KR102268009B1 - Shopping mall system and method for recommendation goods using text analysis - Google Patents

Abstract

A product recommendation shopping mall system using text analysis according to an embodiment of the present invention includes: a shopping mall server to which a plurality of user terminals are connected and providing a product recommendation user interface to the user terminals; and a text analysis device that receives, as metadata, text information corresponding to images of each product provided by the shopping mall server in cooperation with the shopping mall server, analyzes it, and generates and provides product attribute values corresponding to the respective products, , the shopping mall server includes a first database in which product images for each product are stored and a second database in which attribute values of products corresponding to the images for each product are stored.

Description

Product recommendation shopping mall system and method using text analysis {SHOPPING MALL SYSTEM AND METHOD FOR RECOMMENDATION GOODS USING TEXT ANALYSIS}

An embodiment of the present invention relates to a shopping mall system, and more particularly, to a shopping mall system and a method for analyzing text corresponding to a product image, storing it in a database, and recommending a product suitable for a customer using the analysis.

Along with the rapid increase in the number of Internet users, the number of users who purchase products through an online shopping mall is also rapidly increasing. Purchasing products through such an online shopping mall has the advantage of being able to quickly and conveniently search for and purchase desired products at home or at work without actually visiting an offline store.

However, purchasing a product through an existing online shopping mall has a disadvantage in that it is impossible to actually view and purchase the product. In particular, in the case of products such as clothing, the use of online shopping malls may be somewhat lower than that of other products due to the high demand from customers to directly check design and size.

Accordingly, there is a need for online shopping malls handling clothing products to provide various methods for selecting products suitable for customers by reflecting customer requirements more actively than online shopping malls handling other products.

An embodiment of the present invention analyzes texts corresponding to images of each product for products in a shopping mall system, extracts features of each product, stores them in a database as product attribute values, and product attributes for each product stored in the database An object of the present invention is to provide a product recommendation shopping mall system and method using text analysis that can recommend products suitable for user needs by using values.

In addition, a product recommendation user interface is provided to a user who has accessed the shopping mall system, and through this, arbitrary two products are displayed so that the user can select one of them, and the product attribute values of the products selected by the user are repeated by repeating this process. An object of the present invention is to provide a product recommendation shopping mall system and a method using text analysis that extracts and recommends products including all of the common characteristics of these product attribute values to a user.

In order to achieve the above object, a product recommendation shopping mall system using text analysis according to an embodiment of the present invention includes: a shopping mall server to which a plurality of user terminals are connected and providing a product recommendation user interface to the user terminals; and a text analysis device that receives, as metadata, text information corresponding to images of each product provided by the shopping mall server in cooperation with the shopping mall server, analyzes it, and generates and provides product attribute values corresponding to the respective products, , the shopping mall server includes a first database in which product images for each product are stored and a second database in which attribute values of products corresponding to the images for each product are stored.

The text analysis apparatus may include: a metadata input unit configured to receive text information corresponding to images of the respective products as metadata; It may include a machine learning algorithm performing unit that analyzes the metadata to generate and provide product attribute values corresponding to the respective products.

The machine learning algorithm performing unit may include: a morpheme analysis unit that analyzes the text information input as the metadata and input in the form of a sentence or a combination of a plurality of words in units of morphemes; a product information extraction unit that analyzes the plurality of morphemes and extracts characteristic information of a product corresponding to the product image from the morphemes; and product attribute values for generating product attribute values corresponding to each product by comparing the characteristic information of the product with preset product attribute values stored in the second database and converting the product attribute values to match the characteristic information It may include a generating/providing unit.

The product attribute value generation/provider unit uses a synonym database for vendor names and product names corresponding to the products and abbreviations, synonyms, and utilization databases for the products by category to match the characteristic information to the product attribute values can be converted to

The shopping mall server may include: a product recommendation user interface providing unit configured to provide the product recommendation user interface to a user terminal; a user selection input receiving unit for receiving user selection information input by a user terminal using the user interface; a product attribute value extraction/storage unit for extracting product attribute values corresponding to at least two product images corresponding to the user selection information and accumulating and storing the product attribute values; and a recommendation result providing unit that analyzes common characteristics of the accumulated and stored product attribute values and provides products including the common characteristics as recommended products to the user terminal.

The product recommendation user interface may display any two product images among images of products included in the product category corresponding to the selection information.

The images of the two arbitrary products may be provided in the form of a first product image selection icon and a second product image selection icon included in products included in the selected category.

The product recommendation user interface may further include a non-selection icon in addition to the first product image selection icon and the second product image selection icon.

