KR102622779B1 - Method, system and non-transitory computer-readable recording medium for tagging attribute-related keywords to product images - Google Patents

Abstract

According to one aspect of the present invention, there is a method of assigning attribute-related keywords to a product image, comprising the steps of obtaining attribute information about a product included in a product image, an attribute keyword and configuring the attribute keyword or derived from the attribute keyword. A method is provided including generating a target attribute keyword associated with attribute information about the product with reference to the association relationship between unit keywords, and assigning the target attribute keyword to the product image.

Description

Method for assigning attribute-related keywords to product images, system, and non-transitory computer-readable recording medium

The present invention relates to a method, system, and non-transitory computer-readable recording medium for assigning attribute-related keywords to product images.

Various research is being conducted to ensure that products desired by buyers are easily exposed and searched in online shopping malls. To achieve this, a technology is needed that allows the product or content to be easily searched by users by assigning timely keywords or identifiers to the product or content (images, etc.) containing the product.

As an example of the prior art in this regard, the technology disclosed in Korean Patent Publication No. 889230 can be cited as an example. According to this, in the shopping mall product search service method using a wired network or a wireless network, a) any client When connecting to a wired network or a wireless network and entering a random product search keyword, providing the client with product search sorting results corresponding to the input product search keyword; b) a product selected by the client for the product search results; a step of accumulating history information for a preset period of time, c) deriving a score for a product by assigning a weight to the accumulated history information according to the number of times a searched product is selected for each search word, and d) deriving the score. According to the results, sorting the product search list by search term according to the score of the product; e) when the product search keyword input by the client matches the previously stored product-specific information, a separate search for the matching product is performed; deriving the score of the product by assigning weights, f) summing the scores derived from step e) and step c), and g) creating a product search list by search word according to the sum result of the product. A shopping mall product search service method including the step of sorting according to the total score is provided.

However, according to the technologies introduced so far, including the above-described prior art, information about the product, such as the name, keyword, and tag of the product being sold, is entered in advance by the product seller, and the search keywords entered by the buyer are matched with each other. In some cases, because the search results are only provided to buyers, if information about the product, such as name, keyword, tag, etc., is not properly entered, or vocabulary that is commonly used or popular among buyers is not properly prepared, There was a problem that it was difficult for the product to be provided to buyers as a search result.

In particular, in the case of fashion products such as clothing, shoes, etc., it is difficult to specify the name and the trend has the characteristic of changing faster than other products, so the seller must provide information about the product one by one according to the fashion (i.e. trend). For example, changing names (names, tags, etc.) manually was not an easy task. As an alternative, technology regarding a keyword decision model that automatically (or adaptively) determines keywords such as names and tags to be given to products has been introduced, but the keyword decision model must be continuously updated according to rapidly changing trends or characteristics. This is causing inconvenience and waste of resources.

Accordingly, the present inventor(s) propose a technology that can generate attribute keywords to be assigned to product images by referring to the association relationships extracted from attribute keywords obtained in advance.

The purpose of the present invention is to solve all the problems of the prior art described above.

In addition, the present invention obtains attribute information about the product included in the product image, refers to the association relationship between the attribute keyword and unit keywords that constitute the attribute keyword or are derived from the attribute keyword, and provides attribute information about the product. By creating a target attribute keyword related to and assigning the above target attribute keyword to the product image, the attribute will be given to the product image based on attributes that are relatively less sensitive to trends and can be commonly applied to various types of products. Another purpose is to enable keywords to be determined in a timely manner.

In addition, another purpose of the present invention is to use attribute keywords assigned to a product image to set filtering standards to be applied to the product image or to provide other product images related to the product image.

A representative configuration of the present invention to achieve the above object is as follows.

According to one aspect of the present invention, there is a method of assigning attribute-related keywords to a product image, comprising the steps of obtaining attribute information about a product included in a product image, an attribute keyword and configuring the attribute keyword or derived from the attribute keyword. A method is provided that includes the steps of generating a target attribute keyword associated with attribute information about the product with reference to the association relationship between unit keywords, and assigning the target attribute keyword to the product image.

