KR20180026155A - Apparatus for automatically analyzing pregerence of rental item using user image and method using the same - Google Patents

Abstract

Disclosed are an apparatus for automatically analyzing the preference of a rental item using a user image and a method using the same. The user image is collected from a user terminal. An item image for determining the preference of the rental item for a user is extracted from the user image. The preference of the rental image of the user for a plurality of rental items registered in an item rental service can be calculated in consideration of an item object detected in the item image. The profits of the item rental service can be improved by recommending the rental items with high rental possibility of the user by automatically acquiring preference information of the users using the item rental service.

Description

[0001] APPARATUS FOR AUTOMATICALLY ANALYZING PREFERENCE OF RENTAL ITEM USING USER IMAGE AND METHOD USING THE SAME [0002]

The present invention relates to a technique for automatically calculating a user's preference for a rental item, and more particularly, to a rental property preference automatic using a user image capable of analyzing a rental item preference by using item information included in a photograph or image related to the user And a method using the same.

The existing online shopping mall aims to sell items, and provides a service that allows the user to easily purchase desired items by inducing purchase by providing a list of items suitable for users. For example, when a user selects a specific item from an item list, the user provides an interface for inducing settlement of the selected item, thereby purchasing the desired item through online.

However, in the case of items such as clothes and bags, it is sensible to be fashionable, and in many cases, the price is high, so it may be reasonable to rent it rather than purchase it.

Accordingly, in recent years, there has been provided a service capable of displaying and lending clothing conforming to the user's body information or preference information.

However, the technology is silent about acquiring the user's preference information without the history of renting the item or the information input from the user, or automatically calculating the preference for the rental items registered in the rental service.

Korean Patent No. 10-0699138, March 16, 2007 (Name: Intelligent Apparel Rental and Sales Service System and Method)

An object of the present invention is to automatically grasp a user's preference tendency in order to accurately select a rental item suitable for a user.

In addition, the object of the present invention is to automatically calculate a user's preference for each rental item through an image that can be acquired from the user's terminal without confirming the rental history of the user or inputting the preference information from the user.

Also, the object of the present invention is to recommend a rental item which is likely to be rented by a user based on the user's preference for each rental item.

It is also an object of the present invention to improve the use efficiency of the item rental service by recommending an item which is expected to have a high preference to the user.

According to an aspect of the present invention, there is provided an apparatus for automatically analyzing rent item preference, comprising: an image collection unit for collecting a user image from a user terminal; An image extracting unit for extracting an item image for determining a rental item preference for the user in the user image; And a preference calculating unit for calculating a preference of the user for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image.

At this time, the image extracting unit may extract the item image for each type according to the predetermined item type considering the plurality of rental items.

An object detector for detecting the item object in the item image for each type using a preference calculating unit object extracting algorithm; And an object storage unit for classifying and storing the item objects according to a style within the preset item type.

At this time, the preference calculating unit may calculate the rent item preference using the ratio of the number of the item objects stored for each predetermined item type to the number of the item objects stored for each style.

At this time, the image collecting unit may collect the image stored in the terminal and the image including the user among the images uploaded to the user's social network service executed through the terminal, as the user image.

At this time, the image collecting unit acquires at least one of the user's terminal information and the face image information of the user based on the user information registered in the item rental service, and stores the face image information stored in the terminal Image and an image included in the user among the images uploaded to the user's social network service executed through the terminal.

At this time, the preference calculating unit may calculate the rent item preference with respect to each of the plurality of rental items, and compare the rental items having the rental item preference of the plurality of rental items with a predetermined reference preference or more to a recommended item list . ≪ / RTI >

At this time, the rental item preference automatic analyzing apparatus may further include an item recommending unit for recommending the rental item to the user based on the recommended item list.

At this time, the image collecting unit may collect the user image every predetermined period.

Also, the automatic item rental preference analyzing method according to the present invention includes: collecting a user image from a user terminal; Extracting an item image for determining a preference of a rental item for the user from the user image; And calculating the user's preference of the rental item for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image.

In this case, the extracting step may extract the item image for each type according to the predetermined item type considering the plurality of rental items.

In this case, the calculating step may include: detecting the item object in the type-specific item image using an object extraction algorithm; And classifying and storing the item object according to a style within the preset item type.

At this time, the calculating step may calculate the rent item preference using the ratio of the number of the item objects stored for each predetermined item type to the number of the item objects stored for each style.

At this time, the collecting step may collect the image including the user among the images stored in the terminal and images uploaded to the user's social network service executed through the terminal, as the user image .

At this time, the collecting step acquires at least one of the user's terminal information and the user's face image information based on the user information registered in the item rental service, The stored image and the image included in the user among the images uploaded to the user's social network service executed through the terminal.

In this case, the calculating step may include calculating the rent item preference for each of the plurality of rental items, and comparing rental items having the rental item preference of the plurality of rental items with a predetermined reference preference or more to a recommendation item You can add it to the list.

At this time, the method of automatically analyzing the preference of the rental item may further include recommending the rental item to the user based on the recommended item list.

In this case, the collecting step may collect the user image every predetermined period.

According to the present invention, the user's preference tendency can be automatically grasped in order to accurately select a rental item suitable for a user.

In addition, the present invention can automatically calculate a user's preference for each rental item through an image that can be acquired from the user's terminal without confirming the rental history of the user or inputting the preference information from the user.

In addition, the present invention can recommend a rental item that a user is likely to rent based on the user's preference for each rental item.

In addition, the present invention can improve the use efficiency of the item rental service by recommending an item which is expected to have a high preference to the user.

