WO2018226022A1 - Serveur de recommandation d'article de mode, et procédé de recommandation d'article de mode utilisant ledit serveur - Google Patents

Serveur de recommandation d'article de mode, et procédé de recommandation d'article de mode utilisant ledit serveur Download PDF

Info

Publication number
WO2018226022A1
WO2018226022A1 PCT/KR2018/006422 KR2018006422W WO2018226022A1 WO 2018226022 A1 WO2018226022 A1 WO 2018226022A1 KR 2018006422 W KR2018006422 W KR 2018006422W WO 2018226022 A1 WO2018226022 A1 WO 2018226022A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
fashion
items
recommendation
item
Prior art date
Application number
PCT/KR2018/006422
Other languages
English (en)
Korean (ko)
Inventor
손성삼
임재우
Original Assignee
손성삼
임재우
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 손성삼, 임재우 filed Critical 손성삼
Publication of WO2018226022A1 publication Critical patent/WO2018226022A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0252—Targeted advertisements based on events or environment, e.g. weather or festivals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Definitions

  • the present invention relates to a fashion item recommendation server and a fashion item recommendation method using the same.
  • a method of facilitating a purchase is generally used by grasping a particular individual's propensity mainly at a fashion store that sells a specific fashion item, and recommending an item that the individual is likely to purchase.
  • An object of the present invention is to provide a system and method for recommending optimal coordination for a user's own top or bottom, shoes and ancillary accessories.
  • an object of the present invention is to increase the user's purchase intention to increase sales by recommending a new fashion item effective to the user when added to a fashion collection consisting of fashion items owned by the user.
  • an object of the present invention by allowing the user to grasp the fashion collection owned at a glance, it is possible to effectively identify the fashion items that are effective in their fashion coordination, ineffective or not wear fashion items It is about making it easy to arrange.
  • the present invention allows a user to register a fashion item owned by the user, creating a database of registered fashion items, and based on the items registered by the user, A method of recommending a fashion item, comprising recommending a combination of specific fashion items.
  • a specific fashion item to a user based on a module for registering a fashion item owned by the user, a module for creating a database of registered fashion items, and items registered by the user. It provides a fashion item recommendation server, including a module for recommending a combination of these.
  • an embodiment provides a method of registering a fashion item owned by a user, generating a database of registered fashion items, and based on the items registered by the user.
  • a method of recommending a fashion item comprising recommending a combination of specific fashion items.
  • the recommendation step may be performed by reflecting a preference of a user or a third party.
  • the user's preference is characterized in that based on the input "like” or “dislike” input by the user or a third party.
  • the recommendation step may be performed by reflecting one of weather, seasons and regions.
  • a registration module for registering a user owns a fashion item
  • a transmission module for transmitting information about registered fashion items to the recommendation server, and from the recommendation server to the user specified
  • a terminal comprising a receiving module for receiving a recommendation for a combination of fashion items and a display means for displaying a combination of fashion items owned by the user based on the recommendation.
  • the recommendation step may be performed by reflecting a preference of a user or a third party.
  • the user's preference is characterized in that based on the input "like” or “dislike” input by the user or a third party.
  • FIG. 1 is a schematic diagram showing a configuration of a computer network in which the present invention can be implemented.
  • FIGS 2 (a)-(d) illustrate examples of various fashion items that may be registered in the recommendation server 180 according to an embodiment of the present invention.
  • a user accesses a smartphone app store including a Google app store, and downloads a fashion recommendation app (“for example, fashion helper”) that operates in conjunction with the recommendation server 180 to his smartphone (301). It is a figure for demonstrating to install in.
  • a fashion recommendation app for example, fashion helper
  • FIG. 4 is a diagram for describing a main screen for registering the fashion items illustrated in FIG. 2.
  • FIG. 5 (a)-(d) are diagrams for explaining an example for registering the fashion items shown in FIG.
  • FIG. 6 (a)-(b) are diagrams for describing another example for registering the fashion items shown in FIG. 2.
  • FIG. 7 is a view for explaining another embodiment of registering various fashion items owned by a user.
  • FIG. 8 is a diagram schematically illustrating user identification information stored in the user database 120 shown in FIG. 1 and fashion item entries linked thereto.
  • FIG. 9 is a diagram illustrating a screen displayed on a user's smartphone when the user operates the "Fashion Helper” app and touches and selects the "smart wardrobe” 440 from the menu of FIG. 4.
  • FIG. 10 illustrates a screen displayed to the user when the user selects and selects fashion items to be coordinated in the smart wardrobe.