In order to achieve the above object, a product recommendation method using text analysis according to another embodiment of the present invention includes providing a product recommendation user interface to a user terminal; receiving category information of selected shopping target products as user selection information input by a user terminal using the user interface; displaying a product image corresponding to any two products among the products included in the selected category through the product recommendation user interface, and selecting one of the two product images; extracting product attribute values respectively corresponding to the plurality of selected product images and accumulating and storing the product attribute values; and analyzing common characteristics of the accumulated and stored product attribute values, and providing products including the common characteristics as recommended products to the user terminal.

The product image corresponding to the two arbitrary products is displayed through the product recommendation user interface, and the step of selecting one of the two product images may be repeated a plurality of times.

The method may further include displaying attribute information of a recommended product selected from among the products provided as the recommended product.

The images of the two arbitrary products may be provided in the form of a first product image selection icon and a second product image selection icon included in products included in the selected category.

The product recommendation user interface may further include a non-selection icon in addition to the first product image selection icon and the second product image selection icon.

The product attribute values corresponding to each of the product images may be generated by receiving text information corresponding to the image of each product as metadata and analyzing it.

The analysis of the metadata may include performing a machine learning algorithm.

The performing of the machine learning algorithm may include: analyzing the text information input as the metadata and input in the form of a sentence or a combination of a plurality of words in units of morphemes; analyzing the plurality of morphemes and extracting characteristic information of a product corresponding to the product image from the morphemes; and comparing the characteristic information of the product with product attribute values previously set and stored in the second database and converting the product attribute values to match the characteristic information to generate product attribute values corresponding to each product. can do.

According to this embodiment of the present invention, texts corresponding to images of products are analyzed, features of each product are extracted, and this is stored in a database as an attribute value of each product, and product attribute values for each product stored in the database are utilized. By doing so, it is possible to recommend a product suitable for the user's needs.

In addition, a product recommendation user interface is provided to a user who has accessed the shopping mall system, and through this, arbitrary two products are displayed so that the user can select one of them, and the product attribute values of the products selected by the user are repeated by repeating this process. , and recommending a product including all of the common characteristics of these product attribute values to the user, thereby receiving the user's preference in a fun game manner to the user and recommending a product suitable for the user's needs.

1 is a block diagram illustrating a network environment including a product recommendation shopping mall system according to an embodiment of the present invention.
FIG. 2 is a block diagram showing the configuration of the user terminal shown in FIG. 1;
Fig. 3 is a block diagram schematically showing an embodiment of the internal configuration of the shopping mall server shown in Fig. 1;
4 is a block diagram showing the configuration of a text analysis apparatus according to an embodiment of the present invention.
5 is an exemplary view of a product display screen according to an embodiment of the present invention.
Fig. 6 is a block diagram showing an embodiment of an internal configuration of the processor shown in Fig. 3;
7 is a flowchart illustrating a product recommendation method using text analysis according to an embodiment of the present invention.
8 is an exemplary diagram of a product recommendation user interface provided by an embodiment of the present invention.
9 to 11 are diagrams illustrating a product recommendation process using a product recommendation user interface according to an embodiment of the present invention.

The contents described in the technical field of the background of the present invention are only for helping the understanding of the background of the technical idea of the present invention, and therefore it can be understood as content corresponding to the prior art known to those skilled in the art of the present invention. none.

In the following description, for purposes of explanation, numerous specific details are set forth to aid in understanding various embodiments. It will be evident, however, that various embodiments may be practiced without these specific details or in one or more equivalent manners. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the various embodiments.

Each block in the accompanying block diagram may be executed by computer program instructions (execution engine), which may be loaded into the processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, so that the computer or The instructions, executed by the processor of the other programmable data processing equipment, will create means for performing the functions described in each block of the block diagram.

These computer program instructions may also be stored in a computer-usable or computer-readable memory that may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer-usable or computer-readable memory. It is also possible that the instructions stored in the block diagram produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram.

Further, since the computer program instructions may be mounted on a computer or other programmable data processing equipment, a series of operating steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to create a computer or other program. It is also possible that instructions for performing the possible data processing equipment provide functionality for performing the functions described in each block of the block diagram.

In addition, each block may represent a module, segment, or portion of code comprising one or more executable instructions for executing specified logical functions, and in some alternative embodiments, the functions recited in the blocks or steps are ordered It is also possible to occur outside of

That is, the two illustrated blocks may be substantially simultaneously performed, and also, the blocks may be performed in the reverse order of the corresponding functions, if necessary.

The terminology used herein is for the purpose of describing particular embodiments and not for the purpose of limitation. Throughout the specification, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. Unless otherwise defined, terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings.

1 is a block diagram illustrating a network environment including a product recommendation shopping mall system according to an embodiment of the present invention.

