of” are used interchangeably. For example, any method may include at least the operations included in the drawings and/or the specification, or may include only the operations included in the drawings and/or the specification. Alternatively, the word “comprising” does not exclude the presence of elements or acts listed in a claim.

Those skilled in the art will recognize that the boundaries between logical blocks are illustrative only and that alternative embodiments may merge logical blocks or circuit elements or impose alternative decompositions of functionality on various logical blocks or circuit elements. You will recognize that it exists. Accordingly, it should be understood that the architecture shown herein is merely exemplary, and in fact many other architectures may be implemented that achieve the same functionality.

Also, for example, in one embodiment, the depicted examples could be implemented on a single integrated circuit or as circuitry located within the same device. Alternatively, the above examples may be implemented as any number of separate integrated circuits or individual devices interconnected together in any suitable manner, and other variations, modifications, variations and alternatives are also possible. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense.

Additionally, for example, the above-described examples, or portions thereof, may be implemented as a software or code representation of a physical circuit or a logical expression convertible to a physical circuit, such as any suitable type of hardware description language.

Additionally, the present invention is not limited to physical devices or units implemented in non-programmable hardware, but includes mainframes, minicomputers, servers, workstations, personal computers, notepads, etc., generally referred to herein as 'computer systems'. A programmable device that can perform a desired device function by operating in accordance with appropriate program code, such as personal digital assistants (PDAs), electronic games, automobiles and other embedded systems, cell phones, and various other wireless devices. Alternatively, it can also be applied to units.

A system, apparatus or device referred to in this specification includes at least one hardware component.

Connections as described herein may be any type of connection suitable for transmitting signals to or from each node, unit or device, for example via an intermediate device. Accordingly, unless implied or otherwise stated, a connection may be, for example, a direct connection or an indirect connection. A connection may be described or depicted with reference to being a single connection, multiple connections, one-way connection, or two-way connection. However, different embodiments may vary the implementation of the connection. For example, you could use a separate one-way connection rather than a two-way connection, or vice versa. Additionally, multiple connections can be replaced with a single connection that transmits multiple signals sequentially or in a time-multiplexed manner. Likewise, a single connection carrying multiple signals may be split into various connections carrying subsets of those signals. Therefore, many options exist for transmitting signals.

In the above, preferred embodiments of the technology of this specification have been described with reference to the attached drawings. Here, terms and words used in this specification and claims should not be construed as limited to their usual or dictionary meanings, but should be construed with meanings and concepts consistent with the technical idea of the present invention. The scope of the present invention is not limited to the embodiments disclosed herein, and the present invention may be modified, changed, or improved in various forms within the scope described in the spirit and claims of the present invention.

10: System for providing judgment information on purchasing fashion items using a virtual wardrobe
100: user terminal
110: Camera unit
120: Department of Communications
130: control unit
140: storage unit
150: display
200: service server
210: Department of Communications
220: control unit
230: storage unit

Claims (13)