  • FIG. 11 illustrates a screen in which a combination of fashion items recommended by the recommendation server 180 is displayed on the smartphone 111 of the user 110 according to the coordination recommendation method of the present invention.
  • FIG. 12 illustrates a method of deriving a high utilization fashion item when it is added to the fashion collection of the user 110 by using the recommendation server 180 of the present invention and recommending it to the user 110. It is for the drawing.
  • FIG. 13 is a diagram illustrating an example of displaying a fashion item having high utilization rate because a degree of improving a user's fashion score is increased when the user 110 additionally purchases the same.
  • FIG. 14 is a diagram illustrating a system for displaying a combination of coordinations close to a model coordination to a user by selecting a model coordination by using the recommendation server 180 of the present invention.
  • FIG. 15 is a diagram for describing a system for displaying a combination of coordination to a user using the system of FIG. 14.
  • FIG. 16 illustrates an example of a recommendation algorithm that can be used in the present invention.
  • the system of the present invention receives a variety of information from the user 110 while communicating with the user 110, based on the information recommendation server 180 for recommending appropriate fashion items and fashion coordination to the user 110 Equipped.
  • the system of the present invention may include a user database 120 that is separate from the recommendation server 180 and in electrical communication with the recommendation server 180.
  • the user 110 of the system cooperates with the recommendation server 180 to register each of their fashion items 130-1, 130-2, and 130-3 with the recommendation server 180.
  • the fashion items 130-1, 130-2, and 130-3 may be stored as objects for each user in the user database 120, and then transmitted to the recommendation server 180 by a call from the recommendation server 180. have.
  • the user database 120 is assumed to be physically and logically separated from the recommendation server 180 and provided in a separate place, the user database 120 includes the user database 120 in the recommendation server 180. It is of course also possible to configure the database 120 to be physically present within the recommendation server 180.
  • the recommendation server 180 may be configured as a client-server system, in which case the recommendation server 180 may be one or more functions on the recommendation server 180 via a wired or wireless network 140.
  • a user device 190 that is a client.
  • the user device 190 may be, for example, a smartphone, and may be a device that operates in a general operating system, that is, an operating system such as Android or Apple iOS.
  • the user device 190 may operate in conjunction with the recommendation server 180 or in a standalone manner on the user device 190, and operate an application app required for implementing the present invention.
  • 190 may be a desktop computer, vehicle computer, tablet computer, navigation device, portable media device, smartphone, or wearable device (eg, smart watch or smart glasses) belonging to user 110.
  • All or one of user device 190 or recommendation server 180 is a general purpose computer that is modified to perform a particular purpose by software for performing one or more functions described herein for that machine, database, or device. Or may be implemented as a smartphone.
  • FIG. 2 (a)-(d) illustrate examples of various fashion items that may be registered in the recommendation server 180 according to an embodiment of the present invention.
  • the fashion recommendation system 100 of the present invention allows the user 110 to display various tops 201-204, bottoms 211-214, shoes 221-223, and coats 231 owned by the user 110. -233) to register a variety of fashion items, such as.
  • fashion items include auxiliary fashion items such as ties, handbags, socks, etc., in addition to these, and the user 110, in the fashion recommendation system 100, owns these auxiliary fashion items that he owns. You can also register.
  • FIG. 3 a user accesses a smartphone app store including a Google app store, and downloads a fashion recommendation app (“for example, fashion assistant”) that operates in conjunction with the recommendation server 180 and uses his or her smartphone (301). Install).
  • FIG. 4 is a diagram for describing a process of registering the fashion items illustrated in FIG. 2 as part of the function of the fashion recommendation system 100.
  • the user 110 enters personal information such as his name and gender, and goes through a normal user registration procedure in which an ID and a password are granted.
  • the recommendation server 110 When registering a user, the recommendation server 110 not only inputs general personal information such as an e-mail, nickname, region, and gender, but also other information which may be helpful or clue to fashion recommendation, for example, skin color, face shape, Personal information such as age, body type, height, limb length, weight, or chest / waist size can be requested and input.
  • general personal information such as an e-mail, nickname, region, and gender
  • other information which may be helpful or clue to fashion recommendation for example, skin color, face shape
  • personal information such as age, body type, height, limb length, weight, or chest / waist size can be requested and input.
