KR20240044029A - Method of providing digital catalog and apparatus performing thereof - Google Patents

Abstract

A digital catalog providing method executed in a digital catalog providing device according to an embodiment of the present invention includes providing a digital catalog production mode selection procedure to an enterprise terminal, producing a digital catalog from the enterprise terminal through the digital catalog production mode selection procedure. It includes receiving a mode and providing a pre-registered digital catalog production format according to the digital catalog production mode, or creating and providing a digital catalog by placing content used on the company's homepage in the digital catalog production format.

Description

Method for providing digital catalog and device for executing the same {METHOD OF PROVIDING DIGITAL CATALOG AND APPARATUS PERFORMING THEREOF}

The present invention relates to a method of providing a digital catalog and a device for executing the same. More specifically, when creating a digital catalog for each company, it is automatically created and provided based on the company's homepage, or a digital catalog production format is provided at the request of the company. This relates to a method of providing a digital catalog that allows manual creation of digital categories using drag and drop, and a device for executing the same.

In recent years, as the importance of e-commerce has been greatly recognized, delivery of accurate information about products distributed through e-commerce is considered the biggest factor for the success of the e-commerce market.

However, when looking at the reality so far, a series of processes such as production, distribution, and exhibition of digital catalogs that convey product information in an e-commerce environment are carried out by each actor, such as product manufacturers, product sellers, and end consumers. As it is done through individual and redundant work, it ultimately causes an increase in costs due to redundant work, and also has the disadvantage of making it difficult to compatibility and share information as each actor maintains a separate digital catalog system suitable for themselves. .

The conventional model for producing and distributing digital catalogs through the Internet is when a product manufacturer directly digitally produces and distributes a catalog for the products it manufactures and supplies, or when a product seller creates a catalog of products sold in his or her Internet store. It can be broadly classified as a case where the product is produced and displayed separately from the supplier of the product.

In this conventional e-commerce digital catalog model, product catalogs can be broadly divided into cases where the product manufacturer produces and distributes the digital catalog separately, and cases where the Internet store selling the product produces and displays the digital catalog separately. Therefore, the digital catalog The reality is that there is currently no entity specializing in distribution.

The problem with this conventional model is that the interests of digital catalog manufacturers and digital catalog users are at odds with each other. Product sellers (e.g., Internet shopping malls) who display product information through digital catalogs want to manage a database with a hierarchical tree structure to manage tens to hundreds of thousands of product information, and enable customers to more easily search for product information. In order to do this, we want to maintain each digital catalog redundantly in each path of the tree structure (while increasing the management burden).

On the other hand, from the perspective of digital catalog producers who want to create and register digital catalogs, if they try to register the digital catalogs they handle in duplicate in this tree structure, not only will it be difficult to properly place them in the required location, but it will also be completely wrong. There is even a risk of registering a digital catalog in the route.

In fact, from the perspective of digital catalog registrants of product information, they prefer product information databases that are easy to input and edit and search, while product sellers who actually reflect product information, such as internet shopping mall operators, have more hierarchically structured products. I prefer structure. On the other hand, from the perspective of customers, who can be called final consumers, they are unable to obtain sufficient product information due to digital catalogs produced according to different standards, which is ultimately hindering the growth of the e-commerce market.

Therefore, a new e-commerce digital catalog management process model that eliminates the shortcomings of the conventional digital catalog process is urgently needed. If a new e-commerce digital catalog management process model that eliminates these problems is presented, all e-commerce actors such as product manufacturers, product sellers, and final buyers can be satisfied, and ultimately, it will lead to the revitalization of e-commerce, including the Internet. It will be achievable.

The present invention provides a digital catalog that automatically creates and provides a digital catalog based on the company's homepage when creating a digital catalog for each company, or provides a digital catalog production format at the company's request, allowing digital categories to be manually created with just drag and drop. It relates to a method and a device for executing the same.

In addition, the present invention uses behavioral information for each user visiting the company's homepage to add weights to each category of the company's homepage, and then arranges the information on the homepage according to the weights on a digital catalog to automatically create a digital catalog. It relates to a method of providing a digital catalog and a device for executing the same.