1 is a diagram illustrating a system for automatically analyzing rent item preference according to an exemplary embodiment of the present invention.
FIG. 2 is a block diagram showing an example of an apparatus for automatically analyzing the preference of a rental item shown in FIG. 1. FIG.
3 is a block diagram showing an example of the preference calculating unit shown in FIG.
4 is a diagram illustrating an item rental service according to an exemplary embodiment of the present invention.
5 to 9 are views showing an example of a user image, an item image, and an item object according to the present invention.
10 is a flowchart illustrating an automatic method of analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention.
11 is a detailed flowchart illustrating a method of automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed to be limited to ordinary or dictionary meanings and the inventor is not limited to the concept of terminology for describing his or her invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible. Also, the terms first, second, etc. are used for describing various components and are used only for the purpose of distinguishing one component from another component, and are not used to define the components.

1 is a diagram illustrating a system for automatically analyzing rent item preference according to an exemplary embodiment of the present invention.

1, the system for automatically analyzing rent item preference according to an exemplary embodiment of the present invention includes an automatic rent item preference analyzer 110, terminals 120-1 to 120-N, an item rental service server 130, Network 140. < / RTI >

The automatic item rental preference analyzer 110 analyzes the rental item preference of each of the terminals 120-1 to 120-N when the item rental service server 130 provides the item rental service to the terminals 120-1 to 120- It is possible to automatically analyze the rental item preference.

In this case, the automatic item analyzer 110 and the item rental service server 130 are separately shown in FIG. 1, but the automatic item rental preference analyzer 110 may not be provided with the item rental service server (130).

The rental item preference automatic analyzing apparatus 110 collects user images from the user's terminals 120-1 to 120-N.

At this time, among the images stored in the terminals 120-1 to 120-N and images uploaded to the user's social network service executed through the terminals 120-1 to 120-N, Images can be collected as user images.

At this time, based on the user information registered in the item rental service, at least one of the user's terminal information and the user's face image information is acquired, and the terminal 120-1 to 120-N It is possible to distinguish the images including the user from the images stored in the user's social network executed through the terminals 120-1 through 120-N.

At this time, the user image can be collected every predetermined period.

Also, the rental item preference automatic analyzing apparatus 110 extracts an item image for determining the preference degree of the rental item for the user in the user image.

At this time, an item image for each type can be extracted according to a predetermined item type considering a plurality of rental items.

In addition, the automatic rental-item-preference analyzer 110 calculates a user's preference for a rental item for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image.

At this time, an item object can be detected from an item image of each type by using an object extraction algorithm.

At this time, the item object can be classified and stored according to the style within the predetermined item type.

At this time, the rent item preference can be calculated using the ratio of the number of item objects stored for each preset item type and the number of item objects stored for each style.

At this time, the rental item preference is calculated for each of the plurality of rental items, and the rental items whose rental item preference among the plurality of rental items is equal to or higher than the preset reference preference may be added to the recommendation item list for the user.

In addition, the rental item preference automatic analyzer 110 recommends a rental item to the user based on the recommended item list.

The terminals 120-1 to 120-N may access the item rental service server 130 to use the item rental service provided by the item rental service server 130 or may connect the item rental service to the item rental service server 130 using a separate service application, Lt; / RTI >

At this time, the terminals 120-1 to 120-N are connected to the communication network and can connect to the item rental service server 130 or can execute applications. The terminals 120-1 to 120-N are mobile phones, Portable Multimedia Play (PMP) Various mobile communication specifications such as a mobile phone, a smart phone, a tablet PC, a notebook, a net book, a personal digital assistant (PDA) Or a mobile terminal having a mobile terminal.

The terminals 120-1 to 120-N receive various kinds of information such as numeric and character information, set various functions, and input signals related to the function control of the terminals 120-1 to 120-N And can be transmitted to the control unit through the input unit. The input unit of the terminals 120-1 to 120-N may include at least one of a keypad and a touchpad for generating an input signal according to a user's touch or operation. At this time, the input units of the terminals 120-1 to 120-N are configured in the form of one touch panel (or touch screen) together with the display units of the terminals 120-1 to 120-N, Display function can be performed at the same time. The input unit of the terminals 120-1 to 120-N may be any type of input unit that can be developed in addition to an input unit such as a keyboard, a keypad, a mouse, a joystick, and the like.

In addition, the display unit of the terminals 120-1 to 120-N can display information on a series of operation states, operation results, and the like that occur during the performance of the functions of the terminals 120-1 to 120-N. In addition, the display units of the terminals 120-1 to 120-N can display menus of the terminals 120-1 to 120-N and user data input by the user. The display units of the terminals 120-1 to 120-N may be a liquid crystal display (LCD), a thin film transistor LCD (TFT-LCD), a light emitting diode (LED) An organic light emitting diode (OLED), an organic light emitting diode (AMOLED), an active matrix OLED, a retina display, a flexible display, and a three-dimensional display have. At this time, when the display units of the terminals 120-1 to 120-N are configured as touch screens, the display units of the terminals 120-1 to 120-N function as the input units of the terminals 120-1 to 120- Some or all of them.

The storage units of the terminals 120-1 to 120-N are devices for storing data, and include a main storage device and an auxiliary storage device, and are used for applications required for functional operations of the terminals 120-1 to 120- You can save the program. The storage units of these terminals 120-1 to 120-N may largely include a program area and a data area. Here, when the terminals 120-1 to 120-N activate respective functions in response to a user's request, the terminals 120-1 to 120-N provide respective functions by executing corresponding application programs under the control of the controller. In particular, the storage units of the terminals 120-1 to 120-N according to the present invention may store an operating system for booting the terminals 120-1 to 120-N and programs for providing services. In addition, the storage units of the terminals 120-1 to 120-N may store information of a content DB storing a plurality of contents and information of the terminals 120-1 to 120-N. At this time, the content DB includes execution data for executing the content and attribute information about the content, and content usage information according to the execution of the content can be stored. The information of the terminals 120-1 to 120-N may include terminal specification information.