  • the "User Registration” 410 submenu is a submenu that allows a user to register himself.
  • the "Register New Item” 420 submenu is a submenu that allows a user to register their new fashion item.
  • the "fashion coordination recommendation” 430 submenu is a submenu for the recommendation server 110 to select a fashion coordination suitable for the user 110 and receive a recommendation based on a database of individual users stored in the user database 120. to be.
  • FIG. 5 (a) illustrates that the user 110 selects the new item registration 420 submenu of FIG. 4 when the user 110 who is given an ID and password through user registration wants to register his or her fashion item.
  • FIG. 3 is a diagram illustrating a screen 301 (see FIG. 3) of a smartphone app displayed to the user 110.
  • the smartphone app prompts the user, FIG. 5 (a).
  • a plurality of categories of fashion items namely, “top”, “bottom”, “shoe”, “coat”, and “secondary fashion items” to select a category of fashion items to be registered by the user. Display choices to the user 110.
  • the smartphone app 301 may further provide a screen for allowing the user to select a sub category of the fashion item when the user 110 selects and touches a category of the fashion item (see FIG. See FIG. 5 (b)). For example, when the user 110 selects the "top” category on the smartphone app 301, the smartphone app 301 is the next screen, such as "T-shirt”, “shirt”, blouse “,” shirt “, etc. Various sub-categories may be displayed and configured so that a user may input more easily.
  • the smartphone app 301 After the user 110 selects a category (or sub-category) of a fashion item to register on the smartphone app 301, the smartphone app 301 causes the user 110 to select a color of the fashion item. Make a choice. For example, the smartphone app 301 displays a screen as shown in FIG. 5C to the user so that the user can select a color closest to the fashion item. In addition, in order to select a color closer to each other, a color palette consisting of a plurality of squares may be presented to the user, and the user may be selected to the color closest to the fashion item.
  • the user 110 selects a category or a subcategory of a fashion item to be registered by the user 110 and based on the screens shown in FIG. 5C.
  • the smartphone app 301 enters a shooting mode in which the user photographs the fashion item that the user wants to register (see FIG. 5 (d)).
  • the user photographs a fashion item that he / she wants to register, and approves the registration of the fashion item if the photographed picture is satisfactory. . If the taken picture is not satisfactory, the user can take the picture once again.
  • the user's smartphone 111 transmits the information about the fashion item to the recommendation server 180, and the recommendation server 180 fashions the fashion.
  • Various information about the item is stored in the database 120 as user data for the user 110.
  • one fashion item as shown in Figure 5 (d), it is possible to take two or more pictures of the front, back (see reference numeral 505) ).
  • the user 110 instead of allowing the user 110 to select a type of fashion item to register, the user 110 provides a plurality of options, and the user 110 merely selects one of the plurality of options displayed on the screen. It is also possible to make fashion item registration easier by making the selection. For example, if the user 110 wants to register his or her fashion item by selecting the “New Item Registration” 420 submenu of FIG. 4, the smartphone app may allow the user 110 to register the fashion item. ) Displays the category of the fashion item to be registered as a plurality of thumbnails, and the user selects a category corresponding to the fashion item to be registered (FIG. 6 (a)).
  • the smartphone app displays a sub category included in the category on the screen, and the user selects a sub category corresponding to his fashion item on the screen.
  • the smartphone app allows to register the color of the fashion item (Fig. 6 (b)).
  • the user 110 photographs his fashion item with a camera and presses a registration button, thereby completing the registration of the fashion item.
  • each of the various types of sample fashion items is displayed to the user 110, and the user 110 selects a sample fashion item that is closest to the fashion item to which the user wants to register. It is also possible to specify.
  • the recommendation server 180 may directly select a color closest to the fashion item based on the color of the fashion item photographed by the user. For example, when the user 110 photographs and uploads his or her fashion item, the recommendation server 180 directly fashions the fashion item most similar to the fashion item, based on information such as color, pattern, and shape of the fashion item. You can select and register an item. It is also possible for the recommendation server 180 to select several candidate items similar to the fashion item and display them to the user 110 to allow the user 110 to select the most similar candidate item.
  • the user 110 may register fashion items owned by the user 110.
  • top, bottom, shoes, etc. are specified as the type of fashion item, but those skilled in the art will understand that the present invention can be applied to various fashion items without departing from the spirit of the present invention. Examples include clothes (t-shirts, shirts, socks, pants, coats, jumpers, skirts, blouses, etc.), shoes (shoes, sneakers, etc.), accessories (scarves, mufflers, ties, tie pins, bags, glasses, sunglasses, watches, Belts, etc.), makeup and other items (wigs, beards, hairstyles, etc.). It includes not only clothing but also all props that can express a person's personality.