The objects of the present invention are not limited to the objects mentioned above, and other objects and advantages of the present invention that are not mentioned can be understood by the following description and will be more clearly understood by the examples of the present invention. Additionally, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof indicated in the patent claims.

A digital catalog providing method executed in a digital catalog providing device to achieve this purpose includes providing a digital catalog production mode selection procedure to an enterprise terminal, and selecting a digital catalog production mode from the enterprise terminal through the digital catalog production mode selection procedure. It includes the step of receiving and providing a pre-registered digital catalog production format according to the digital catalog production mode, or creating and providing a digital catalog by placing content used on the company's homepage in the digital catalog production format.

In addition, the digital catalog provision device to achieve this purpose is a company that analyzes each content used on the company's homepage by accessing a digital catalog format database where the digital catalog format is stored and a web service provision server to determine the priority for each content. Provides a content analysis unit and a digital catalog production mode selection procedure to an enterprise terminal, receives a digital catalog production mode from the enterprise terminal through the digital catalog production mode selection procedure, and generates a digital catalog pre-registered according to the digital catalog production mode. It includes a digital catalog production department that provides production formats or creates and provides digital catalogs by placing content used on the company's homepage in a digital catalog production format.

According to the present invention as described above, when creating a digital catalog for each company, it is automatically created and provided based on the company's homepage, or a digital catalog production format is provided at the request of the company to manually create digital categories with drag and drop. There is an advantage to being able to do this.

In addition, according to the present invention, a digital catalog can be automatically created by adding weights to each category of the company's homepage using behavioral information for each user visiting the company's homepage and then placing the information on the homepage on the digital catalog according to the weight. There is an advantage to having it.

1 is a diagram for explaining a digital catalog providing system according to an embodiment of the present invention.
Figure 2 is a block diagram for explaining the internal structure of a user terminal according to an embodiment of the present invention.
Figure 3 is a block diagram for explaining the internal structure of a digital catalog providing device according to an embodiment of the present invention.
Figure 4 is a flowchart for explaining an embodiment of a method for providing a digital catalog according to the present invention.

The above-described objects, features, and advantages will be described in detail later with reference to the attached drawings, so that those skilled in the art will be able to easily implement the technical idea of the present invention. In describing the present invention, if it is determined that a detailed description of known techniques related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In the drawings, identical reference numerals are used to indicate identical or similar components.

1 is a diagram for explaining a digital catalog providing system according to an embodiment of the present invention.

Referring to FIG. 1, the digital catalog providing system includes user terminals (100_1 to 100_N), a web service providing server 200, a digital catalog providing device 300, and an enterprise terminal 400.

The user terminals (100_1 to 100_N) have an application installed to access the web service providing server (200). Accordingly, when the application is selected and executed, the user terminals 100_1 to 100_N can access the corresponding web service providing server 200 through the application.

User terminals 100_1 to 100_N may display web pages provided by the web service providing server 200 through an application. At this time, the web page includes a screen loaded on the electronic device and/or content inside the screen so that it can be immediately displayed on the screen as the user scrolls.

For example, while a web page is displayed on an application of the user terminal 100, the entire execution screen of the application that extends horizontally or vertically and is displayed as the user scrolls may be included in the concept of the web page, and the camera may be included in the concept of the web page. The screen in roll may also be included in the concept of the web page.

Additionally, an application (eg, software, neural network model, etc.) for analyzing user interests is installed in the user terminal 100. Accordingly, the user terminals (100_1 to 100_N) can determine the user's taste by collecting log records or engagement records and then analyzing the log records or engagement records through an application for analyzing user interests.

In one embodiment, the user terminals 100_1 to 100_N may extract user behavior information by analyzing log records or engagement records, and extract a label for determining the type of content from the user behavior information.

In another embodiment, the user terminals (100_1 to 100_N) are equipped with a crawler, parser, and indexer to collect web pages viewed by the user, and access text information such as images, item names, and prices included in the web page. A label to determine the type of content can be extracted.