According to another aspect of the present invention, there is a system for assigning attribute-related keywords to a product image, comprising: an information acquisition unit that acquires attribute information about a product included in a product image; and an attribute keyword and configuring the attribute keyword or the attribute keyword. A system is provided that includes a keyword management unit that generates a target attribute keyword associated with attribute information about the product, and assigns the target attribute keyword to the product image by referring to the association relationship between unit keywords derived from.

In addition, another method for implementing the present invention, another system, and a non-transitory computer-readable recording medium for recording a computer program for executing the method are further provided.

According to the present invention, it is possible to timely determine attribute keywords to be assigned to product images based on attributes that are relatively less sensitive to trends and can be commonly applied to various types of products.

In addition, according to the present invention, it is possible to set filtering standards to be applied to the product image by utilizing attribute keywords assigned to the product image, or to provide other product images related to the product image.

Additionally, according to the present invention, it is possible to save resources consumed to determine keywords to be assigned to product images in accordance with trends.

Figure 1 is a diagram showing a schematic configuration of an entire system for assigning attribute-related keywords to product images according to an embodiment of the present invention.
Figure 2 is a diagram illustrating in detail the internal configuration of a service provision system according to an embodiment of the present invention.
Figure 3 is a diagram illustrating a case in which attribute information about a product included in a product image is obtained according to an embodiment of the present invention.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented with changes from one embodiment to another without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description described below is not to be taken in a limiting sense, and the scope of the present invention should be taken to encompass the scope claimed by the claims and all equivalents thereof. Like reference numbers in the drawings indicate identical or similar elements throughout various aspects.

Hereinafter, several preferred embodiments of the present invention will be described in detail with reference to the attached drawings in order to enable those skilled in the art to easily practice the present invention.

Configuration of the entire system

Figure 1 is a diagram showing a schematic configuration of an entire system for assigning attribute-related keywords to product images according to an embodiment of the present invention.

As shown in FIG. 1, the entire system according to an embodiment of the present invention may include a communication network 100, a service provision system 200, and a device 300.

First, the communication network 100 according to an embodiment of the present invention can be configured regardless of communication mode, such as wired communication or wireless communication, and can be used as a local area network (LAN) or a metropolitan area network (MAN). ), and a wide area network (WAN). Preferably, the communication network 100 referred to in this specification may be the known Internet or World Wide Web (WWW). However, the communication network 100 is not necessarily limited thereto and may include at least a portion of a known wired or wireless data communication network, a known telephone network, or a known wired or wireless television communication network.

For example, the communication network 100 is a wireless data communication network, including Wi-Fi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, and Bluetooth communication (e.g., low-power Bluetooth (e.g., low-power Bluetooth). It may implement at least part of a conventional communication method such as BLE (Bluetooth Low Energy) communication, infrared communication, ultrasonic communication, etc.

Next, the service provision system 200 according to an embodiment of the present invention can perform communication with the device 300, which will be described later, through the communication network 100, and obtain attribute information about the product included in the product image. And, by referring to the association relationship between the attribute keyword and the unit keywords that constitute the attribute keyword or derived from the attribute keyword, a target attribute keyword associated with the attribute information about the product is generated, and the above target attribute keyword is used as the corresponding attribute keyword. It can perform the function of adding to the product image.

The configuration and function of the service provision system 200 according to the present invention will be discussed in detail through the detailed description below. Meanwhile, although the service provision system 200 has been described as above, this description is illustrative, and at least some of the functions or components required for the service provision system 200 may be used as a device 300 or It will be apparent to those skilled in the art that it may be realized within an external system (not shown) or included in the device 300 or an external system (not shown).

Next, according to an embodiment of the present invention, the device 300 is a digital device including a function that allows communication after accessing the service provision system 200 through the communication network 100, such as a smartphone or tablet PC. Any portable digital device equipped with a memory means and equipped with a microprocessor and equipped with computing power, such as the like, can be adopted as the device 300 according to the present invention.

