• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.404-406
• /
• 2023

본 논문은 맞춤형 카페 추천 서비스를 제안한다. 대중적인 포털 사이트의 카페 정보와 사용자 리뷰를 크롤링 하여 지역별, 키워드별 카페 데이터를 수집한다. 사용자가 원하는 지역과 임의의 키워드를 기준으로 데이터셋 내의 키워드와 비교하여 가장 유사한 키워드를 추출한다. spaCy 라이브러리의사전 학습된 모델 중 similarity method를 사용하여 추출된 키워드를 바탕으로 해당하는 카페를 추천한다. 이를 통해 사용자는 불필요한 정보를 걸러내고 쉽게 원하는 정보를 얻을 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.187-188
• /
• 2020

본 논문에서는 한방 8체질 및 신체정보 관련 데이터셋을 바탕으로 개인 맞춤 식품 및 식단을 추천하는 데이터베이스의 설계·구축을 수행한다. 또한 이 시스템을 이용하여 추천된 식품(식단)과 희망하는 지역을 입력했을 때 선별된 음식점 정보를 제공한다. 데이터베이스 생성 프로세스와 수집한 데이터를 통해 데이터베이스 설계, 데이터 수집, 생산 및 처리 예제, 데이터베이스 활용 등에 대해 다양한 방법을 제공한다. 일상생활에서 데이터베이스 시스템을 활용함으로써, 이 시스템은 한의원 또는 전문채널을 통해 알 수 있었던 맞춤 식단 정보를 대중에 공개되어 정보 진입장벽을 낮추고 편의성을 도모한다. 이로써 오늘날 고령 사회에 진입한 대한민국에서 국민들이 건강한 식생활을 지원하여 궁극적으로 국민 건강 증진에 기여한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.17-22
• /
• 2023

This study analyzed the genres of popular character web dramas and studied the development of story recommendations through the language model GPT. As a result of the study, it was confirmed that similar cliches are repeated in web dramas. In this study, a common story structure (cliché) was analyzed and a typical story structure was standardized and presented so that even unskilled video producers can easily produce character web dramas. For analysis, clichés of web dramas in the school romance genre, which is the most popular genre among teenagers, were listed in order of success. In addition, this study studied the story recommendation mechanism for users by learning the clichés that were analyzed and cataloged in GPT. Through this study, it is expected to accelerate the production of various contents as well as popular popularity through the acceptance of various databases from the standpoint of database consumption theory of web contents.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1170-1172
• /
• 2015

최근 현대인들은 자신의 시간을 관리하며 남는 시간을 활용해 어떻게 여가생활을 즐길 것인지가 큰 관심사로 떠오르고 있다. 이런 여가시간에 많은 즐길거리가 있는 축제를 많이 찾는다. 이에 따라 가족 단위 혹은 연인단위로 축제를 찾는 사람이 많아졌는데 자가용과 대중교통을 이용하여 교외의 축제를 다닐 수 있는 기회가 늘어남으로써 전국의 축제를 언제든지 즐길 수 있게 되었다. 이에 따라 전국에서 개최하는 축제의 횟수도 늘어나는 추세이다. 이렇게 축제가 늘어남으로써 사용자들은 원하는 축제가 무엇인지를 찾기 힘들게 되었고 이를 해소하기위해 개인 성향에 따른 축제를 추천해주는 시스템을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1169-1172
• /
• 2017

스마트 거울은 다양한 IT기술을 활용하여 다양한 정보를 제공해 주는 거울이다. 그러나 기존의 스마트 거울은 단순한 정보만을 제공하거나 기존 정보 시스템에 답습에 그치고 있다. 본 논문에서는 기존 스마트 거울의 기능과 함께 사용자 맞춤형 스타일링 가이드 모드를 최적화한 Iot 기반 스마트 거울 시스템을 제안한다. 제안하는 시스템의 스타일링 가이드모드는 헤어 스타일링 방법 추천과 메이크 업 방법 추천, 퍼스널 컬러를 이용한 화장품 색상 추천 등의 다양한 기능을 제공하여 거울의 본질을 극대화 할 수 있도록 한다. 제안 시스템은 스마트 거울이 갖추어야 할 날씨 정보, 대중교통 도착정보, 길찾기, 일정 관리, 사진 촬영 등의 일반적인 기능을 제공한다. 이를 바탕으로 사용자에게 새로운 스타일링의 접근성과 활용성을 높이고, 다양한 미디어 정보를 통한 정보 활용과 외출 시간을 단축하는 새로운 스마트 거울 시스템을 제안한다.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.87-94
• /
• 2021