For example, crawlers collect data related to item information by collecting a list of web addresses that users browse, checking websites, and tracking links. At this time, the parser interprets the web pages collected during the crawling process and extracts item information such as images, item prices, and item names included in the page, and the indexer can index the location and meaning.

The label for determining the type of content includes content viewed by the user (e.g., web browser) included in user behavior information, images of content that generated a like tag (e.g., social network), and images viewed by the user. It refers to the meaning of the item based on the images and text on a homepage.

The web service providing server 200 is a server that provides different content depending on the type of application when the user terminal 100 accesses it through an application. These web service providing servers (300_1 to 300_N) may be implemented as online shopping mall servers, search engine servers, etc.

The digital catalog providing device 300 can extract characteristics of content used in a company's homepage and structure characteristic information of the content.

More specifically, the digital catalog providing device 300 can detect characteristic areas (Interest Point Detection) of content used on a company's homepage. Here, the feature area refers to the main area from which a feature descriptor, that is, a descriptor for the features of an image for determining whether images are identical or similar, is extracted.

According to an embodiment of the present invention, these feature areas include the contours included in the image, corners such as corners among the contours, blobs distinguished from the surrounding areas, areas that are invariant or co-variable depending on the deformation of the image, or brightness greater than the surrounding brightness. It can be a pole with dark or bright features and can target a patch of the image or the entire image.

Furthermore, the digital catalog providing device 300 can extract a feature descriptor (Descriptor Extraction) from the feature area. A feature descriptor expresses the features of an image as vector values.

According to an embodiment of the present invention, this feature descriptor can be calculated using the location of the feature area or the brightness, color, sharpness, gradient, scale, or pattern information of the feature area for the content used on the company's homepage. For example, the feature descriptor may calculate the brightness value, brightness change value, or distribution value of the feature area by converting it into a vector.

Meanwhile, according to an embodiment of the present invention, the feature descriptor for the content used on the company's homepage includes not only a local descriptor based on the feature area as above, but also a global descriptor, a frequency descriptor, It can be expressed as a binary descriptor or a neural network descriptor.

More specifically, the feature descriptor converts the brightness, color, sharpness, gradient, scale, pattern information, etc. of each feature area or the entire content used on the company's homepage into vector values. It may include a global descriptor that is extracted.

For example, the feature descriptor is a frequency descriptor that extracts the number of times pre-classified specific descriptors are included in the content, the number of times global features such as conventionally defined color tables are included in the content, etc., by converting them into vector values, and each descriptor In the layer of the binary descriptor and neural network, which extracts bit by bit whether or not the size of each element value constituting the descriptor is larger or smaller than a specific value and then converts it to an integer type and uses it. It may include a neural network descriptor that extracts image information used for learning or classification.

Furthermore, according to an embodiment of the present invention, the digital catalog providing device 300 can convert a feature information vector extracted from content used on a company's homepage into a low dimension. For example, feature information extracted through an artificial neural network corresponds to 40,000-dimensional high-dimensional vector information, and it is appropriate to convert it to a low-dimensional vector in an appropriate range considering the resources required for search.

The conversion of the feature information vector can use various dimension reduction algorithms such as PCA and ZCA, and the feature information converted to a low-dimensional vector can be indexed in the corresponding content.

Furthermore, the digital catalog providing device 300 according to an embodiment of the present invention can extract the attributes of the meaning of the content by applying machine learning techniques based on the content used in the company's homepage. The attribute may be expressed as an abstracted value, but may also be expressed in text form by interpreting the abstracted value.

According to an embodiment of the present invention, the digital catalog providing device 300 predefines attributes, creates a neural network model that learns the characteristics of content corresponding to the attributes, classifies items in the content, and classifies items in the content. properties can be extracted.

At this time, the digital catalog providing device 300 may assign the corresponding attribute to content that matches a specific pattern with random probability through a neural network model that has learned the pattern of the content corresponding to each attribute.