Referring to FIG. 1 , a network environment including a product recommendation shopping mall system according to an embodiment of the present invention includes a plurality of user terminals 110_1, 110_2, ?, 110_n, a network 120, a shopping mall server 130, and text. and an analysis device 140 .

The user terminal 110 includes a mobile terminal that a user can carry and carry. For example, the user terminal 110 may be a smart phone, a tablet, a laptop computer, or the like.

A product recommendation application provided by the shopping mall server 130 may be installed in the user terminals 110 , and through this, the product recommendation shopping mall system, that is, the shopping mall server 130 and the text analysis device ( 140) provides various product recommendation information. The product recommendation information includes an image and product attribute values for a product suitable for a user's preference. If the product recommendation application is not installed in the user terminal, the user may download the application from the shopping mall server 130 and install it in the user's terminal.

The network 120 may be implemented as a wireless communication network or a wired communication network. In this case, the communication method is not limited, and not only a communication method using a communication network (eg, a mobile communication network, a wireless LAN network, a wired Internet, a broadcasting network) that the network 120 may include, but also short-range wireless communication between devices may be included.

The shopping mall server 130 accesses the interface provided by the plurality of user terminals 110 through the network 120 to search for various items, such as clothing items, as a result of which the user wants. Merchandise As an entity providing an online environment for purchasing a product, it may include at least one server device that provides commands, codes, files, contents, services, and the like.

In the case of the embodiment of the present invention, the shopping mall server 130 receives the user's preference in a fun game manner to the user connected to the shopping mall system and recommends a product suitable for the user's needs, text corresponding to the image of each product. analysis, extracting the characteristics of each product, storing it in a database as an attribute value of each product, and recommending a product suitable for the user's preference through this. For this, it operates in connection with the shopping mall server 130 and a product recommendation device 140 to

For example, when the user terminal 110 accesses the shopping mall server 130 and searches for products (eg, clothing products) provided by the shopping mall server, the interface provided by the shopping mall server 130 and/or Information on a product suitable for a user's preference may be provided using a product recommendation function of an application installed in the user terminal.

The text analysis apparatus 140 may perform a role of receiving and analyzing text information corresponding to an image of each product as metadata to generate and provide product attribute values corresponding to the respective products. The product attribute values stored in the database refer to values generated by analyzing texts corresponding to images of each product and extracting features of each product.

For example, the shopping mall system according to the embodiment of the present invention, that is, the shopping mall server 130 and the text analysis apparatus 140 provides a product recommendation user interface to a user who has accessed the shopping mall server 130, and through this displays two products of , so that the user selects one of them, and extracts product attribute values of the products selected by the user by the text analysis device 140 through the accumulated information by repeating this process, and By recommending a product including all of the common characteristics of product attribute values to the user, a product suitable for the user's needs can be recommended by receiving the user's preference in a fun game manner.

In FIG. 1 , the text analysis device 140 is configured separately from the shopping mall server 130 as an example. However, this is an example, and the text analysis device 140 and the shopping mall server 130 are a single unit. It may also be implemented as a device.

The shopping mall server 130 may be implemented in the form of a web server, and the web server is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and the client or other It refers to a computer system that receives a request for performing work from a web server, derives the work result and provides it, and computer software (web server program) installed therefor. However, in addition to the above-described web server program, it can be understood as a broad concept including a series of application programs operating on the web server and, in some cases, various databases built therein. For example, the shopping mall server 130 is a web server that is provided in various ways according to operating systems such as DOS, Windows, Linux, UNIX, and Macintosh in general server hardware. It can be implemented using a program, and representative examples include a website used in a Windows environment, Internet Information Server (IIS), and CERN, NCSA, APPACH, etc. used in a Unix environment.

FIG. 2 is a block diagram illustrating the configuration of the user terminal shown in FIG. 1 .

Referring to FIG. 2 , each user terminal 110 may include a communication module 111 , a memory 112 , a display module 113 , an audio output module 114 , and a control unit 116 .

The communication module 111 may communicate with any internal component or at least one external device through the network 120 . In this case, an external device may include, for example, the shopping mall server 130 and/or the text analysis device 140 shown in FIG. 1 . Here, as wireless Internet technologies, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), Wimax (World Interoperability for Microwave Access: Wimax), HSDPA (High Speed Downlink Packet Access) ), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), etc. In this case, the communication module 111 transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above.

In addition, short-range communication technologies include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and Near Field Communication (NFC). , Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi (Wi-Fi), Wi-Fi Direct (Wi-Fi Direct), etc. may be included.