Meanwhile, according to an embodiment of the present invention, the device 300 may include an application to support a function according to the present invention in which information about a product is determined. Such applications may be downloaded from the service provision system 200 or an external application distribution server (not shown).

Configuration of service provision system

Below, we will look at the internal structure of the service provision system 200 and the function of each component, which performs important functions for implementing the present invention.

FIG. 2 is a diagram illustrating in detail the internal configuration of the service provision system 200 according to an embodiment of the present invention.

The service provision system 200 according to an embodiment of the present invention may be a digital device equipped with a memory means and a microprocessor to have computing capabilities. This service providing system 200 may be a server system. As shown in FIG. 2, the service provision system 200 may be configured to include an information acquisition unit 210, a keyword management unit 220, a communication unit 230, and a control unit 240. According to one embodiment of the present invention, at least some of the information acquisition unit 210, keyword management unit 220, communication unit 230, and control unit 240 may be program modules that communicate with an external system. These program modules may be included in the service provision system 200 in the form of an operating system, application program module, or other program module, and may be physically stored in various known storage devices. Additionally, these program modules may be stored in a remote memory device capable of communicating with the service provision system 200. Meanwhile, such program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

First, according to an embodiment of the present invention, the information acquisition unit 210 may perform a function of acquiring attribute information about a product included in a product image.

Here, according to an embodiment of the present invention, attribute information about a product may mean information about the product that can be determined for each of the variously defined attribute classifications.

Figure 3 is a diagram illustrating a case in which attribute information about a product included in a product image is obtained according to an embodiment of the present invention.

Referring to Figure 3, 13 attribute classifications for fashion products (i.e., category, item, body length, arm length, neckline, shape) , it can be assumed that texture, print, style, detail, and color are defined, and in this case, the above 13 attributes from the product image 310 For each category: "Dress", "Slip dress", "Knee length", "Sleeveless", "V-neck", "A-line", "Silk", "Tie-dye", "Casual", "None", and "Orange" , White” attribute information 320 may be determined.

Specifically, according to one embodiment of the present invention, attribute information about a product included in a product image may be recognized by analyzing the product image using a learning-based model. As an example of a technology for extracting and recognizing attribute information about products included in product images using a learning-based model, the technology described in Korean Patent Publication No. 1801846, filed and announced by the applicant of this application, can be assumed. You can. The above publications are to be understood as incorporated herein in their entirety. However, it should be noted that the technology for extracting or recognizing attribute information about a product according to the present invention is not necessarily limited to the above-mentioned technology, and may be changed to any extent within the scope of achieving the purpose of the present invention. .

Meanwhile, according to another embodiment of the present invention, the attribute information about the product included in the product image is attribute information arbitrarily input by the manager (fashion industry worker, expert, etc.) of the service provision system 200 according to the present invention. It may be possible.

Next, according to an embodiment of the present invention, the keyword management unit 220 refers to the association relationship between an attribute keyword and a unit keyword that constitutes the attribute keyword or is derived from the attribute keyword to associate attribute information about the product. The function of creating target attribute keywords can be performed.

Here, according to an embodiment of the present invention, attribute keywords may be obtained and stored in advance from external sources such as social network services (SNS), online communities, online shopping malls, and online portals. Specifically, according to one embodiment of the present invention, the attribute keywords obtained in advance in the present invention are the attributes of products (for example, fashion products) by analyzing numerous keywords obtained from external sources using a learning-based model. It may be a keyword obtained by determining keywords that include related keywords or are determined to be composed of such keywords.

However, it should be noted that attribute keywords according to the present invention are not necessarily obtained from external sources or determined by a learning-based model, and may be arbitrarily generated by the administrator or user of the service providing system 200 according to the present invention.