According to another embodiment of the present invention, the digital catalog providing device 300 learns the characteristics of content corresponding to each attribute to form an initial neural network model, and applies a large number of image items to it to further refine the neural network model. It can also be expanded.

Thereafter, when the digital catalog providing device 300 receives a label from the user terminal 100, the digital catalog providing device 300 may increase the number of accesses to content having attributes matching the label.

As described above, the digital catalog providing device 300 determines the ranking of the content by using the number of accesses to the content used on the company's homepage and applying a weight according to the number of accesses to each content. Then, when the digital catalog production mode is the automatic mode, the digital catalog providing device 300 can produce a digital catalog by placing the content in the digital catalog automatic production format according to the ranking of the content.

To this end, the digital catalog providing device 300 provides a digital catalog production mode selection procedure to the enterprise terminal 400 and receives a digital catalog production mode from the enterprise terminal 400 through the digital catalog production mode selection procedure. .

If the digital catalog production mode is an automatic production mode, the digital catalog providing device 300 determines the arrangement order of each content on the company's homepage based on the predetermined number of accesses corresponding to the content used on the homepage, and The digital catalog is produced by arranging content in a pre-registered digital catalog production format according to the arrangement order.

At this time, the digital catalog providing device 300 selects content according to the arrangement order, and selects the content according to whether the type of the selected content is the same based on the type of content that can be placed in each arrangement area among the digital catalog production formats. Place .

Meanwhile, the digital catalog providing device 300 provides a pre-registered digital catalog production format when the digital catalog production mode is a manual production mode, allowing digital categories to be manually created by dragging and dropping.

When the enterprise terminal 400 receives the digital catalog production mode selection procedure from the digital catalog providing device 300, it selects the digital catalog production mode through the digital catalog production mode selection procedure. At this time, the digital catalog production mode includes manual production mode and automatic production mode.

If the enterprise terminal 400 selects the automatic production mode through the digital catalog production mode selection procedure, it is provided with a digital catalog automatically created by the digital catalog providing device 300 and the digital catalog is automatically created through the digital catalog production mode selection procedure. If you select the production mode, you can create a digital catalog by placing content in the digital catalog production format through drag and drop.

Figure 2 is a block diagram for explaining the internal structure of a user terminal according to an embodiment of the present invention.

Referring to FIG. 2 , the user terminal 100 includes a user browsing record storage unit 110, an application storage unit 120, a label storage unit 130, and a label provision unit 140.

User browsing records are stored in the user browsing record storage unit 110. User viewing records include log records and engagement records. At this time, the log record is created by the user recording events that occur while the operating system or software of the mobile terminal device 400 is running.

Additionally, the user browsing record storage unit 110 may store a list of web addresses viewed by the user. These lists of web addresses can be collected by crawlers, parsers, and indexers. For example, crawlers collect data related to item information by collecting a list of web addresses that users browse, checking websites, and tracking links. At this time, the parser interprets the web pages collected during the crawling process and extracts item information such as images, item prices, and item names included in the page, and the indexer can index the location and meaning.

An application for accessing the web service providing server 200 is installed in the application storage unit 120. These applications may be software, neural network models, etc. that collect log records or engagement records and then analyze the log records or engagement records through an application for user interest analysis to determine the user's tastes.

The label storage unit 130 stores a label for determining the type of content extracted based on user browsing records. The label for determining the type of content includes the content viewed by the user included in user behavior information (e.g., web browser), the image of the content that generated a like tag (e.g., social network), and the image viewed by the user. It refers to the meaning of the item based on the images and text on a homepage.

The label providing unit 140 provides the label stored in the label storage unit 130 to the digital catalog providing device 300.

As described above, the present invention does not directly transmit the user access records collected through the user terminal to the outside, but processes the user access records internally to generate labels for user interests and provides them to the outside, thereby providing internal user access from the outside. The advantage is that the records are inaccessible, preventing leakage of user personal information.

Figure 3 is a block diagram for explaining the internal structure of a digital catalog providing device according to an embodiment of the present invention.

Referring to FIG. 3, the digital catalog providing device 300 includes a digital catalog format database 310, a corporate content analysis unit 320, and a digital catalog production unit 330.