The memory 112 stores various user interfaces (UIs), graphic user interfaces (GUIs), and the like. In addition, the memory 112 stores data and programs necessary for the user terminal 110 to operate. That is, the memory 112 may store a plurality of application programs (hereinafter, 'applications') driven in the user terminal 110 , data for operation of the user terminal 110 , and commands. That is, at least one or more applications are stored in the memory 112 of the user terminal 110 according to the embodiment of the present invention. At least some of these applications may be downloaded from an external server through wireless communication. An embodiment of the present invention is characterized in that it includes the product recommendation application 112a provided by the shopping mall server 130 shown in FIG. 1 .

In addition, the applications include automatic speech recognition (ASR) applications, map applications, media applications (eg, QuickTime, MobileMusic.app, or MobileVideo.app), social networking applications (eg, Facebook). , Twitter, etc.), Internet browsing applications, and the like. Meanwhile, the applications may be stored in the memory 112 , installed in the user terminal 110 , and driven to perform an operation (or function) of the user terminal 110 by the controller 116 .

In addition, the memory 112 is a flash memory type (Flash Memory Type), a hard disk type (Hard Disk Type), a multimedia card micro type (Multimedia Card Micro Type), a card type memory (eg, SD or XD memory, etc.) ), magnetic memory, magnetic disk, optical disk, random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), PROM ( Programmable Read-Only Memory) may include at least one storage medium.

The display module 113 displays various contents such as various menu screens using a user interface and/or a graphic user interface stored in the memory 112 under the control of the control unit 116, and is controlled by the control unit 116. An execution result screen of the travel information application 112a executed by the user may be displayed.

For example, when the product recommendation application 112a is executed, the display module 113 may display an interface provided by the product recommendation application 112a on the screen, and the user may select a preferred product provided through the interface. may be sequentially selected a plurality of times to provide information on common characteristics of the user's own preferred products.

Here, the content displayed on the display module 113 may include various text or image data (including various information data), an icon, a menu screen indicating a list menu, and the like. The display module 113 is a liquid crystal display (LCD), an organic light-emitting diode (OLED), a flexible display, a three-dimensional display (3D display), an electronic ink display (e-) ink display), LED (Light Emitting Diode), and the like.

The audio output module 114 may output voice information included in a predetermined signal-processed signal under the control of the controller 116 . Here, the audio output module 114 may include a receiver, a speaker, and the like.

3 is a block diagram schematically illustrating an example of an internal configuration of the shopping mall server shown in FIG. 1 .

Referring to FIG. 3 , the shopping mall server 130 includes a memory 132 , a database 133 , a processor 134 , a communication module 136 , and an input/output interface 138 .

The memory 132 is a computer-readable recording medium and may include a non-volatile mass storage device such as a RAM, a ROM, and a disk drive. Also, an operating system and at least one program code may be stored in the memory 132 . These software components may be loaded from a computer-readable recording medium separate from the memory 132 using a drive mechanism. The separate computer-readable recording medium may include a recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In addition, the software components may be loaded into the memory 132 through the communication module 136 .

The database 133 may store and maintain information transmitted and received from the user terminals 110 connected to the shopping mall server 130 according to an embodiment of the present invention. Also, the database 133 may store image information on products owned by the shopping mall server 130 and attribute values of products corresponding to the images for each product. For example, as shown in FIG. 4 , the database 130 includes a first database 133a in which product images for each product are stored and a second database 133b in which attribute values of products corresponding to each product image are stored. ) may be included.

The processor 134 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. The instructions may be provided to the processor 134 by the memory 132 or the communication module 136 . As an example, the processor 134 may be configured to execute a received instruction according to a program code stored in a recording device such as the memory 132 . That is, the processor 134 may include a program module that is implemented by software such as C, C++, Java, Visual Basic, Visual C, and the like and performs various functions.

The shopping mall server 130 searches for various products (eg, clothing products) by accessing an interface provided by the shopping mall server 130 by a plurality of user terminals 110 through the network 120 , and as a result, It serves to provide an online environment where users can purchase desired products.

The shopping mall server 130 according to an embodiment of the present invention provides an interface and/or application capable of recommending a product suitable for the user's needs by receiving the user's preference in a fun game manner to the user terminals 110 and In addition, it is characterized in that the information on all products stored in the database of the shopping mall server is classified and stored.

More specifically, as described above, data corresponding to the image of each product is stored in the first database 133a, texts corresponding to the image of each product are analyzed, and features of each product are extracted and stored in the first database 133a. The attribute value of each product is stored in the second database 133b, and through this, an operation of recommending a product suitable for the user's preference can be performed.

