KR20190125687A - Method, apparatus, system and computer program for recommending contract information based on ontology - Google Patents

Abstract

Disclosed is a method for recommending contract information based on ontology. The method comprises the following steps: creating ontology information representing the association between a plurality of pieces of attribute information based on the predetermined attribute information; determining a keyword for performing a search on a network based on the created ontology information; performing search on the network according to the determined keyword; determining whether to update the created ontology information based at least in part on search result on the network; and creating travel recommendation information personalized for the first user in response to the reception of a travel information recommending request from a first user.

Description

Ontology-based contract information recommendation method, device, system and computer program {METHOD, APPARATUS, SYSTEM AND COMPUTER PROGRAM FOR RECOMMENDING CONTRACT INFORMATION BASED ON ONTOLOGY}

The present invention relates to a method, apparatus, and computer program for recommending ontology-based contract information, and more particularly, to a method, apparatus, and computer program for recommending contract information using an association between metadata.

With the advent of IPTV and smart TVs and the service to watch and search video contents, access to video contents has become easier. However, the amount of serviced content is enormous, and the time and effort for searching for the desired content has been increased. Accordingly, various methods for providing easy and accurate search and recommendation of desired video content have been studied.

Recommend systems have a convergence technique that combines the two techniques, collaborative filtration, content-based filtration, depending on the approach. The collaborative filtration is similar based on the information consumed in the past and the user's information such as gender, age, and occupation. It is a technique that analyzes and recommends items that were consumed in the past by classifying users or creating user groups.

The content-based filtering is a technique for recommending similar items by analyzing data of items consumed in the past by the user.

This recommendation technique analyzes item metadata and recommends items through the analyzed results.

Movie metadata reflects user preferences well, and the characteristics of such movie metadata are useful when recommending a movie.

The recommendation technology using this metadata is being studied by many researchers and used in the service for recommending and watching movies.

Korean Unexamined Patent Publication No. 2008-0066361

According to an embodiment of the present invention, an ontology expressing a relation between metadata is analyzed by analyzing the correlation between metadata of image content, and the association, similarity, and user (person / group) between metadata are based on the ontology. ) Provides a video content recommendation system and method for recommending video content to a user through preference, weight, and emotional state.

The problem to be solved by the present invention is not limited to the problem (s) mentioned above, another problem that is not mentioned will be clearly understood by those skilled in the art from the following description.

The image content recommendation system using the association between the ontology-based metadata according to an embodiment of the present invention is an ontology construction unit for constructing an ontology for the plurality of image contents based on the relationship between the metadata of each of the plurality of image contents. ; And a content recommendation unit for deriving an association between the metadata based on the ontology and providing at least one recommendation image content of the plurality of image contents to a user terminal based on the association.

The content recommendation unit may measure similarity for each item of the metadata based on the association between the metadata and provide the recommended video content to the user terminal based on the similarity for each item.

The content recommending unit may provide the user terminal with the image content of the person having similarity based on the similarity of each item item of the metadata as the recommended image content.

According to an embodiment of the present invention, by analyzing the association between the metadata of the image content to build an ontology representing the relationship between the metadata, based on the ontology, the similarity, similarity, user (personal) Video content can be recommended to the user through preferences, weights, and emotional states.

It is to be noted that the technical terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In addition, the technical terms used in the present specification should be interpreted as meanings generally understood by those skilled in the art unless they are specifically defined in this specification, and are overly inclusive. It should not be interpreted in the sense of or in the sense of being excessively reduced. In addition, when the technical terms used herein are incorrect technical terms that do not accurately represent the spirit of the present invention, it should be replaced with technical terms that can be understood correctly by those skilled in the art.

 In addition, the general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted in an excessively reduced sense.

Also, the singular forms used herein include the plural forms unless the context clearly indicates otherwise. In the present application, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components, or various steps described in the specification, wherein some of the components or some of the steps It should be construed that it may not be included or may further include additional components or steps.

Hereinafter, the present invention will be described in more detail with reference to Examples, but the scope of the present invention is not limited to the following Examples.

The image content recommendation system using the association between the ontology-based metadata according to an embodiment of the present invention is an ontology construction unit for constructing an ontology for the plurality of image contents based on the relationship between the metadata of each of the plurality of image contents. ; And a content recommendation unit for deriving an association between the metadata based on the ontology and providing at least one recommendation image content of the plurality of image contents to a user terminal based on the association.

The content recommendation unit may measure similarity for each item of the metadata based on the association between the metadata and provide the recommended video content to the user terminal based on the similarity for each item.

While specific embodiments of the present invention have been described above, the present invention is not limited to the above-described specific embodiments, and the technical field to which the present invention pertains without departing from the gist of the present invention as claimed in the claims. Anyone of ordinary skill in the art can make various modifications, as well as such modifications are within the scope of the claims.

Claims (1)

Ontology-based contract information recommendation method,
Generating ontology information indicating an association between the plurality of attribute information based on a plurality of predetermined attribute information;
Determining a keyword for performing a search on a network based on the generated ontology information;
Performing a search on the network according to the determined keyword;
Determining whether to update the generated ontology information based at least in part on a search result on the network; And
In response to receiving the travel information recommendation request from the first user, generating personalized travel recommendation information for the first user.