The digital catalog format database 310 stores a digital catalog format.

The corporate content analysis unit 320 can connect to the web service providing server 200, extract characteristics of content used in the company's homepage, and structure characteristic information of the content.

More specifically, the corporate content analysis unit 320 can detect characteristic areas of content used on the company's homepage (Interest Point Detection). Here, the feature area refers to the main area from which a feature descriptor, that is, a descriptor for the characteristics of an image for determining whether images are identical or similar, is extracted.

According to an embodiment of the present invention, these feature areas include the contours included in the image, corners such as corners among the contours, blobs distinguished from the surrounding areas, areas that are invariant or co-variable depending on the deformation of the image, or brightness greater than the surrounding brightness. It can be a pole with dark or bright features and can target a patch of the image or the entire image.

Furthermore, the corporate content analysis unit 320 can extract feature descriptors from the feature area. A feature descriptor expresses the features of an image as vector values.

According to an embodiment of the present invention, this feature descriptor can be calculated using the location of the feature area or the brightness, color, sharpness, gradient, scale, or pattern information of the feature area for the content used on the company's homepage. For example, the feature descriptor may calculate the brightness value, brightness change value, or distribution value of the feature area by converting it into a vector.

Meanwhile, according to an embodiment of the present invention, the feature descriptor for the content used on the company's homepage includes not only a local descriptor based on the feature area as above, but also a global descriptor, a frequency descriptor, It can be expressed as a binary descriptor or neural network descriptor.

More specifically, the feature descriptor converts the brightness, color, sharpness, gradient, scale, pattern information, etc. of each feature area or the entire content used on the company's homepage into vector values. It may include a global descriptor that is extracted.

For example, the feature descriptor is a frequency descriptor that extracts the number of times pre-classified specific descriptors are included in the content, the number of times global features such as conventionally defined color tables are included in the content, etc., by converting them into vector values, and each descriptor In the layer of the binary descriptor and neural network, which extracts bit by bit whether or not the size of each element value constituting the descriptor is larger or smaller than a specific value and then converts it to an integer type and uses it. It may include a neural network descriptor that extracts image information used for learning or classification.

Furthermore, according to an embodiment of the present invention, the corporate content analysis unit 320 can convert the feature information vector extracted from the content used on the company's homepage into a low dimension. For example, feature information extracted through an artificial neural network corresponds to 40,000-dimensional high-dimensional vector information, and it is appropriate to convert it to a low-dimensional vector in an appropriate range considering the resources required for search.

The conversion of the feature information vector can use various dimension reduction algorithms such as PCA and ZCA, and the feature information converted to a low-dimensional vector can be indexed in the corresponding content.

Furthermore, the corporate content analysis unit 320 according to an embodiment of the present invention can apply machine learning techniques based on the content used in the company's homepage to extract the attributes of the meaning of the content. The attribute may be expressed as an abstracted value, but may also be expressed in text form by interpreting the abstracted value.

According to one embodiment of the present invention, the corporate content analysis unit 320 defines attributes in advance, creates a neural network model that learns the characteristics of content corresponding to the attributes, classifies items in the content, and properties can be extracted.

At this time, the corporate content analysis unit 320 can assign the corresponding attribute to content that matches a specific pattern with random probability through a neural network model that has learned the pattern of the content corresponding to each attribute.

According to another embodiment of the present invention, the corporate content analysis unit 320 learns the characteristics of advertising content corresponding to each attribute to form an initial neural network model, and applies a large number of image items to it to view the neural network model. It can also be expanded elaborately.

Thereafter, when the corporate content analysis unit 320 receives a label from the user terminal 100, it can increase the number of accesses to content having attributes matching the label.

The digital catalog production unit 330 provides a digital catalog production mode selection procedure to the user terminals (100_1 to 100_N), and when the digital catalog production mode is selected through the digital catalog production mode selection procedure, the digital catalog production mode pre-registered according to the digital catalog production mode is created. We provide a catalog production format or create and provide a digital catalog by placing the content used on the company's homepage in a digital catalog production format.