For example, when the user terminal 110 accesses the shopping mall server 130 and searches for products (eg, clothing products) provided by the shopping mall server, the interface provided by the shopping mall server 130 and/or Information on a product suitable for a user's preference may be provided based on a result value of the text analysis apparatus 140 using a product recommendation function of an application installed in the user terminal.

Basic operations of the shopping mall server 130 and the text analysis apparatus 140 according to an embodiment of the present invention will be described in more detail below with reference to FIGS. 4 and 5 .

The communication module 136 may provide a function for the user terminals 110 and the shopping mall server 130 to communicate with each other through the network 120 . For example, a control signal, command, content, file, etc. provided under the control of the processor 134 of the shopping mall server 130 is transmitted to the user terminals 110 through the network 120 through the communication module 136 . can be

The input/output interface 138 may serve to provide an interface between an input device implemented as a keyboard or mouse and an output device such as a display.

4 is a block diagram illustrating the configuration of a text analysis apparatus according to an embodiment of the present invention, and FIG. 5 is an exemplary diagram of a product display screen according to an embodiment of the present invention.

4 and 5 , the text analysis apparatus 140 according to an embodiment of the present invention receives text information corresponding to an image of each product as metadata, analyzes it, and a product attribute value corresponding to each product. As performing an operation of generating and providing , the text analysis apparatus 140 may include a metadata input unit 142 and a machine learning algorithm performing unit 150, and the machine learning algorithm performing unit 150 may include It may include a morpheme analysis unit 152 , a product information extraction unit 154 , and a product attribute value generation/providing unit 156 . Also, the text analysis apparatus 140 may interwork with the database 133 of the shopping mall server 130 .

The database 133 may store image information on products owned by the shopping mall server 130 and attribute values of products corresponding to the images for each product. For example, as shown in FIG. 4 , the database 130 includes a first database 133a in which product images for each product are stored and a second database 133b in which attribute values of products corresponding to each product image are stored. ) may be included.

In addition, the text analysis apparatus 140 shown in FIG. 4 may be implemented as a processor. In this case, the place metadata input unit 142 and the machine learning algorithm performing unit 150 which are components of the text analysis apparatus 140 . and each of the morpheme analysis unit 152 , the product information extraction unit 154 , and the product attribute value generation/providing unit 156 , which are components of the machine learning algorithm execution unit 150 , are different from each other performed by the processor. It can be understood as expressing the functions separately. In this case, the processor may be implemented as a separate processor distinct from the processor 134 included in the shopping mall server 130 as described above, but the embodiment of the present invention is not limited thereto. That is, each component of the text analysis apparatus 140 may be functional blocks implemented in the processor 134 of the shopping mall server 130 .

The metadata input unit 142 may receive text information corresponding to an image of a product provided by the shopping mall server 130 as metadata.

5 is an exemplary view of a product display screen 500 displayed on an interface provided by the shopping mall server 130, wherein the product display screen 500 includes a representative image 510 of a product and the product image 510 may include text information 520 corresponding to .

Referring to FIG. 5 , the product image 510 may represent, for example, clothing of a specific design, and detailed information about the product image 510 is text information displayed on the side of the product image 510 . (520).

5, "short sleeve floral print dress plus", "95% rayon, 5% spandex", "made in USA", "$14.50", etc. described as the text information 520 are various features of the product. can be used as metadata representing For example, through the text information, the classification (dress / short sleeve), design (floral print), size (plus), material (95% rayon, 5% spandex), country of manufacture (made in USA), and price ( $14.50), etc., can be used as metadata including information.

Accordingly, the metadata input unit 142 may receive the text information 520 corresponding to the product image 510 as metadata, and the text information 520 as the input metadata performs a machine learning algorithm. It is transmitted to the unit 150, and the machine learning algorithm performing unit 150 may analyze the metadata to generate and provide product attribute values corresponding to the respective products. The machine learning algorithm performing unit 150 may include a morpheme analysis unit 152 , a product information extraction unit 154 , and a product attribute value generation/providing unit 156 .

The morpheme analyzer 152 analyzes texts input in the form of a sentence or a combination of various words as the text information 520 in units of morphemes.

As an example, when the input text is in Korean, generally, 'morpheme candidate analysis' using tabular parsing or 'part of speech tagging' based on machine learning may be performed. . In addition, a machine learning method such as Hidden Markov Model (HMM) or Conditional Random Field (CRF) may be used for the morpheme analysis, and a method to which deep learning is applied may also be used.

According to the embodiment of the present invention, the metadata input to the morpheme analysis unit 152, that is, text information corresponding to the image of each product may be divided into predetermined morphemes and transmitted to the product information extraction unit 154. have.

The product information extraction unit 154 may analyze the received morphemes and extract characteristic information of the product corresponding to the product image 510 from the morphemes.