In addition, the communication units of the terminals 120-1 to 120-N may perform a function of transmitting and receiving data through the network. Here, the communication unit of the terminals 120-1 to 120-N may include RF transmitting means for up-converting and amplifying the frequency of the transmitted signal, RF receiving means for low-noise amplifying the received signal and down-converting the frequency . The communication units of the terminals 120-1 to 120-N may include at least one of a wireless communication module and a wired communication module. In the case where the terminals 120-1 to 120-N use wireless communication, the wireless communication module is a module for transmitting and receiving data according to a wireless communication method. The wireless communication module, the wireless LAN communication module, Data can be transmitted / received using any one of the above-described methods. The wired communication module is for transmitting / receiving data by wire. The wired communication module can connect to the network through wired and send / receive data. That is, the terminals 120-1 to 120-N access the network using a wireless communication module or a wired communication module, and can transmit and receive data through the network.

In addition, the control units of the terminals 120-1 to 120-N may be an operating system (OS) and a process unit for driving each configuration. For example, the control unit can control the entire process of connecting to the server. When accessing the server through a separate service application, the entire process of executing the service application can be controlled according to the request of the user, and the service use request can be transmitted to the server at the same time as execution. The information of the terminals 120-1 to 120-N necessary for the terminal 120-1 to be transmitted together can be controlled.

In addition, the control units of the terminals 120-1 to 120-N can execute the specific contents stored in the storage units of the terminals 120-1 to 120-N according to the request of the user. At this time, the control unit can store the content usage history according to the execution of the content as the content usage information.

The item rental service server 130 is a server for providing an item rental service to the terminals 120-1 to 120-N. The item rental service server 130 provides a rental item to users of the terminals 120-1 to 120-N, You can claim.

At this time, the item rental service server 130 may connect with the terminals 120-1 to 120-N of the users through the network 140 to provide the item rental service.

In addition, the item rental service server 130 can automatically acquire rental item preference information for service users by communicating with the automatic item rental preference analyzer 110 according to the present invention through the network 140. [

The network 140 provides a channel for transferring data between the automatic item analyzer 110 for analyzing the rental item preferences, the terminals 120-1 to 120-N and the item rental service server 130, And future developable networks. For example, the network may be a wired or wireless local area network that provides communication of various information devices within a limited area, a mobile communication network that provides communication between mobile objects and mobile objects outside the mobile object, A satellite communication network, a wired / wireless communication network, or a combination of two or more. Meanwhile, the network transmission standard is not limited to the existing transmission standard but may include all transmission standard to be developed in the future.

FIG. 2 is a block diagram showing an example of an apparatus for automatically analyzing the preference of a rental item shown in FIG. 1. FIG.

1, the automatic item rental preference analyzing apparatus 110 includes a communication unit 210, an image collecting unit 220, an image extracting unit 230, a preference calculating unit 240, (250) and a storage unit (260).

The communication unit 210 can transmit and receive information necessary for calculating and analyzing the preference of the rental item with the user terminal and the item rental service server through a communication network such as a network. In particular, the communication unit 210 according to an exemplary embodiment of the present invention collects and receives a user image for calculating the preference of the rental item from the user terminal, and provides the item rental service server with rental item preference information and recommendation item list .

The image collection unit 220 collects the user image from the user terminal.

At this time, there is a high possibility that the user image includes clothing, user's favorite accessories, or accessories commonly used by the user. That is, it can be used to analyze the preference of a rental item to a user in the future by acquiring an image including a wearer's usual clothes or item information to be used from the user's terminal.

At this time, the image stored in the terminal and the image including the user among the images uploaded to the user's social network service executed through the terminal can be collected as a user image.

For example, it is possible to access an application corresponding to a camera or a gallery among applications installed in a smart terminal of a user, thereby collecting images stored in the terminal of the user. At this time, a separate application for automatically analyzing the preference of the rental item may be installed in the user terminal so as to access the camera or the gallery. Also, the user can access the camera or the gallery installed in the user terminal through a separate application that performs the item rental service, and collect user images.

In another example, the user may access at least one social network service used by the user to collect images uploaded by the user. At this time, the social network service may correspond to any of the services in which the image can be uploaded from the user.

At this time, based on the user information registered in the item rental service, at least one of the user's terminal information and the user's face image information can be obtained.

For example, when the user subscribes to the item rental service, the terminal information and the user's face image information may be input from the user or acquired through the user's terminal in order to automatically analyze the rental item preference for the user.

At this time, the account information of the social network service used by the user can be inputted together. That is, the user may access the social network service based on the user's social network account to collect the user image.

In addition, when there are a plurality of terminals that the user normally uses, information about the terminals can be acquired and stored.

Also, the image stored in the terminal and the image included in the user among the images uploaded to the social network service executed through the terminal can be distinguished using the user's face image information.

For example, among the images stored in the terminal of the user, there is a high possibility that the user is not included or an image including only the user's acquaintances exists. The same is true for images uploaded to social network services. Accordingly, in order to acquire information on the items that the user normally uses, the user image must be included in the user image.

Accordingly, among the images stored in the terminal and the images uploaded to the social network service, only the image including the user's face image can be distinguished and collected as the user image.

When an image stored in the terminal and an image uploaded to the social network service do not include a separate person and there is an image focused on a specific item, the user determines that the item is interested in the item, .