The purpose of this study is to categorize tourists according to the types of Korean popular culture as travel motives and to explore their characteristics and behavior in the tourism-related decision-making process. A sample of 12,914 leisure tourists from the 2018 foreign tourist survey data was analyzed using MNL and ANOVA. The popular cultural tourists were categorized into K-food, K-fashion, and K-pop groups. They showed a higher percentage of female tourists, social media usage in the tourism information search, and visits from countries geographically close to Korea. K-pop tourists did not hesitate to choose Korea as the destination and visited Korea the most frequently. They showed the highest satisfaction, revisit intention and recommendation intention, suggesting loyalty and growth potential.

• Journal of the Korean Society for information Management
• /
• v.30 no.2
• /
• pp.297-315
• /
• 2013

This study aims to analyze and evaluate term suggestion services of major search portals, Naver and Google Korea. In particular, this study evaluated relevance and currency of related search terms provided, and analyzed characteristics such as number and distribution of terms, and queries that did not produce terms. This study also analyzed types of terms in terms of the relationship between queries and terms, and investigated types and characteristics of harmful terms and terms with grammatical errors. Finally, Korean queries and English queries, and popular queries and academic queries were compared in terms of the amount and relevance of search terms provided. The results of this study show that the relevance and currency of Naver's related search terms are somewhat higher than those of Google. Both Naver and Google tend to add terms to or delete terms from original queries, and provide identical search terms or synonym terms rather than providing entirely new search terms. The results of this study can be implemented to the portal's effective development of term suggestion services.

• The Journal of the Korea Contents Association
• /
• v.19 no.2
• /
• pp.284-295
• /
• 2019

In the recent times, a personalized travel path recommendation based on both travelogues and community contributed photos and the heterogeneous meta-data (tags, geographical locations, and date taken) which are associated with photos have been studied. The travellers using social media leave their location history, in the form of paths. These paths can be bridged for acquiring information, required, for future recommendation, for the future travellers, who are new to that location, providing all sort of information. In this paper, we propose a personalized travel path recommendation scheme, based on social life log. By taking advantage, of two kinds of social media, such as travelogue and community contributed photos, the proposed scheme, can not only be personalized to user's travel interest, but also be able to recommend, a travel path rather than individual Points of Interest (POIs). The proposed personalized travel route recommendation method consists of two steps, which are: pruning POI pruning step and creating travel path step. In the POI pruning step, candidate paths are created by the POI derived. In the creating travel path step, the proposed scheme creates the paths considering the user's interest, cost, time, season of the topic for more meaningful recommendation.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.270-283
• /
• 2012

With the advent of multi-channel TV, IPTV and smart TV services, excessive amounts of TV program contents become available at users' sides, which makes it very difficult for TV viewers to easily find and consume their preferred TV programs. Therefore, the service of automatic TV recommendation is an important issue for TV users for future intelligent TV services, which allows to improve access to their preferred TV contents. In this paper, we present a recommendation model based on statistical machine learning using a collaborative filtering concept by taking in account both public and personal preferences on TV program contents. For this, users' preference on TV programs is modeled as a latent topic variable using LDA (Latent Dirichlet Allocation) which is recently applied in various application domains. To apply LDA for TV recommendation appropriately, TV viewers's interested topics is regarded as latent topics in LDA, and asymmetric Dirichlet distribution is applied on the LDA which can reveal the diversity of the TV viewers' interests on topics based on the analysis of the real TV usage history data. The experimental results show that the proposed LDA based TV recommendation method yields average 66.5% with top 5 ranked TV programs in weekly recommendation, average 77.9% precision in bimonthly recommendation with top 5 ranked TV programs for the TV usage history data of similar taste user groups.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2871-2877
• /
• 2015

Shopping patterns are changing with the emergence of SNS. Recently, it is also interested in providing the information based on the users' needs. Generally, the provided information is obtained from the history of users' simple browsing. Best selling hot item list is also provided in order to reflect the preferences of public users. However, the provided information is irrelevant to an individual preference. In this paper, we propose a method to utilize inner and outer SNS for analyzing public preferences about goods which are interested by individual users. The inner analyzing module collects and analyzes the preferences of community members about two goods designated by individual users. The outer analyzing module supports to analyze public preferences by using the tweeter SNS. The results of implementation show that it is possible to recommend goods based on the individual users' preferences unlike the existing shopping mall.