As an example, the process of extracting feature information about the product may be implemented by constructing an ontology for the product (eg, clothing product) in advance and using it to analyze the text information divided into the morphemes. have. That is, by analyzing the text information, features for a product category (or sub-category) can be extracted.

As an example of the ontology, when the product is limited to women's clothing, the category of the product may include a dress, tops, etc., and corresponding to the dress category, a pattern, a style It may include subcategories of (style) and length (length). For example, the pattern is "floral print, stripe print, ?", and the style is "trapeze, ruffle, ?". The length may include "maxi, calf, ?".

In addition, corresponding to the tops category, this may also include sub-categories of a pattern, a style, and a length. For example, the pattern is "stripe, graphic, ?", and the style is "tunic, tank top, ?". The length may include "hip, cropped, ?".

According to an embodiment of the present invention, the characteristic information of the product extracted by the product information extracting unit 154 may be transmitted to the product attribute value generating/providing unit 156 .

The product attribute value generating/providing unit 156 compares the received characteristic information of the product with preset and stored product attribute values and converts them into product attribute values matching the characteristic information, thereby product attributes corresponding to each product. An operation that generates values can be performed.

As an example, the process of converting the characteristic information into product attribute values to generate a product attribute value corresponding to the product builds a synonym DB for a vendor name, a product name, etc. used in the shopping mall server 130 , and the product It is possible to construct an abbreviation, synonym, and conjugation type (single or plural type) DB for categories (or sub-categories) for the items and convert them into product attribute values matching the characteristic information by using the DB.

In addition, the product attribute value information for each product generated through this is provided from the product attribute value generating/providing unit 156 to the shopping mall server 130, which is provided to the database 133 of the shopping mall server 130, more specifically, the Attribute values of products corresponding to images for each product may be stored in the stored second database 133b.

As described above, through the configurations of the shopping mall system, that is, the shopping mall server 130 and the text analysis device 140 according to the embodiment of the present invention, a product suitable for the preference of the user who has accessed the shopping mall server 130 can be recommended.

The shopping mall system according to an embodiment of the present invention provides a product recommendation user interface, displays any two products through this, so that the user selects one of them, and repeats this process to obtain the above information through the accumulated information. By extracting the product attribute values of the products selected by the user by the text analysis device 140 and recommending a product including all common features of these product attribute values to the user, the user's preference is input in a fun game manner. It is possible to recommend a product suitable for the user's needs by receiving the product. Hereinafter, a product recommendation method using text analysis according to an embodiment of the present invention will be described in more detail with reference to FIGS. 6 to 11 .

6 is a block diagram illustrating an embodiment of the internal configuration of the processor shown in FIG. 3 , and FIG. 7 is a flowchart illustrating a product recommendation method using text analysis according to an embodiment of the present invention.

6 and 7 , the processor 134 of the shopping mall server 130 includes a product recommendation user interface providing unit 610 , a user selection input receiving unit 620 , a product attribute value extraction/storing unit 630 , and a recommendation. A result providing unit 640 may be included. In addition, the processor 134 identifies the terminal 110 of the user who is a registered member of the site provided by the shopping mall server 130 , and interworks with the database 133 for storing information provided to the user terminal 110 . The processor 134 may control the shopping mall server 130 to perform the steps ST 700 to ST 750 included in the product recommendation method using text analysis shown in FIG. 7 .

Here, the processor 134 may be implemented to execute an instruction according to an operating system code and at least one program code included in the memory 132 . At this time, the components in the processor 134 , that is, the product recommendation user interface providing unit 610 , the user selection input receiving unit 620 , the product attribute value extraction/storing unit 630 , and the recommendation result providing unit 640 are It may be understood that different functions performed by the processor 134 according to a control command provided by the program code stored in the shopping mall server 130 are distinguished and expressed.

The product recommendation user interface providing unit 320 performs an operation of providing the product recommendation user interface according to the embodiment of the present invention to the user terminal 110 (ST 700). As an example, FIG. 8 is an exemplary diagram of a product recommendation user interface provided by an embodiment of the present invention.

Referring to FIG. 8 , the shopping mall server 130 may target fashion/clothing products as an example. 8 shows a part of the user interface 800 displayed on the user terminal 110 when the user terminal 110 accesses the shopping mall server 130, and the user selects a category of the menu bar located on the left side of the screen. By selecting, the user can search for preferred clothing products.

The user selection input receiving unit 620 performs an operation of receiving user selection information input by the user terminal 110 using the user interface 800 . That is, a user can directly select a category of a shopping target product by using the user interface 800 displayed on the user terminal 110 (ST 710).