For example, a user may take a shopping bag with a smartphone that he did not purchase while shopping. At this time, it is possible to analyze the user's preference of the bag included in the future image by collecting the photograph of the bag stored in the smart phone as the user image.

At this time, the user image can be collected every predetermined period.

Assuming that there are a plurality of users registered in the item rental service, too much load may be generated in the system for automatically analyzing the rental item preference when collecting user images every hour through terminals corresponding to a plurality of users . Such a load may cause a system error and cause the system to halt.

Therefore, in order to prevent such a problem, in the present invention, a period for collecting a user image may be set in advance, and a user image may be collected from a user terminal every time the corresponding period returns.

For example, if it is assumed that the preset period is one week, the user image can be collected and stored from the user terminal every Sunday.

At this time, the preset period can be freely set and changed by the manager of the system for automatically analyzing the rent item preference or the user using the rental item service.

The image extracting unit 230 extracts an item image for determining the preference degree of the rental item for the user in the user image.

At this time, the item image may correspond to an image for specific items in the user image.

For example, assuming that the user included in the user image wears sunglasses, a certain area including the sunglasses can be extracted as an item image.

For another example, the image included in the user image may be extracted as an item image, and a certain area corresponding to the bottom and the bottom of the image, respectively.

At this time, the item image may be extracted into a predetermined shape region or a portion corresponding to the shape of the item to be extracted.

At this time, an item image for each type can be extracted according to a predetermined item type considering a plurality of rental items.

For example, when a plurality of rental items provided in the item rental service mainly correspond to clothes, an item type is classified into an upper, a lower, a dress, and shoes, and an item image is extracted based on items corresponding to the divided types .

In another example, when a plurality of rental items provided in the item rental service correspond to goods such as a bag or an accessory, the item type is classified into a bag, a wallet, an earring, a necklace, a bracelet, a hat, It is possible to extract the item image based on the item corresponding to the selected type.

In another example, when a plurality of rental items provided in the item rental service corresponds to most items such as clothing, sundries, and accessories, the item type is classified into clothes, bags, hats, accessories, shoes, Most items included in the item image can be extracted as an item image.

The preference calculating unit 240 calculates a user's preference for a rental item for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image. That is, it can be determined that the item object detected from the user image is the item of the user's preferred type, and the preference for the rental item of a type similar to the item object among the plurality of rental items can be calculated.

At this time, an item object can be detected from an item image of each type by using an object extraction algorithm.

At this time, the object extraction algorithm can recognize a specific object in the image and extract it as a single object. There are various kinds of object extraction algorithms according to a method of recognizing objects in an image. In the present invention, various kinds of object extraction algorithms can be used variously according to the configuration of the system, not limited to specific object extraction algorithms.

At this time, the item object can be classified and stored according to the style within the predetermined item type.

For example, if it is assumed that an item object corresponding to an item type is detected in an item image, the item object can be classified and stored according to styles corresponding to sunglasses such as a cat eye, an aviator, and a club master.

For example, if it is assumed that an item object corresponding to a skirt is detected in an item image, the item object is classified and stored according to a style corresponding to a skirt such as an A-line skirt, an H-line skirt, a trumpet skirt, and a flare skirt It is possible.

At this time, the rent item preference can be calculated using the ratio of the number of item objects stored for each preset item type and the number of item objects stored for each style.

For example, it can be assumed that the number of item objects corresponding to the item type of sunglasses is 100, and the number of item objects corresponding to the style of the aviator among the sunglasses is 10. At this time, the ratio of the number of item objects stored for each predetermined item type and the number of item objects stored for each style is 100: 10, that is, the preference of the rental item corresponding to the aviator style sunglasses can be calculated corresponding to 10% .

In this case, if it is determined that the number of item objects stored for each preset item type is too small to accurately calculate the rent item preference, the rental item preference calculation may be discontinued until a certain number of item objects are stored.

For example, if only one item object corresponding to an item type skirt is stored, the preference of a rental item corresponding to a currently stored skirt of one style can be calculated by 100%. Since it is difficult to judge that this is an accurate result, it is possible to set the minimum number of object storage for each style and calculate the preference of the rental item for that style only when the item object is stored in the minimum number of object storage.

At this time, the rental item preference is calculated for each of the plurality of rental items, and the rental items whose rental item preference among the plurality of rental items is equal to or higher than the preset reference preference may be added to the recommendation item list for the user.

For example, if it is assumed that the predetermined reference preference is 50%, it is possible to add rental items having a preference value of 50% or more calculated through automatic analysis of the rental item preference according to the present invention among the plurality of rental items to the recommended item list .

The item recommending unit 250 recommends a rental item to the user based on the recommended item list.

In addition, by providing the recommendation item list to the item rental service server, the item rental service server can recommend the rental item included in the recommended item list to the user.

The storage unit 260 stores various information generated in the process of automatically analyzing the preference of the rental item according to an embodiment of the present invention, as described above.

According to the embodiment, the storage unit 260 may be configured independently of the automatic analyzing apparatus for analyzing the preference of the rental item to support a function for automatically analyzing the preference of the rental item. At this time, the storage unit 250 may operate as a separate mass storage and may include a control function for performing operations.

On the other hand, the rental item preference automatic analyzing apparatus can store information in a memory equipped with the apparatus. In one implementation, the memory is a computer-readable medium. In one implementation, the memory may be a volatile memory unit, and in other embodiments, the memory may be a non-volatile memory unit. In one implementation, the storage device is a computer-readable medium. In various different implementations, the storage device may include, for example, a hard disk device, an optical disk device, or any other mass storage device.