Figure 4 is a flowchart for explaining an embodiment of a method for providing a digital catalog according to the present invention.

Referring to FIG. 4, the digital catalog providing device 300 provides a digital catalog production mode selection procedure to the enterprise terminal (step S410).

The digital catalog providing device 300 receives a digital catalog production mode from the enterprise terminal through the digital catalog production mode selection procedure (step S420).

The digital catalog providing device 300 provides a pre-registered digital catalog production format according to the digital catalog production mode or creates and provides a digital catalog by placing content used on the company's homepage in the digital catalog production format (step S430). .

In one embodiment of step S430, when the digital catalog production mode is an automatic production mode, the digital catalog providing device 300 creates each content on the company's homepage based on a predetermined number of accesses corresponding to the content used in the homepage. The digital catalog can be produced by determining the arrangement order and arranging the content in a pre-registered digital catalog production format according to the arrangement order.

In the above embodiment, the digital catalog providing device 300 selects content according to the arrangement order and based on the type of content that can be placed in each arrangement area of the digital catalog production format. The content can be arranged depending on whether the type of the selected content is the same.

Although the present invention has been described with reference to limited embodiments and drawings, the present invention is not limited to the above embodiments, and various modifications and variations can be made by those skilled in the art from these descriptions. Accordingly, the spirit of the present invention should be understood only by the scope of the claims set forth below, and all equivalent or equivalent modifications thereof shall fall within the scope of the spirit of the present invention.

100: user terminal,
110: User viewing record storage unit,
120: application storage,
130: label storage unit,
140: Label provision department,
200: Web service providing server,
300: Digital catalog provision device
310: digital catalog format database,
320: Enterprise content analysis department,
330: Digital catalog production department,
400: Enterprise terminal.

Claims (6)

In a digital catalog provision method executed on a digital catalog provision device,
Providing a digital catalog production mode selection procedure to the enterprise terminal;
Receiving a digital catalog production mode from the enterprise terminal through the digital catalog production mode selection procedure; and
Providing a pre-registered digital catalog production format according to the digital catalog production mode or placing the content used on the company's homepage in the digital catalog production format to produce and provide a digital catalog.
How to provide a digital catalog.
According to paragraph 1,
The step of producing and providing the digital catalog is
When the digital catalog production mode is an automatic production mode, determining the arrangement order of each content on the company's homepage based on a predetermined number of accesses corresponding to the content used on the homepage; and
Characterized in that it includes the step of producing the digital catalog by arranging the content in a pre-registered digital catalog production format according to the arrangement order.
How to provide a digital catalog.
According to paragraph 2,
The step of producing and providing the digital catalog is
Selecting content according to the arrangement order and arranging the content according to whether the type of the selected content is the same based on the type of content that can be placed in each arrangement area of the digital catalog production format. to do
How to provide a digital catalog.
In the digital catalog providing device,
A digital catalog format database in which digital catalog formats are stored;
A corporate content analysis unit that connects to the web service providing server and analyzes each content used on the company's homepage to determine priorities for each content;
Providing a digital catalog production mode selection procedure to a corporate terminal, receiving a digital catalog production mode from the enterprise terminal through the digital catalog production mode selection procedure, and providing a digital catalog production format registered in advance according to the digital catalog production mode. or a digital catalog production unit that produces and provides a digital catalog by placing the content used on the company's homepage in a digital catalog production format.
Digital catalog provision device.
According to clause 4,
The corporate content analysis department
If the digital catalog production mode is an automatic production mode, the arrangement order of each content is determined on the company's homepage based on the predetermined number of accesses corresponding to the content used on the homepage,
The digital catalog production department
Characterized in producing the digital catalog by placing content in a pre-registered digital catalog production format according to the arrangement order.
Digital catalog provision device.
According to clause 5,
The digital catalog production department
Selecting content according to the arrangement order and arranging the content according to whether the type of the selected content is the same based on the type of content that can be placed in each arrangement area of the digital catalog production format. to do
How to provide a digital catalog.