As an example, the example shown in FIG. 8 shows a case where the category of the product the user wants to purchase is "dress", and in "pattern" among the subcategories, "floral print" is selected. Various products may be displayed on the user terminal 110 through the user interface 800 .

A general shopping mall server displays all products corresponding to the category selected by the user as shown in FIG. 8 so that the user can directly purchase the desired product, but this gives the user a one-sided choice, and the shopping mall server manually There is a disadvantage in that the role is limited as it only provides results according to the user's selection.

In contrast, in the product recommendation method using text analysis according to an embodiment of the present invention, any two products are displayed through the provided product recommendation user interface 800 so that the user selects one of them, and this process is performed Extracting product attribute values of products selected by the user by the text analysis device 140 through the information accumulated by repetition, and recommending to the user a product including all common characteristics of these product attribute values Through this, it is possible to recommend a product suitable for the user's needs by inputting the user's preference in a fun game method.

9 to 11 are diagrams illustrating a product recommendation process using a product recommendation user interface according to an embodiment of the present invention.

As described above, when a user directly selects a category of a shopping target product using the user interface 800 displayed on the user terminal 110, a product recommendation user interface 900 as shown in FIG. 9 may be displayed. have. More specifically, any two product images among images of products included in the category selected by the user may be displayed (ST 720).

An example of the user interface 900 of FIG. 9 corresponds to a case in which the user, which is the embodiment shown in FIG. 8, selects "floral print" of "pattern" from among the "dress" product category and sub-categories. Products The first product image selection icon 910 and the second product image selection icon 920 are displayed as images of two arbitrary products. Accordingly, the user may click one of the first product image selection icon 910 and the second product image selection icon 920 to select a product that the user prefers.

In addition, according to an embodiment of the present invention, a non-selection icon 930 may be additionally displayed in case the user does not want to select both the first and second product images 910 and 920 .

When the user selects a preferred product by clicking one of the first product image selection icon 910 and the second product image selection icon 920 or clicks the non-selection icon 930, the user interface ( 900) may display and provide an image of another product to the user in the same manner, and this process may be repeated a plurality of times. Therefore, it is possible to grasp the user's preference through repetition of this process.

At this time, in the case of two product images sequentially displayed through the user interface 900 of FIG. 9 , as described above with reference to FIGS. 4 and 5 , the text analysis device 140 generates the shopping mall server 130 . ) of the second database 133b, there are product attribute values corresponding to the stored images for each product.

Therefore, when the user selects a specific product image through the step (ST 720) of displaying any two product images among the images of products included in the category selected by the user, the product attribute value extraction/storage unit ( The 630 may extract product attribute values corresponding to the product image selected by the user and accumulate and store them (ST 730).

The recommendation result providing unit 640 may analyze common characteristics of stored product attribute values accumulated through the above process, and may perform an operation of providing products including these common characteristics as recommended products (ST 740). .

Referring to FIG. 10 , as an example of the user interface 1000 in which the recommended products are displayed, FIG. 10 indicates that the user has previously made three selections through the user interface 900 of FIG. It shows an example of recommending a plurality of products including common features with product attribute values derived by .

More specifically, product image selection icons 1010 , 1020 , 1030 directly selected by the user in the previous step are displayed at the bottom of the user interface 1000 , and the derived product attribute values are displayed at the top of the user interface 1000 . A plurality of recommended product image selection icons 1040 including common features may be displayed.

Next, when the user selects one of the plurality of recommended product image selection icons 1040, as shown in FIG. 11 , attribute information of the product selected by the user from among the recommended products may be displayed (ST 750). .

Referring to FIG. 11 , as an example of a display screen of a recommended product selected by a user, in FIG. 11 , an icon 1110 for selecting a recommended product image selected by the user and text information 1120 corresponding to the product image are displayed. The text information 1120 may include product attribute values for the corresponding product as described in detail above.

The product recommendation method using text analysis according to an embodiment of the present invention does not provide only a result according to the user's selection passively, but displays two arbitrary products so that the user selects one of them, such a process by extracting product attribute values of products selected by the user by the text analysis device 140 through the information accumulated by repeating , and recommending a product including all common features of these product attribute values to the user. It is possible to recommend the optimal product reflecting the user's preference while inducing interest.

As described above, the present invention has been described with specific matters such as specific components and limited embodiments and drawings, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , various modifications and variations are possible from these descriptions by those of ordinary skill in the art to which the present invention pertains.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and not only the claims to be described later, but also all those with equivalent or equivalent modifications to the claims will be said to belong to the scope of the spirit of the present invention. .