Specifically, according to one embodiment of the present invention, the attribute keywords obtained and stored in advance as described above may be divided into at least one unit keyword constituting the corresponding attribute keyword, and the unit keywords thus classified can be classified into attribute keywords related to the product. It may be a keyword related to . Additionally, according to an embodiment of the present invention, an attribute keyword and at least one unit keyword constituting the attribute keyword may be mapped to each other, and two or more unit keywords constituting the attribute keyword may also be mapped to each other. , Based on this mapping, the association relationship between attribute keywords and unit keywords or the association relationship between two or more unit keywords may be dynamically determined.

For example, when an attribute keyword called “checked slacks” is obtained, this attribute keyword is divided into a unit keyword called “check”, which corresponds to the attribute category “print”, and a unit keyword “slacks”, which corresponds to the attribute category “item”. It can be. And, accordingly, the attribute keyword “check slacks” and the unit keywords “check” and “slacks” can be mapped to each other, and the unit keywords “check” and “slacks” can be mapped to each other.

For another example, when an attribute keyword called "oversized graphic t-shirt" is obtained, this attribute keyword is a unit keyword called "oversize" corresponding to the attribute category called fit, and a unit keyword called "graphic" corresponding to the attribute category called print. It can be divided into a unit keyword called “T-shirt” that corresponds to the attribute category called unit keyword and item. Accordingly, the attribute keyword "oversized graphic T-shirt" and the unit keywords "oversize", "graphic", and "t-shirt" can be mapped to each other, and the units "oversize", "graphic", and "t-shirt" Keywords can be mapped to each other.

For another example, when an attribute keyword called “round neck t-shirt” is obtained, this attribute keyword is a unit keyword called “round neck” that corresponds to the attribute category called neckline, and “t-shirt” which corresponds to the attribute category called item. It can be divided into unit keywords. Accordingly, the attribute keyword “round neck t-shirt” and the unit keywords “round neck” and “t-shirt” may be mapped to each other, and the unit keywords “round neck” and “t-shirt” may be mapped to each other.

Meanwhile, according to an embodiment of the present invention, even if it does not constitute an attribute keyword, at least one unit keyword that has a relationship with the attribute keyword itself or a unit keyword that constitutes the attribute keyword can be derived. The unit keyword derived in this way may be a keyword related to the attribute classification of the product. In addition, according to an embodiment of the present invention, an attribute keyword and at least one unit keyword derived from the attribute keyword may be mapped to each other, and two or more unit keywords derived as above may be mapped to each other, Based on this mapping, an association relationship between an attribute keyword and a unit keyword or an association relationship between two or more unit keywords may be dynamically determined.

For example, when an attribute keyword called "neutral color jacket" is obtained, various unit keywords such as "brown", "beige", and "grey" are added from the unit keyword "neutral color" that constitutes this attribute keyword. can be derived. Accordingly, the attribute keyword “neutral color jacket” and the unit keywords “neutral color”, “brown”, “beige”, and “grey” can be mapped to each other, and “neutral color”, “brown”, and “beige”. The unit keywords "and "gray" may be mapped to each other.

For another example, when an attribute keyword called “loose fit pants” is obtained, various unit keywords such as “loose”, “wide”, “baggy”, etc. are further derived from the unit keyword “loose” that constitutes this attribute keyword. It can be. Accordingly, the attribute keyword "loose fit pants" and the unit keywords "loose", "wide", and "baggy" may be mapped to each other, and the unit keywords "loose", "wide", and "baggy" may be mapped to each other. It can be.

Continuing, according to an embodiment of the present invention, the keyword management unit 220 refers to the relationship between the attribute keyword determined as above and the unit keywords that constitute the attribute keyword or are derived from the attribute keyword, and determines the product The function of generating target attribute keywords related to attribute information about products included in the image can be performed. Additionally, according to an embodiment of the present invention, the keyword management unit 220 may perform the function of generating the above target attribute keyword by further referring to the association relationship between two or more unit keywords.

Specifically, the keyword management unit 220 according to an embodiment of the present invention determines the target attribute to be assigned to the product image by combining at least one unit keyword associated with at least one attribute information about the product included in the product image. You can create keywords.