  • the user 110 visits the fashion brand store 710 to purchase a fashion item required by the user, and the user of the ID or the information registered in the fashion recommendation system 100 may specify the fashion brand company 710.
  • Notify The fashion brand company 710 notifies the recommendation server 180 of the user registration information and the product label or item serial number of the fashion item purchased by the user.
  • a method well known in the art may be used, such as a method of scanning a barcode.
  • the recommendation server 180 previously stores various product information corresponding to a label or an item serial number of various fashion products handled by the company from the fashion brand company 701, and then purchases the information by the user 110.
  • the item serial number of the fashion item in this embodiment, "8451-2014" is transmitted to the recommendation server 180 together with the user's ID.
  • the recommendation server 180 extracts the product information of the corresponding product, for example, the category, sub category, color code, pattern code, etc. of the corresponding product, based on the transmitted user ID and the product serial number "8451-2014". Register as a new entry in the smart wardrobe (described in detail below).
  • the user 110 automatically inputs the category, sub-category, color code, pattern code, etc. of the fashion item he / she purchased, without having to register as a new entry automatically. Registration can be done.
  • FIG. 8 is a diagram schematically illustrating user identification information stored in the user database 120 shown in FIG. 1 and fashion item entries linked thereto.
  • the user of the fashion recommendation system 100 registers the fashion items owned one by one, or through the automatic registration through the partnership with the fashion brand company 501, the category of the own fashion items 803 ),
  • the sub category 804, the color code 805, the pattern code 806, and the like may be registered in the recommendation server 180 for each fashion item.
  • the recommendation server 180 may store these information in the user database 120 in association with identification information about individual users, such as user IDs.
  • the sub category entry 804 is a further subdivision of the category entry 803 and may be omitted.
  • the photo entry 807 is obtained by a photo registered by the user for the fashion item or an item number transmitted by the brand store 710 for the fashion item that the user 110 visited the brand store 710 and purchased. It may be a photograph.
  • the miscellaneous entry 807 may include various information for identifying fashion items, in addition to the various data entries listed above.
  • the other entry 807 may include photo information of fashion items photographed by a user.
  • the recommendation server 180 may show the user 110 a list of various fashion items registered by the user 110 or a combination of these fashion items. Will be.
  • the user database 120 may store a fashion item object ID representing the fashion items based on various pieces of information of individual fashion items. That is, the user database 120 may create and store object data about fashion items based on data of numerous colors, shapes, etc. of the fashion items.
  • the recommendation server 180 may apply to the corresponding fashion item among a plurality of fashion item objects included in the user database 120 based on various data of the fashion item input by the user. By identifying which fashion item object is the closest, the ID of the nearest fashion item object may be stored as part of the other entry 807.
  • FIG. 9 is a diagram illustrating a screen displayed on a user's smartphone when the user operates the "Fashion Helper" app and touches and selects the "smart wardrobe” 440 from the menu of FIG. 4.
  • the user's smart wardrobe displays all fashion items owned by each category or subcategory.
  • all fashion items registered by the user are listed at a glance, so that if the actual size of the wardrobe is narrow or it is difficult to store the fashion items in one place, it is remembered which fashion items he owns. Even if it is difficult to select fashion items depending only on, it is possible to easily utilize their own fashion items as efficiently as possible.
  • the recommendation server 180 may select and display only specific types of items among all fashion items registered by the user 110. For example, the recommendation server 180 divides all fashion items registered by the user 110 into four seasons of spring, summer, autumn, and winter, and lists only the fashion items suitable for the season in the user 110 in a specific season. It is also possible to show by (implementation of seasonal wardrobe).
  • FIG. 10 illustrates a screen displayed to the user when the user selects and selects fashion items to be coordinated in the smart wardrobe.
  • the “Fashion Assistant” app displays the fashion items registered by the user for each category.
  • the "Fashion Assistant” app displays the fashion items belonging to the following categories in order on the screen, and the user sequentially selects the fashion items accordingly. Choose.
  • the "Fashion Helper” app moves to the next step and displays the user's pre-populated photos and displays them to the user. It allows you to judge ahead.