Claims (16)

a shopping mall server connected to a plurality of user terminals and providing a product recommendation user interface to the user terminals;
A text analysis apparatus that interworks with the shopping mall server to receive text information corresponding to each image of shopping target products provided by the shopping mall server as metadata, analyze it, and generate and provide product attribute values corresponding to the respective products includes,
The shopping mall server,
Products using text analysis including a first database in which product images for shopping target products provided by the shopping mall server are stored and a second database in which attribute values of products corresponding to images for each shopping target product provided by the shopping mall server are stored Recommended shopping mall system. According to claim 1,
The text analysis device,
a metadata input unit for receiving text information corresponding to the images of the respective products as metadata;
and a machine learning algorithm execution unit that analyzes the metadata to generate and provide product attribute values corresponding to the respective products. 3. The method of claim 2,
The machine learning algorithm performing unit,
a morpheme analyzer that analyzes the text information input as the metadata and input in the form of a sentence or a combination of a plurality of words in units of morphemes;
a product information extraction unit that analyzes the plurality of morphemes and extracts characteristic information of a product corresponding to the product image from the morphemes; and
Product attribute value generation for generating product attribute values corresponding to each product by comparing the characteristic information of the product with preset product attribute values stored in the second database and converting the product attribute values matching the characteristic information Product recommendation shopping mall system using text analysis including /provider. 4. The method of claim 3,
The product attribute value generation/provider unit uses a synonym database for vendor names and product names corresponding to the products and abbreviations, synonyms, and utilization databases for the products by category to match the characteristic information to the product attribute values A product recommendation shopping mall system using text analysis that transforms into According to claim 1,
The shopping mall server,
a product recommendation user interface providing unit providing the product recommendation user interface to a user terminal;
a user selection input receiving unit for receiving user selection information input by a user terminal using the user interface;
a product attribute value extraction/storage unit for extracting product attribute values corresponding to at least two product images corresponding to the user selection information and accumulating and storing the product attribute values; and
and a recommendation result providing unit that analyzes common characteristics of the accumulated and stored product attribute values and provides products including the common characteristics as recommended products to a user terminal. 6. The method of claim 5,
The product recommendation user interface is a product recommendation shopping mall system using text analysis for displaying arbitrary two product images among images of products included in the product category corresponding to the selection information. 7. The method of claim 6,
The product recommendation shopping mall system using text analysis, wherein the images of the two arbitrary products are provided in the form of a first product image selection icon and a second product image selection icon included in products included in the selected category. 8. The method of claim 7,
The product recommendation user interface further includes a non-selection icon in addition to the first product image selection icon and the second product image selection icon. providing a product recommendation user interface to a user terminal by a shopping mall server;
receiving category information of selected shopping target products as user selection information input by a user terminal using the user interface;
displaying a product image corresponding to any two products among the products included in the selected category through the product recommendation user interface, and selecting one of the two product images;
extracting product attribute values respectively corresponding to the plurality of selected product images and accumulating and storing the product attribute values; and
analyzing common characteristics of the accumulated stored product attribute values, and providing products including the common characteristics as recommended products to a user terminal;
The shopping mall server,
Products using text analysis including a first database in which product images for shopping target products provided by the shopping mall server are stored and a second database in which attribute values of products corresponding to images for each shopping target product provided by the shopping mall server are stored Recommended way. 10. The method of claim 9,
A product image corresponding to the two arbitrary products is displayed through the product recommendation user interface, and the step of selecting one of the two product images is a product recommendation method using text analysis that is repeated multiple times. 10. The method of claim 9,
Product recommendation method using text analysis further comprising the step of displaying attribute information of a recommended product selected from among the products provided as the recommended product. 10. The method of claim 9,
The product recommendation method using text analysis in which the images of the two arbitrary products are provided in the form of a first product image selection icon and a second product image selection icon included in products included in the selected category. 13. The method of claim 12,
The product recommendation user interface further includes a non-selection icon in addition to the first product image selection icon and the second product image selection icon. 10. The method of claim 9,
Product attribute values corresponding to each of the product images are generated by receiving text information corresponding to the image of each product as metadata and analyzing it. 15. The method of claim 14,
The analysis of the metadata is a product recommendation method using text analysis, including the step of performing a machine learning algorithm. 16. The method of claim 15,
The step of performing the machine learning algorithm is,
analyzing the text information input as the metadata and input in the form of a sentence or a combination of a plurality of words in units of morphemes;
analyzing the plurality of morphemes and extracting characteristic information of a product corresponding to the product image from the morphemes; and
Comprising the step of comparing the characteristic information of the product with product attribute values previously set and stored in the second database and converting the product attribute values matching the characteristic information to generate product attribute values corresponding to each product Product recommendation method using text analysis.

Images