In the example shown in FIG. 3, “dress”, “slip dress”, “knee length”, “sleeveless”, “V-neck”, and “A-line” are determined for each of the 13 attribute categories from the product image 310. , “Silk,” “Tie Dye,” “Casual,” “None,” and “Orange, White” can be obtained. Furthermore, as the attribute keyword “V-neck slip dress” is obtained in advance, it can be assumed that there is a mapping between the attribute keyword “V-neck slip dress”, the unit keyword “V-neck”, and the unit keyword “slip dress”. there is.

In this case, the keyword management unit 220 according to an embodiment of the present invention provides attribute information 320 about the product included in the product image 310 among the unit keywords that are determined to have a correlation based on the above mapping. A target attribute keyword called "V-neck slip dress" can be created by combining the unit keyword "slip dress" and the unit keyword "V-neck" that are judged to be related to.

In the above embodiment, when generating a target attribute keyword, when the attribute information 320 about the product included in the product image 310 exactly matches (or corresponds to) the unit keywords constituting the previously obtained attribute keyword Although this has been mainly described, it should be noted that the embodiments of the present invention are not necessarily limited to these cases.

For example, since the attribute keyword "A-line black dress" is obtained in advance, between the attribute keyword "A-line black dress" and the unit keyword "A-line", the unit keyword "black", and the unit keyword "dress" It can be assumed that a mapping exists. In this case, the keyword management unit 220 according to another embodiment of the present invention provides attribute information 320 about the product included in the product image 310 among the unit keywords that are determined to have a correlation based on the above mapping. Combining the unit keyword "A-line" and the unit keyword "dress", which are judged to be related (corresponding) to (corresponding to), the unit keyword "black" and the attribute "orange", which has a common attribute classification as color By further combining the unit keyword "orange" specified from the information, a target attribute keyword "A-line orange dress" can be created, and further by combining the unit keyword "white" specified from the attribute information "white" By doing this, you can create an additional target attribute keyword called “A-line white dress.” That is, the keyword management unit 220 according to an embodiment of the present invention refers to the association relationship between attribute keywords and unit keywords or the association relationship between unit keywords, and sets two or more various target attribute keywords for one product image. You can also create .

Meanwhile, according to an embodiment of the present invention, the keyword management unit 220 may perform the function of assigning the target attribute keyword generated as above to the corresponding product image. According to an embodiment of the present invention, the target attribute keyword assigned as above can be used as a corresponding product image or a name or tag of the corresponding product. For example, according to one embodiment of the present invention, the above target attribute keywords may be given as tags to product images provided in an online shopping mall, and these tags are used in search filters and category classification of products sold in an online shopping mall. It can function as a classifier used.

According to an embodiment of the present invention, target attribute keywords that are highly related to attribute information about the product included in the product image can be assigned to the product image, so filtering criteria applied to the product image can be appropriately set. Furthermore, other product images related to the product image can be provided through the target attribute keyword.

In addition, according to an embodiment of the present invention, when searching for other product images related to the product image through the target attribute keyword assigned to the product image, the association relationship between the attribute keyword and the unit keyword described in detail above Alternatively, the association relationship between unit keywords may be referenced, and accordingly, even if there is no keyword directly in common with the target attribute keyword assigned to the product image, there are other keywords that are related to the product image based on the attribute keyword-based association relationship. Product images can now be searched.

For example, when searching for other product images using the target attribute keyword "neutral color jacket" given to product image A, "brown jacket" and "beige jacket" are searched by referring to the previously determined attribute keyword-based association relationship. Other product images with keywords such as ", "grey jacket", etc. may be searched.

For another example, when searching for other product images using the target attribute keyword "loose fit pants" given to product image B, "wise fit pants" and "baggy" are searched by referring to the previously determined attribute keyword-based association relationship. Other product images with keywords such as “pants” may be searched.

Meanwhile, the keyword management unit 220 according to an embodiment of the present invention can dynamically re-determine the above target attribute keyword.