By using the automatic analyzing device of the preference of the rental item, it is possible to automatically grasp the preference of the user in order to accurately select the rental item suitable for the user.

Also, it is possible to automatically calculate the user's preference for each rental item through an image that can be acquired from the user's terminal without confirming the rental history of the user or inputting the preference information from the user.

Also, it is possible to recommend a rental item, which is likely to be borrowed by the user, based on the user's preference for each rental item, thereby improving the use efficiency of the item rental service.

3 is a block diagram showing an example of the preference calculating unit shown in FIG.

Referring to FIG. 3, the preference calculating unit 240 shown in FIG. 2 includes an object detecting unit 310 and an object storing unit 320.

The object detection unit 310 detects an item object in an item image by type using an object extraction algorithm.

At this time, the object extraction algorithm can recognize a specific object in the image and extract it as a single object. There are various kinds of object extraction algorithms according to a method of recognizing objects in an image. In the present invention, various kinds of object extraction algorithms can be used variously according to the configuration of the system, not limited to specific object extraction algorithms.

The object storage unit 320 classifies and stores item objects according to a style within a preset item type.

For example, if it is assumed that an item object corresponding to an item type is detected in an item image, the item object can be classified and stored according to styles corresponding to sunglasses such as a cat eye, an aviator, and a club master.

For example, if it is assumed that an item object corresponding to a skirt is detected in an item image, the item object is classified and stored according to a style corresponding to a skirt such as an A-line skirt, an H-line skirt, a trumpet skirt, and a flare skirt It is possible.

4 is a diagram illustrating an item rental service according to an exemplary embodiment of the present invention.

4, an item rental service according to an exemplary embodiment of the present invention is provided through a process of registration, customized item offering, delivery and return or purchase .

At this time, the user registration process can be subdivided into a membership registration process and a profiling process.

For example, the membership process may correspond to a process in which a user accesses and joins a server in order to use an item rental service.

Also, in the profiling process, the user's fashion preference can be investigated. For example, an item owned by the user can be registered in the server, or an item of a style preferred by the user can be registered in the server. In addition, in the profiling process, a profiling meeting is performed with the user at a 1: 1 level, thereby grasping the user's body shape, fashion shopping occasion, and style.

At this time, the rent item preference automatic analyzing apparatus according to the present invention collects the user image from the user's terminal and can calculate the user's rent item preference.

At this time, the Personal Offering process can be subdivided into a custom set delivery process, a virtual fitting process, and a Pick & Confirm process.

For example, a custom set delivery process may analyze a user's preference information and then send a Personal Styling Set to a mobile application or mail. At this time, the Personal Styling Set can be composed of an upper, a lower, a shoe, a bag, and an additional item.

In addition, the Personal Styling Set can be provided in the form of virtual fitting based on the user's body shape.

Therefore, the user can confirm the customized set provided through the virtual fitting and confirm the desired product only.

At this time, the delivery process can package selected products in the Pick & Confirm process as a gift box or dry cleaning type and deliver them to the user's home.

Thereafter, the return process uses the item rented by the user for a desired period or for a specified period of time, connects to the item rental server and clicks the return button for the item, automatically receives the withdrawal request and returns the item . At this time, after the items corresponding to the return button input are collected, the next product can be delivered.

Also, the 'Keep' process can perform purchase based on the item rental server when the user wants to purchase the rented item.

FIG. 9 is a view showing an example of a user image, an item image, and an item object according to the present invention.

5 to 9, a user image according to the present invention may be collected from an image stored in a terminal of a user as shown in FIGS. 5 to 6, or may be collected from an image posted to a user SNS as shown in FIGS. have.

At this time, the automatic item rental preference analyzing apparatus according to the present invention can acquire the images (500, 600) stored in the terminal by accessing the camera and gallery application installed in the user's terminal.

In addition, the automatic item rental preference analyzing apparatus according to the present invention obtains the SNS account information of the user through the user information, accesses the SMS (Social Network Service) of the user based on the obtained SNS account information, Images 700, 800, 900 can be obtained.

In this case, when the user uses various types of SNSs as shown in FIGS. 7 to 9, the user may access the various SNSs to collect user images.

At this time, the automatic item rental preference analyzing apparatus according to the present invention can collect only the user image including the user among the various images that can be collected from the terminal or the SNS using the face image information of the user included in the user information have.

At this time, the reason why the user only collects the included images may be that it is necessary to acquire item information to be worn or used by the user in order to calculate the preference of the rental item for the user.

Alternatively, in the case of an image based on an item rather than a person, such as the image 900 posted on the user SNS shown in FIG. 9, it is determined that the user has liked the item included in the image and posted or stored the item, Images can also be collected as user images.

In this case, the automatic item rental preference analyzing apparatus according to the present invention may include item images 510, 520, 530, 610, 620, and 630 corresponding to the respective items included in the user image, , 710, 720, 730, 810, 820, 910, 920).

For example, referring to FIGS. 5 to 6, areas including sunglasses, coats, bags, walkers and hand held purses that the user wears in images 500 and 600 stored in the terminal are referred to as item images 510, 520, 530, 610, 620, 630).

7 to 9, the image 700, 800, 900 posted to the user SNS may be displayed on the screen of the user 700 with the hat, shoes, bag, headphone, bracelet worn by the user, 720, 730, 810, 820, 910, and 920, respectively, of the region including the sneaker and the bag in which the focus is set in the item images 710, 720, 730, 810,

In this case, the areas of the item images 510, 520, 530, 610, 620, 630, 710, 720, 730, 810, 820, 910 and 920 shown in FIGS. 5 to 9 are all rectangular , The area of the item image is not limited to a certain shape but can be variously extracted.