  • the recommendation server 180 selects a fashion item object that is closest to the fashion item based on details corresponding to the fashion item registered by the user, such as color, pattern, and other information, and the user selects all categories. After the selection of each fashion item is completed, the corresponding fashion item objects are synthesized, and a virtual image 1001 based on this is generated and displayed to the user, thereby enabling the user to optimally coordinate the fashion item.
  • the recommendation server 180 calculates a fashion score for the coordination selected by the user based on an internal algorithm, and displays the display 1002 to the user 110 to objectively evaluate the coordination selected by the user 110. You can expect a value.
  • the user 110 may evaluate the coordination 1001 selected by himself, and may press the "Like” (1003) button if he / she likes it, or the “Dislike” (1004) button if he / she does not like it.
  • the recommendation server 180 may receive the result of the selection when the user 110 presses the "like” (1003) or “dislike” (1004) button, and may reflect this when calculating the next fashion score.
  • the coordination recommendation method of the present invention will be described.
  • the recommendation server 180 selects a combination of fashion items that are considered most appropriate based on an internal algorithm. Displayed on the smartphone 310 of (110).
  • FIG. 11 illustrates a screen in which a combination of fashion items recommended by the recommendation server 180 is displayed on the smartphone 111 of the user 110 according to the coordination recommendation method of the present invention.
  • the recommendation server 180 extracts fashion items one by one from each category according to an internal algorithm from the fashion items registered by the user, completes the coordination to be recommended to the user, and then displays the coordination 1101 to the user.
  • the recommendation server 180 scores the coordinates composed of the combinations of the fashion items and displays them to the user by using an internal algorithm.
  • the recommendation server 180 displays the coordination to the user in order from the highest score for the plurality of coordination candidates, and the user clicks the "Like” button for the coordination of his / her preferred coordination among the displayed coordinations.
  • the coordination displayed by the recommendation server 180 does not prefer the fashion. Can be informed.
  • the selection result is sent to the recommendation server 180, which is used to prioritize future coordination.
  • the confirmation that the user presses the "Like” button is stored in the user's database 120 as a high preference coordination, and if the user presses the "Dislike” button, the confirmation has a low preference on the user's database 120.
  • the recommendation server 180 may select a coordination suitable for the user and recommend it to the user by using various algorithms.
  • the user 110 may touch the arrow 710 displayed on the screen to sequentially display various coordinations in order of decreasing fashion score.
  • the coordination recommendation method of the present invention may make a recommendation to the user 110 by utilizing various variables.
  • Various variables that the recommendation server 180 may utilize include weather, seasons, regions, and the like.
  • the recommendation server 180 may change the priority of the coordination to be displayed to the user 110 by using the weather of the day on which the user will use the coordination. For example, when a user requests a recommendation of a fashion coordination to be worn on the morning, the recommendation server 180 searches for the weather and the expected temperature on the day, and if it is colder than usual, weights the darker fashion. By calculating the fashion score by assigning a, it can be recommended to the user 110 so that the fashion of the dark series has a higher fashion score, and thus a higher priority.
  • the user may receive a situation in which the coordination is utilized as a variable. That is, the user can select a particular event on the "fashion assistant" app.
  • the particular event may be an event such as a date, a wedding ceremony, a job interview, a first visit to a customer, a party, a trip, or the like.
  • the recommendation server 180 may receive an event of such a user, select a suitable coordination for the event, and recommend the event to the user.
  • the recommendation server 180 to recommend the fashion coordination that is most appropriate for the event, and the user 110 is more effectively optimized. You can select the coordination of.
  • the recommendation server 180 in conjunction with the user's smartphone 301, receives specific date information from the user 110, such as a schedule and an anniversary of the user, thereby presenting a more specific coordination to the user 110. can do.
  • specific date information such as a schedule and an anniversary of the user
  • the user instead of receiving a situation in which a corresponding coordination is utilized as a variable, the user receives user-specific information such as a schedule and an anniversary of the user from a schedule management program installed in the smartphone 301, and the user 110. You can suggest the best coordination for your situation.
  • the recommendation server 180 uses various algorithms to provide the user 110 with a combination of desirable coordination that can be selected from the user's fashion collection.