For example, the keyword management unit 220 according to an embodiment of the present invention may re-determine the target attribute keyword related to the product image every predetermined period (eg, 1 day, 12 hours, etc.).

For another example, when a trend change above a certain level is detected from an external source of the keyword management unit 220 according to an embodiment of the present invention (for example, if the attribute keyword that is the basis of mapping is found to be unusually large in a short period of time) (if obtained), the target attribute keyword related to the product image may be re-determined.

Next, the communication unit 230 according to an embodiment of the present invention may perform a function that enables data transmission and reception to/from the information acquisition unit 210 and the keyword management unit 220.

Lastly, the control unit 240 according to an embodiment of the present invention may perform a function of controlling the flow of data between the information acquisition unit 210, the keyword management unit 220, and the communication unit 230. That is, the control unit 250 according to the present invention controls the data flow to/from the outside of the service provision system 200 or the data flow between each component of the service provision system 200, thereby controlling the information acquisition unit 210, The keyword management unit 220 and the communication unit 230 can each be controlled to perform their own functions.

In the above, an embodiment of assigning a target attribute keyword to a product image including a product has been mainly described, but the embodiment according to the present invention is not necessarily limited thereto, and other types of content including a product (e.g. , videos, etc.), it should be noted that embodiments of assigning target attribute keywords can also be assumed.

The embodiments according to the present invention described above can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium), and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. A hardware device can be converted into one or more software modules to perform processing according to the invention and vice versa.

In the above, the present invention has been described in terms of specific details, such as specific components, and limited embodiments and drawings, but this is only provided to facilitate a more general understanding of the present invention, and the present invention is not limited to the above embodiments. Anyone with ordinary knowledge in the technical field to which the invention pertains can make various modifications and changes from this description.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the scope of the claims are within the scope of the spirit of the present invention. It will be said to belong to

100: communication network
200: Service provision system
210: Information acquisition department
220: Keyword management department
230: Department of Communications
240: control unit
300: device

Claims (13)

A method implemented in a system for assigning attribute-related keywords to a product image - the system includes an information acquisition unit and a keyword management unit -
A step of the information acquisition unit acquiring attribute information about the product included in the product image,
The keyword management unit refers to an association relationship between an attribute keyword and a unit keyword that constitutes the attribute keyword or is derived from the attribute keyword, and combines at least one unit keyword associated with attribute information about the product to create a target attribute keyword. steps for generating, and
The keyword management unit includes assigning the target attribute keyword to the product image,
The attribute keywords are obtained in advance from an external source and
In the generation step, a target attribute keyword associated with attribute information about the product is generated by further referring to the association relationship between two or more unit keywords,
The unit keyword constituting the target attribute keyword corresponds to the unit keyword constituting the attribute keyword,
method. According to paragraph 1,
In the acquisition step, attribute information about the product is recognized from the product image by a learning-based model.
method. delete According to paragraph 1,
The association relationship between the attribute keyword and the unit keyword is determined based on direct or indirect mapping between the attribute keyword and the unit keyword.
method. delete delete A non-transitory computer-readable recording medium recording a computer program for executing the method according to claim 1. A system that assigns attribute-related keywords to product images,
An information acquisition unit that acquires attribute information about the product included in the product image, and
Generating a target attribute keyword by combining at least one unit keyword associated with attribute information about the product, with reference to an association relationship between an attribute keyword and a unit keyword constituting the attribute keyword or derived from the attribute keyword, A keyword management unit that assigns target attribute keywords to the product image,
The attribute keywords are obtained in advance from an external source,
The keyword management unit generates a target attribute keyword associated with attribute information about the product by further referring to the association relationship between two or more unit keywords,
The unit keyword constituting the target attribute keyword corresponds to the unit keyword constituting the attribute keyword,
system. According to clause 8,
Attribute information about the product is recognized from the product image by a learning-based model.
system. delete According to clause 8,
The association relationship between the attribute keyword and the unit keyword is determined based on direct or indirect mapping between the attribute keyword and the unit keyword.
system. delete delete

Images