In this case, the automatic item rental preference analyzing apparatus according to the present invention may include item objects 511, 521, 531, 611, 621, 631, 711, 721, 731, 811 , 821, 911, and 921 can be detected.

At this time, the rental item preference automatic analyzing apparatus according to the present invention can detect an item object by using a separate object extraction algorithm for recognizing the object in the image.

10 is a flowchart illustrating an automatic method of analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention.

Referring to FIG. 10, a method for automatically analyzing rent item preference using a user image according to an exemplary embodiment of the present invention collects a user image from a user terminal (S1010).

At this time, there is a high possibility that the user image includes clothing, user's favorite accessories, or accessories commonly used by the user. That is, it can be used to analyze the preference of a rental item to a user in the future by acquiring an image including a wearer's usual clothes or item information to be used from the user's terminal.

At this time, the image stored in the terminal and the image including the user among the images uploaded to the user's social network service executed through the terminal can be collected as a user image.

For example, it is possible to access an application corresponding to a camera or a gallery among applications installed in a smart terminal of a user, thereby collecting images stored in the terminal of the user. At this time, a separate application for automatically analyzing the preference of the rental item may be installed in the user terminal so as to access the camera or the gallery. Also, the user can access the camera or the gallery installed in the user terminal through a separate application that performs the item rental service, and collect user images.

In another example, the user may access at least one social network service used by the user to collect images uploaded by the user. At this time, the social network service may correspond to any of the services in which the image can be uploaded from the user.

At this time, based on the user information registered in the item rental service, at least one of the user's terminal information and the user's face image information can be obtained.

For example, when the user subscribes to the item rental service, the terminal information and the user's face image information may be input from the user or acquired through the user's terminal in order to automatically analyze the rental item preference for the user.

At this time, the account information of the social network service used by the user can be inputted together. That is, the user may access the social network service based on the user's social network account to collect the user image.

In addition, when there are a plurality of terminals that the user normally uses, information about the terminals can be acquired and stored.

Also, the image stored in the terminal and the image included in the user among the images uploaded to the social network service executed through the terminal can be distinguished using the user's face image information.

For example, among the images stored in the terminal of the user, there is a high possibility that the user is not included or an image including only the user's acquaintances exists. The same is true for images uploaded to social network services. Accordingly, in order to acquire information on the items that the user normally uses, the user image must be included in the user image.

Accordingly, among the images stored in the terminal and the images uploaded to the social network service, only the image including the user's face image can be distinguished and collected as the user image.

When an image stored in the terminal and an image uploaded to the social network service do not include a separate person and there is an image focused on a specific item, the user determines that the item is interested in the item, .

For example, a user may take a shopping bag with a smartphone that he did not purchase while shopping. At this time, it is possible to analyze the user's preference of the bag included in the future image by collecting the photograph of the bag stored in the smart phone as the user image.

At this time, the user image can be collected every predetermined period.

Assuming that there are a plurality of users registered in the item rental service, too much load may be generated in the system for automatically analyzing the rental item preference when collecting user images every hour through terminals corresponding to a plurality of users . Such a load may cause a system error and cause the system to halt.

Therefore, in order to prevent such a problem, in the present invention, a period for collecting a user image may be set in advance, and a user image may be collected from a user terminal every time the corresponding period returns.

For example, if it is assumed that the preset period is one week, the user image can be collected and stored from the user terminal every Sunday.

At this time, the preset period can be freely set and changed by the manager of the system for automatically analyzing the rent item preference or the user using the rental item service.

In addition, an automatic method of analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention extracts an item image for determining a rental item preference for a user in a user image (S1020).

At this time, the item image may correspond to an image for specific items in the user image.

For example, assuming that the user included in the user image wears sunglasses, a certain area including the sunglasses can be extracted as an item image.

For another example, the image included in the user image may be extracted as an item image, and a certain area corresponding to the bottom and the bottom of the image, respectively.

At this time, the item image may be extracted into a predetermined shape region or a portion corresponding to the shape of the item to be extracted.

At this time, an item image for each type can be extracted according to a predetermined item type considering a plurality of rental items.

For example, when a plurality of rental items provided in the item rental service mainly correspond to clothes, an item type is classified into an upper, a lower, a dress, and shoes, and an item image is extracted based on items corresponding to the divided types .

In another example, when a plurality of rental items provided in the item rental service correspond to goods such as a bag or an accessory, the item type is classified into a bag, a wallet, an earring, a necklace, a bracelet, a hat, It is possible to extract the item image based on the item corresponding to the selected type.

In another example, when a plurality of rental items provided in the item rental service corresponds to most items such as clothing, sundries, and accessories, the item type is classified into clothes, bags, hats, accessories, shoes, Most items included in the item image can be extracted as an item image.

In addition, the method of automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention may include analyzing a user's preference of a rental item for a plurality of rental items registered in the item rental service, (S1030). That is, it can be determined that the item object detected from the user image is the item of the user's preferred type, and the preference for the rental item of a type similar to the item object among the plurality of rental items can be calculated.

At this time, an item object can be detected from an item image of each type by using an object extraction algorithm.

At this time, the object extraction algorithm can recognize a specific object in the image and extract it as a single object. There are various kinds of object extraction algorithms according to a method of recognizing objects in an image. In the present invention, various kinds of object extraction algorithms can be used variously according to the configuration of the system, not limited to specific object extraction algorithms.

At this time, the item object can be classified and stored according to the style within the predetermined item type.