  • the recommendation server 180 may internally calculate fashion scores for various coordinations that can be selected from the user's fashion collection, and display the fashion scores for the coordination to the user 110.
  • the recommendation server 180 may recommend a preferred coordination to the user 110 based on a generally known rule. More specifically, the recommendation server 180 may include, in its database, rules generally known in the fashion industry.
  • recommendation server 180 is one of these rules, for example, "It is desirable for the brightness to darken from top to bottom", "fat Body stripe has a set of rules, The recommendation server 180 prioritizes these rules, indexes all combinations that can be obtained from the fashion collection of the user 110 based on these priorities, and based on the ranking of these indexes. It can be configured to recommend the most desirable combination as the best coordination to the user.
  • the recommendation server 180 may also recommend a desirable coordination to the user 110 by utilizing color matching degrees frequently used in the fashion industry. That is, for all combinations that can be obtained from the fashion collection of the user 110 based on the color harmony, a fashion score or similar index is given, and the most preferable combination is optimal for the user based on the ranking of these indexes. It can be configured to recommend as a coordination of.
  • the recommendation server 180 may also recommend an optimal coordination to the user 110 using an artificial intelligence algorithm. More specifically, the recommendation server 180 with the artificial intelligence algorithm recommends the desired coordination to the user 110, or randomly, the algorithms cited above, and the user 110 may like or "like” it. If you press the "dislike" button as an input value, the user 110 can memorize the pattern of fashion coordination desired. After a certain pattern is entered, the recommendation server 180 indexes the user 110 for all combinations that can be obtained from the fashion collection of the user 110 based on this pattern, and ranks of these indexes. Can be configured to recommend the most desirable combination as the best coordination to the user.
  • FIG. 12 illustrates a method of deriving a high utilization fashion item when it is added to the fashion collection of the user 110 by using the recommendation server 180 of the present invention and recommending it to the user 110. It is for the drawing.
  • the recommendation server 180 receives data 1201 for various fashion items from the fashion brand company 1210, and combines the information with the information of fashion item entries previously stored for them and the user. If the candidate is added to the current fashion collection of the candidates 1212 of fashion items that can increase the score is selected and displayed to the user (110).
  • FIG. 13 is a diagram illustrating an example of displaying a fashion item having high utilization rate because a degree of improving a user's fashion score is increased when the user 110 additionally purchases the same.
  • the display of fashion item candidates may be separately provided with a part of the menu of the "Fashion Assistant" app so that the user may display it by selecting the menu, and display as an advertisement 1302 at the bottom of the "Fashion Assistant” app. It is also possible.
  • the user may display a fashion score that may be increased when the corresponding fashion item is provided.
  • Reference numeral 1301 is a display of a fashion item with high utilization to the user.
  • This approach can be particularly useful when a user wants to be recommended for a fashion coordination required for an event after a certain period of time. For example, if a user wants to receive a recommendation of a coordination for a job interview a week later, the recommendation server 180 may ask the user 110 for the coordination candidates in order of fashion scores that can be obtained with the fashion items owned by the user. In addition to displaying, the user 110 by displaying a fashion score that can be obtained by purchasing a certain fashion item, for example, black high heels, and combining it with other fashion items of the user from a particular fashion brand company 1210. ) Can make an objective evaluation of its coordination, and can also promote the purchase of goods by inspiring the user to purchase the fashion item.
  • the product image 1301 or the advertisement message 1302 displayed to the user includes a hyperlink, so that when the user 110 touches the corresponding product image 1301 or touches the advertisement message 1302, the corresponding product image 1301 or the advertisement message 1302 is displayed. It may also be directly connected to the purchase website of the fashion brand company 1201 that can purchase the product.
  • the recommendation server 180 may virtually combine each of the various fashion items owned by the user with items of a category other than the category to which the fashion item belongs, and may not be well matched with or used with other fashion items. By extracting items that are not used, it may be suggested that the user 110 donate or sell these items at a used shopping mall. In this case, it is also possible to display the corresponding items that are not frequently used by the user, and to display the used shopping mall banner advertisements together so that the user can easily sell the fashion items as used goods.