registering the first image of the fashion item selected by the user as a held fashion item in a virtual wardrobe;
Receiving a second video of a fashion item that the user wants to purchase;
Comparing the first image and the second image to calculate a similarity score; and
Based on the similarity score, it is determined whether the purchased fashion item is similar to the owned fashion item, and if the two fashion items are determined to be similar to each other, the similarity score and the first image are output to the user terminal to determine the purchased fashion item. providing purchase decision information for an item, and if it is determined that the two fashion items are not similar to each other, searching for a fashion item similar to the purchased fashion item, and outputting coordination information related to the similar fashion item; containing
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. According to claim 1,
The step of calculating a similarity score by comparing the first image and the second image is,
The first image and the second image are input to an artificial intelligence model that extracts the characteristics of the fashion item from the image for the input fashion item, and the characteristics of the fashion item corresponding to the first image and the second image are calculated. Extracting features of a fashion item; and
Calculate a first feature value for the feature of the fashion item corresponding to the first image and a second feature value for the feature of the fashion item corresponding to the second image, and the first feature value and the second feature value Calculating the similarity score by comparing
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. According to clause 2,
When it is determined that the two fashion items are similar to each other, it is determined whether the user is wearing the held fashion item, and the held fashion item is stored for a predetermined period based on the date on which wearing of the held fashion item was confirmed. Calculating the wearing frequency for and outputting it to the user terminal; further comprising
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. According to clause 3,
If the two fashion items are determined to be similar to each other, it is determined whether the owned fashion item is eligible for resale based on the wearing frequency, and if the owned fashion item is selected as a resale target, the purchased fashion item is eligible for resale. Notifying the user terminal that it is similar to the selected fashion item; further comprising
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. According to clause 4,
When it is determined that the two fashion items are similar to each other, outputting evaluation information about the first image and the owned fashion item to the user terminal;
The evaluation information includes wearing reviews and wearing evaluation scores for the owned fashion item.
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. According to clause 2,
Coordination information related to fashion items similar to the purchased fashion items,
The third image of the fashion item collected through web crawling is input into the artificial intelligence model to extract the characteristics of the fashion item corresponding to the third image, and the characteristics of the fashion item corresponding to the third image are extracted. A third feature value is calculated for the feature, and the second feature value and the third feature value are compared to obtain a second similarity score between the fashion item corresponding to the second image and the fashion item corresponding to the third image. Calculate, and if the second similarity score corresponds to a second predetermined score standard, the third image or the link of the web page where the third image was collected is obtained.
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. storage unit;
display; and
Includes a control unit functionally connected to the storage unit and the display,
The control unit,
Registering the first image of the fashion item selected by the user as a holding fashion item in the virtual wardrobe created in the storage unit,
Receiving a second image of a purchased fashion item that the user wants to purchase, comparing the first image and the second image to calculate a similarity score between the owned fashion item and the purchased fashion item, and
Based on the similarity score, determine whether the purchased fashion item is similar to the owned fashion item,
If it is determined that the two fashion items are similar to each other, the similarity score and the first image are output to the user terminal to provide purchase judgment information for the purchased fashion item,
If it is determined that the two fashion items are not similar to each other, a fashion item similar to the purchased fashion item is searched and then coordination information related to the similar fashion item is output.
A device that provides judgment information about purchasing fashion items using a virtual wardrobe. According to clause 7,
The storage unit,
Includes an artificial intelligence model that extracts the characteristics of fashion items from the video of the input fashion item,
The control unit,
Input the first image and the second image into the artificial intelligence model to extract the characteristics of the fashion item corresponding to the first image and the characteristics of the fashion item corresponding to the second image,
Calculate a first feature value for the feature of the fashion item corresponding to the first image and a second feature value for the feature of the fashion item corresponding to the second image, and the first feature value and the second feature value Calculating the similarity score by comparing
A device for providing decision information about purchasing fashion items using a virtual wardrobe. The method of claim 8, wherein the control unit,
If the two fashion items are judged to be similar to each other,
Determining whether the user is wearing the held fashion item, calculating the frequency of wearing the held fashion item during a predetermined period based on the date on which wearing of the held fashion item was confirmed, and outputting the worn fashion item on the display.
A device for providing decision information about purchasing fashion items using a virtual wardrobe. The method of claim 9, wherein the control unit,
If the two fashion items are determined to be similar to each other, it is determined whether the owned fashion item is eligible for resale based on the wearing frequency, and if the owned fashion item is selected as a resale target, the purchased fashion item is eligible for resale. Similarity to the selected fashion item is displayed on the display.
A device for providing decision information about purchasing fashion items using a virtual wardrobe. The method of claim 10, wherein the control unit,
If it is determined that the two fashion items are similar to each other, the first image and evaluation information about the owned fashion item are output on the display,
The evaluation information includes wearing reviews and wearing evaluation scores for the fashion items owned.
A method of providing judgment information about purchasing fashion items using a virtual wardrobe. The method of claim 8, wherein the control unit,
If it is determined that the two fashion items are not similar to each other, the third image of the fashion item collected through web crawling is input to the artificial intelligence model to determine the characteristics of the fashion item corresponding to the third image. After extraction, a third feature value for the feature of the fashion item corresponding to the third image is calculated,
Comparing the second feature value and the third feature value to calculate a second similarity score between the fashion item corresponding to the second image and the fashion item corresponding to the third image, and
If the second similarity score corresponds to a second predetermined score standard, outputting the third image or a link to the web page where the third image was collected on the display.
A device for providing decision information about purchasing fashion items using a virtual wardrobe. Combined with hardware,
A computer program stored in a computer-readable recording medium for executing each step included in the method of providing decision information for purchasing fashion items using a virtual wardrobe according to any one of claims 1 to 6.