For example, if it is assumed that an item object corresponding to an item type is detected in an item image, the item object can be classified and stored according to styles corresponding to sunglasses such as a cat eye, an aviator, and a club master.

For example, if it is assumed that an item object corresponding to a skirt is detected in an item image, the item object is classified and stored according to a style corresponding to a skirt such as an A-line skirt, an H-line skirt, a trumpet skirt, and a flare skirt It is possible.

At this time, the rent item preference can be calculated using the ratio of the number of item objects stored for each preset item type and the number of item objects stored for each style.

For example, it can be assumed that the number of item objects corresponding to the item type of sunglasses is 100, and the number of item objects corresponding to the style of the aviator among the sunglasses is 10. At this time, the ratio of the number of item objects stored for each predetermined item type and the number of item objects stored for each style is 100: 10, that is, the preference of the rental item corresponding to the aviator style sunglasses can be calculated corresponding to 10% .

In this case, if it is determined that the number of item objects stored for each preset item type is too small to accurately calculate the rent item preference, the rental item preference calculation may be discontinued until a certain number of item objects are stored.

For example, if only one item object corresponding to an item type skirt is stored, the preference of a rental item corresponding to a currently stored skirt of one style can be calculated as 100%. Since it is difficult to judge that this is an accurate result, it is possible to set the minimum number of object storage for each style and calculate the preference of the rental item for that style only when the item object is stored in the minimum number of object storage.

At this time, the rental item preference is calculated for each of the plurality of rental items, and the rental items whose rental item preference among the plurality of rental items is equal to or higher than the preset reference preference may be added to the recommendation item list for the user.

For example, if it is assumed that the predetermined reference preference is 50%, it is possible to add rental items having a preference value of 50% or more calculated through automatic analysis of the rental item preference according to the present invention among the plurality of rental items to the recommended item list .

Although not shown in FIG. 10, the method of automatically analyzing the preference of the rental item using the user image according to an exemplary embodiment of the present invention recommends the rental item to the user based on the recommended item list.

In addition, by providing the recommendation item list to the item rental service server, the item rental service server can recommend the rental item included in the recommended item list to the user.

In addition, although not shown in FIG. 10, a method of automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention includes calculating and analyzing the preference of a rental item and a user terminal and an item rental service server through a communication network such as a network It is possible to transmit and receive the information necessary for it. Particularly, a user image is collected and received from a user terminal to calculate rental item preference, and the item rental service server can provide rental item preference information and a recommendation item list for the user.

Although not shown in FIG. 10, a method of automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention may be performed in the automatic analysis of the preference of a rental item according to an exemplary embodiment of the present invention Various information is stored in a separate storage module.

The user can automatically grasp the user's preference tendency in order to accurately select the rental item suitable for the user through the automatic analysis method of the user's name and preference of the user.

Also, it is possible to automatically calculate the user's preference for each rental item through an image that can be acquired from the user's terminal without confirming the rental history of the user or inputting the preference information from the user.

Also, it is possible to recommend a rental item, which is likely to be borrowed by the user, based on the user's preference for each rental item, thereby improving the use efficiency of the item rental service.

11 is a detailed flowchart illustrating a method of automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention.

Referring to FIG. 11, a method for automatically analyzing the preference of a rental item using a user image according to an exemplary embodiment of the present invention may first acquire user information registered in an item rental service (S 1110).

That is, in order to automatically analyze the preference of the rental item for the user, the user may be a registered or subscribed user of the item rental service. At this time, the user information may be inputted and stored by the user at the time when the user registers or subscribes to the item rental service.

After that, the terminal information included in the user information and the face image information of the user can be acquired (S1120).

At this time, the account information of the user's social network service included in the user information can also be acquired.

Thereafter, the image stored in the terminal and the image uploaded to the SNS may be collected (S1130).

For example, it is possible to access an application corresponding to a camera or a gallery among applications installed in a smart terminal of a user, thereby collecting images stored in the terminal of the user. At this time, a separate application for automatically analyzing the preference of the rental item may be installed in the user terminal so as to access the camera or the gallery. Also, the user can access the camera or the gallery installed in the user terminal through a separate application that performs the item rental service, and collect user images.

In another example, the user may access at least one social network service used by the user to collect images uploaded by the user. At this time, the social network service may correspond to any of the services in which the image can be uploaded from the user.

At this time, the image stored in the terminal and the image included in the user among the images uploaded to the social network service executed through the terminal can be distinguished using the user's face image information.

For example, among the images stored in the terminal of the user, there is a high possibility that the user is not included or an image including only the user's acquaintances exists. The same is true for images uploaded to social network services. Accordingly, in order to acquire information on the items that the user normally uses, the user image must be included in the user image.

When an image stored in the terminal and an image uploaded to the social network service do not include a separate person and there is an image focused on a specific item, the user determines that the item is interested in the item, .

Thereafter, an item image for each type may be extracted according to a predetermined item type considering a plurality of rental items registered in the item rental service in the user image (S1140).

For example, when a plurality of rental items provided in the item rental service mainly correspond to clothes, an item type is classified into an upper, a lower, a dress, and shoes, and an item image is extracted based on items corresponding to the divided types .

In another example, when a plurality of rental items provided in the item rental service correspond to goods such as a bag or an accessory, the item type is classified into a bag, a wallet, an earring, a necklace, a bracelet, a hat, It is possible to extract the item image based on the item corresponding to the selected type.

In another example, when a plurality of rental items provided in the item rental service corresponds to most items such as clothing, sundries, and accessories, the item type is classified into clothes, bags, hats, accessories, shoes, Most items included in the item image can be extracted as an item image.

Thereafter, the item object can be detected in the item image for each type using the object extraction algorithm (S1150).