  • the user 110 checks whether information about the fashion item is stored in the recommendation server 180, and if the information about the fashion item is stored in the recommendation server 180. If it is stored, it is possible to check how the corresponding fashion item is matched with various fashion items of its fashion collection. In this way, when purchasing a particular fashion item, it is also possible to reduce the impulse purchase by checking how effectively it can be used.
  • FIG. 14 utilizes the recommendation server 180 of the present invention to allow the user 110 to select a model coordination, and a combination of coordinations that most closely matches the model coordination from the fashion collection of the user 110.
  • the content provider 1410 is a provider that provides various broadcast contents such as movies, dramas, and music programs. Examples of the content provider 1410 include wired and wireless broadcasting stations.
  • the content provider 1410 may receive data 1401 about the coordination worn or worn by the characters included in the broadcast content on various broadcast screens included in the broadcast content through a wired or wireless network. 180).
  • the recommendation server 180 creates and stores various model coordinations based on the data 1401 about the coordination of various characters received from the content provider 1410.
  • FIG. 15 utilizes the system of FIG. 14 to allow the user 110 to select a model coordination, and selects a combination of coordinations that most closely matches the model coordination from the fashion collection of the user 110 to the user. It is a figure for explaining the screen to display.
  • the user 110 selects a drama or a movie presented by a fashion recommendation app and requests the recommendation server 180 to select a coordination most similar to a fashion style worn or worn by a specific person in the drama. do.
  • the recommendation server 180 Selects 1502 from the user's fashion collection a top, bottom, coat and ancillary accessories that best match the fashion style worn or worn by a particular person in the drama or movie (1502) and displays it to the user.
  • the recommendation server 180 Selects 1502 from the user's fashion collection a top, bottom, coat and ancillary accessories that best match the fashion style worn or worn by a particular person in the drama or movie (1502) and displays it to the user.
  • the scene 1503 of the scene of the drama or movie it is possible to allow the user to compare the coordination recommended by the recommendation server 180 with the fashion style worn by the actual character.
  • the recommendation server 180 of the present invention is a predetermined rule R01-R55 (for a combination of all the coordination that can be selected from the fashion collection input by the user, or a plurality of coordinations, for example, CD001-CD190 1601). 1602, it is determined how well the plurality of coordination CD001-CD190 (1601) is matched, and calculates the rule degree of agreement (1603) for each rule. Regularity of conformity is exemplified as having a value of 0-100% in the present invention.
  • These rules include general rules for preferred fashion combinations, commonly used in the general fashion industry described above.
  • R01 represents rules such as "the brightness is preferably darker from the top to the bottom", and R02 represents "a horizontal stripe is inappropriate for a fat body.”
  • the weight 1604 represents the weight for each of the rules R01-R55.
  • the recommendation server 180 determines how well match each rule R01-R55 with respect to the combination CD001-CD190 of all possible coordinations for a specific user, calculates the rule compliance degree for each rule and multiplies the corresponding weight ( 1605) calculate the final score 1606 by summing.
  • the recommendation server 180 presents the recommendation coordination to the user by the final score calculated for all the coordination CD001-CD190.
  • the weight corresponding to a rule with a high rule conformance * weight for the coordination is increased by a constant value, for example, +0.5, and "disliked". If is pressed, the weight corresponding to a rule with a high rule conformance * weighting value for the coordination is lowered by a constant value, for example, -0.5, so that when the recommendation server 180 recommends the next coordination, You can configure it to reflect the user's "likes” or "dislikes.”
  • the recommendation server 180 of the present invention can be applied to a social network environment.
  • a person other than the user may be configured to input a feedback about a recommendation coordination for the user or a coordination selected by the user.
  • the weight is increased by +0.5, as if the user "likes” or “dislikes”. Or -0.5 to descend.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Environmental & Geological Engineering (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un procédé de recommandation d'article de mode, le procédé comprenant les étapes consistant à : amener un utilisateur à enregistrer des articles de mode détenus par l'utilisateur ; générer une base de données par rapport aux articles de mode enregistrés ; et recommander à l'utilisateur une combinaison particulière d'articles de mode sur la base des articles enregistrés par l'utilisateur.
PCT/KR2018/006422 2017-06-05 2018-06-05 Serveur de recommandation d'article de mode, et procédé de recommandation d'article de mode utilisant ledit serveur WO2018226022A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170069665A KR20180133121A (ko) 2017-06-05 2017-06-05 패션 아이템 추천 서버 및 그를 이용한 패션 아이템 추천 방법
KR10-2017-0069665 2017-06-05

Publications (1)

Publication Number Publication Date
WO2018226022A1 true WO2018226022A1 (fr) 2018-12-13

Family

ID=64565993

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2018/006422 WO2018226022A1 (fr) 2017-06-05 2018-06-05 Serveur de recommandation d'article de mode, et procédé de recommandation d'article de mode utilisant ledit serveur

Country Status (2)

Country Link
KR (1) KR20180133121A (fr)
WO (1) WO2018226022A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110750567A (zh) * 2019-09-29 2020-02-04 珠海中科先进技术研究院有限公司 一种基于智能衣柜的穿搭数据生成方法及系统
US20200219166A1 (en) * 2019-01-08 2020-07-09 Electronics And Telecommunications Research Institute Apparatus and method for providing fashion coordination knowledge based on neural network having explicit memory

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20200092265A (ko) * 2019-01-24 2020-08-03 삼성전자주식회사 전자 장치 및 그 동작방법
KR102448593B1 (ko) * 2020-01-03 2022-09-28 배민준 지능형 화장 안내 방법과 그 방법을 위한 장치

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050123361A (ko) * 2004-06-25 2005-12-29 주식회사 팬택 이동 통신 단말기의 패션 매니저 서비스 제공 방법
US20090281922A1 (en) * 2008-05-12 2009-11-12 Childress Rhonda L Method and system for selecting clothing items according to predetermined criteria
KR101418372B1 (ko) * 2012-07-02 2014-07-14 주식회사 씨제이오쇼핑 가상피팅을 이용한 상품 추천 시스템 및 추천 방법
US20140379426A1 (en) * 2014-09-04 2014-12-25 Atelier CAAAW, Inc. System and method for providing automated clothing fashion recommendations
KR20160013496A (ko) * 2014-07-26 2016-02-04 주식회사 왁스앤컴퍼니 이미지 검색을 기반으로 사용자가 원하는 패션 아이템에 관한 정보를 제공하는 시스템

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050123361A (ko) * 2004-06-25 2005-12-29 주식회사 팬택 이동 통신 단말기의 패션 매니저 서비스 제공 방법
US20090281922A1 (en) * 2008-05-12 2009-11-12 Childress Rhonda L Method and system for selecting clothing items according to predetermined criteria
KR101418372B1 (ko) * 2012-07-02 2014-07-14 주식회사 씨제이오쇼핑 가상피팅을 이용한 상품 추천 시스템 및 추천 방법
KR20160013496A (ko) * 2014-07-26 2016-02-04 주식회사 왁스앤컴퍼니 이미지 검색을 기반으로 사용자가 원하는 패션 아이템에 관한 정보를 제공하는 시스템
US20140379426A1 (en) * 2014-09-04 2014-12-25 Atelier CAAAW, Inc. System and method for providing automated clothing fashion recommendations

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200219166A1 (en) * 2019-01-08 2020-07-09 Electronics And Telecommunications Research Institute Apparatus and method for providing fashion coordination knowledge based on neural network having explicit memory
CN110750567A (zh) * 2019-09-29 2020-02-04 珠海中科先进技术研究院有限公司 一种基于智能衣柜的穿搭数据生成方法及系统

Also Published As

Publication number Publication date
KR20180133121A (ko) 2018-12-13

Similar Documents

Publication Publication Date Title
US10963944B2 (en) System and method for fashion recommendations
WO2018226022A1 (fr) Serveur de recommandation d'article de mode, et procédé de recommandation d'article de mode utilisant ledit serveur
WO2020171535A2 (fr) Procédé pour fournir un service de recommandation d'article de mode en utilisant la forme du corps et l'historique d'achats de l'utilisateur
WO2016153200A2 (fr) Procédé d'essayage virtuel et programme informatique
JP6212013B2 (ja) 商品推奨装置及び商品推奨方法
KR20200046924A (ko) 패션 코디의 자동 추천 방법 및 시스템
US11157988B2 (en) System and method for fashion recommendations
WO2020235817A1 (fr) Procédé et dispositif de recommandation de style de mode en fonction des vêtements que possède un utilisateur
US20090281922A1 (en) Method and system for selecting clothing items according to predetermined criteria
US11509712B2 (en) Fashion item analysis based on user ensembles in online fashion community
JP4021149B2 (ja) コーディネートサービス方法、コンピュータ及びプログラム
WO2020141802A2 (fr) Procédé pour fournir un service de recommandation d'article de mode à un utilisateur en utilisant une date
WO2014119873A1 (fr) Procédé de génération et d'identification d'un code d'identification en forme d'image préférée et procédé pour fournir des informations l'utilisant
WO2020141799A2 (fr) Procédé pour fournir un service de recommandation d'article de mode à un utilisateur au moyen de données de calendrier
WO2020138941A2 (fr) Procédé de fourniture de service de recommandation d'article de mode à un utilisateur au moyen d'un geste de glissement
KR102212942B1 (ko) 유명 의상 디자이너 스타일 코디 제안 시스템 및 그 운용방법
US11526925B2 (en) System and method for fashion recommendations
US11430043B2 (en) System and method for fashion recommendations
JP2003345943A (ja) コーディネイト検索方法及びシステム
JP4297441B2 (ja) 衣料品等の商品販売システム
KR20200048508A (ko) 개인화된 의류 정보 제공 방법 및 장치
WO2021107642A2 (fr) Procédé, dispositif et système de fourniture d'informations de mode
WO2021107556A1 (fr) Procédé pour fournir un article recommandé sur la base d'informations d'événement d'utilisateur et dispositif pour l'exécuter
CN113935790A (zh) 穿搭推荐方法、装置、电子设备及存储介质
WO2020156306A1 (fr) Procédé, système et dispositif de traitement d'informations de collocation de vêtements, et procédé, système et dispositif de traitement d'objets de données

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18812844

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18812844

Country of ref document: EP

Kind code of ref document: A1