At this time, an item object can be detected from an item image of each type by using an object extraction algorithm.

Thereafter, the item objects may be classified and stored according to a style within the preset item type (S1160).

For example, if it is assumed that an item object corresponding to an item type is detected in an item image, the item object can be classified and stored according to styles corresponding to sunglasses such as a cat eye, an aviator, and a club master.

For example, if it is assumed that an item object corresponding to a skirt is detected in an item image, the item object is classified and stored according to a style corresponding to a skirt such as an A-line skirt, an H-line skirt, a trumpet skirt, and a flare skirt It is possible.

After that, the rental item preference can be calculated using the ratio of the number of item objects stored for each preset item type and the number of item objects stored for each style (S1170).

For example, it can be assumed that the number of item objects corresponding to the item type of sunglasses is 100, and the number of item objects corresponding to the style of the aviator among the sunglasses is 10. At this time, the ratio of the number of item objects stored for each predetermined item type and the number of item objects stored for each style is 100: 10, that is, the preference of the rental item corresponding to the aviator style sunglasses can be calculated corresponding to 10% .

Thereafter, the rental items having the rent item preference of the plurality of rental items equal to or greater than a preset reference may be added to the recommend item list for the user (S1180).

For example, if it is assumed that the predetermined reference preference is 50%, it is possible to add rental items having a preference value of 50% or more calculated through automatic analysis of the rental item preference according to the present invention among the plurality of rental items to the recommended item list .

Thereafter, the rental item can be recommended to the user based on the recommended item list (S1190).

In addition, by providing the recommendation item list to the item rental service server, the item rental service server can recommend the rental item included in the recommended item list to the user.

Certain embodiments of the subject matter described herein have been described. Other embodiments are within the scope of the following claims. For example, the operations recited in the claims may be performed in a different order and still achieve desirable results. By way of example, the process illustrated in the accompanying drawings does not necessarily require that particular illustrated or sequential order to obtain the desired results. In certain implementations, multitasking and parallel processing may be advantageous.

The description sets forth the best modes of the present invention and provides examples for the purpose of illustrating the invention and enabling a person skilled in the art to make and use the invention. The written description is not intended to limit the invention to the specific terminology presented. Thus, while the present invention has been described in detail with reference to the above examples, those skilled in the art will recognize that modifications, changes, and modifications can be made thereto without departing from the scope of the present invention.

The method of automatically analyzing the preference of a rental item according to the present invention may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Includes all types of hardware devices that are specially configured to store and execute magneto-optical media and program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such a hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the automatic item rental preference analyzing apparatus and method using the user image according to the present invention are not limited to the configuration and method of the above-described embodiments, All or some of the embodiments may be selectively combined.

According to the present invention, a user image is collected from a user terminal, an item image for judging a rental item preference for a user in a user image is extracted, and a plurality of items registered in an item rental service It is possible to calculate the user's preference of the rental item with respect to the rental items. Further, it is possible to improve the profit of the item rental service by recommending the rental item more effectively by automatically generating information of the rental items preferred by the users using the item rental service.

110: Automatically analyzing the preference of the rental item
120-1 to 120-N: terminal 130: an item rental service server
140: Network 210:
220: image collecting unit 230: image extracting unit
240: preference calculating unit 250: item recommendation unit
260: storage unit 310: object detection unit
320: Object storage unit
500, 600: Images stored in the terminal
510, 520, 530, 610, 620, 630: Item image
511, 521, 531, 611, 621, 631:
700, 800, 900: Images posted to your SNS
710, 720, 730, 810, 820, 910, 920: Item image
711, 721, 731, 811, 821, 911, 921:

Claims (10)

An image collection unit for collecting a user image from a user terminal;
An image extracting unit for extracting an item image for determining a rental item preference for the user in the user image; And
A preference calculating unit for calculating a preference of the user for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image,
And an automatic analyzer for analyzing the preference of the rental item. The method according to claim 1,
The image extracting unit
And an item image for each type is extracted according to a predetermined item type in consideration of the plurality of rental items. The method of claim 2,
The preference calculating unit
An object detection unit for detecting the item object in the type-specific item image using an object extraction algorithm; And
And an object storage unit for classifying and storing the item objects according to a style within the preset item type. The method of claim 3,
The preference calculating unit
Wherein the rent item preference is calculated using the ratio of the number of the item objects stored for each preset item type to the number of the item objects stored for each style. The method according to claim 1,
The image collecting unit
And automatically collects an image including the user among the images stored in the terminal and the image uploaded to the user's social network service executed through the terminal as the user image. Device. The method of claim 5,
The image collecting unit
Acquiring at least one of the terminal information of the user and the face image information of the user on the basis of the user information registered in the item rental service, and using the image stored in the terminal and the terminal Wherein the image analyzing unit distinguishes the images included in the user from the images uploaded to the social network service of the user to be executed. The method of claim 4,
The preference calculating unit
Wherein the rental item preference is calculated for each of the plurality of rental items and the rental items whose rental item preference among the plurality of rental items is equal to or greater than a preset reference preference are added to the recommendation item list for the user Automatic item preference analysis device. The method of claim 7,
The rental item preference automatic analyzing device
And an item recommendation unit for recommending a rental item to the user based on the recommended item list. The method of claim 5,
The image collecting unit
And the user image is collected every predetermined period. Collecting a user image from a user terminal;
Extracting an item image for determining a preference of a rental item for the user from the user image; And
Calculating a user's rental item preference for a plurality of rental items registered in the item rental service in consideration of the item object detected in the item image
And automatically analyzing the preference of the rental item.

Images