• Journal of the Korean Society for information Management
• /
• v.41 no.3
• /
• pp.145-169
• /
• 2024

This study examined university library services for students, including international students, and the AI-based information services provided by libraries. Additionally, the standards of Korean language education for international students were investigated. Based on the analysis of library services and these standards, a book recommendation system for learning Korean was developed using ChatGPT. The recommendation results from three training datasets were evaluated for recommendation precision. The results of the chatbot's book recommendations based on the 13 test questions were evaluated by recommendation precision. The comparison of the recommendation precision showed that the chatbot using the combined dataset was more successful in recommending all relevant books compared to the individual datasets. This study serves as an example of an effective approach to utilizing artificial intelligence technology for user services in university libraries.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2013.06a
• /
• pp.277-280
• /
• 2013

워터프론트의 의미 특히 친수공간과 워터프론트의 차이와 함께 유래와 변천을 살펴보고자 하였다. 아울러 수역적 관점에서 워터프론트 개발사례와 개발의 주요 목적을 구분하였다. 또한 유럽 각국과 미국 등에서의 시기별, 유형별 개발의 주안점과 키워드를 정리하는 한편 개발이 지역경제에 미치는 영향을 정성적으로 다루어보고자 하였다. 마지막으로 관광활성화를 목적으로 하는 경우의 전제조건과 도입사례를 제시하였고, 우리나라 항만친수공간 관련 정책의 전개와 문제점을 제시하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.175-184
• /
• 2022

Travel YouTubers who cross the boundary between tradition and novelty communicate by sharing their activities with others through SNS-based media. Media content should not only satisfy individuals, nor should it be too purpose-oriented. YouTube channels should be operated so that users can easily access content naturally, and more diverse methods can be pursued based on usage patterns and satisfaction theory. This study is about the type of perception of Generation Z on travel YouTube titles. As a result of conducting QUANL program analysis on 34 Q samples and 28 P samples from the Q methodological perspective, a total of three types were found. For types with unique characteristics, the first type was named "attention of keywords that draw imagination," the second type was "preferred to stories that stimulate curiosity," and the third type was "image satisfaction reflecting expectations." In addition, considering the characteristics of each type found, the scalability and strategic plan of the activities that Generation Z travel YouTubers want to unfold were presented.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.396-399
• /
• 2011

모바일 기기의 보급이 확대됨으로서 모바일 기기에 내장된 카메라로 획득한 영상을 처리하는 다양한 종류의 응용프로그램이 개발되어 사용되고 있다. 대표적인 응용프로그램은 카메라로 찍은 영상의 사물 검색결과를 인터넷 검색엔진과 연계함으로서 키워드 입력 없이 검색할 수 있도록 하는 것이다. 본 연구는 그 중에서 한글 문자가 포함된 영상을 대상으로 영상검색 수행하는 연구로서 영상에서 한글 문자 영역을 검출하는 방법을 제안하였다. 한글 문자 구조 특징으로 한글 자소를 병합하여 후보 문자 영역을 추출하고 병합된 후보 문자 영역을 한글 6가지 문자 유형 특징을 기반으로 문자 영역을 여부를 판별함으로서 최종적인 문자 영역을 검출한다. 실험결과 문자영역 재현률이 향상됨을 알 수 있었다.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.816-818
• /
• 2015

본 논문에서는 질의유형을 통한 검색기반 질의응답 시스템을 구현하기 위한 설계방법을 제안한다. 이를 위해 위키피디아 문서의 링크 데이터를 이용하여 색인 대상문서와 데이터베이스를 구축하는 색인 모델과 2-포아송 모델을 이용하여 얻은 문서들을 색인 데이터베이스를 통해 필터링하여 정답 후보문장을 추출하는 검색모델, 키워드 패턴 매칭 기반 질의유형 분류 모델을 설계하였다.

• Annual Conference of KIPS
• /
• 2013.05a
• /
• pp.208-211
• /
• 2013

인터넷의 발달과 온라인 음악서비스로 인해 많은 사람들이 손쉽게 원하는 곡들을 선택하여 청취할 수 있다. 수많은 곡들 중 자기가 선호하는 음악을 듣고 찾기엔 많은 시간이 필요할 뿐만 아니라 검색하기 위해 곡 제목이나 아티스트 및 연도에 관한 정보도 숙지해야 할 것이다. 또한 질의에 해당하는 키워드가 포함되는 리스트만 제공되는 기존 음악 다운 사이트의 환경을 개선하고자, 영국 헤리엇와트 대학 연구진의 결과를 토대로 한 성격유형을 매칭시켜 해당된 장르를 구하고 컨텐트 기반인 음색유사도를 통해 질의에 해당된 음악을 추천해 주는 시스템을 설계하고자 한다. 4Shared.com과 비교 분석하였고 누구나 아는 유명한 곡들보다 한번도 들어보지 못한 곡들을 추천함으로써 유용성에 대한 기대감을 높이고자 한다.

• Journal of Korean Library and Information Science Society
• /
• v.34 no.2
• /
• pp.233-253
• /
• 2003

Knowledge organization is the way we humans understand the world. There are two types of information organization mechanisms studied in information retrieval: namely classification md clustering. Classification organizes entities by pigeonholing them into predefined categories, whereas clustering organizes information by grouping similar or related entities together. The system of the Internet information resources extracts a keyword from the words which appear in the web document and draws up a reverse file. Term clustering based on grouping related terms, however, did not prove overly successful and was mostly abandoned in cases of documents used different languages each other or door-way-pages composed of only an anchor text. This study examines infometric analysis and clustering possibility of web documents based on co-link topology of web pages.

• Journal of Korean Society of Archives and Records Management
• /
• v.13 no.3
• /
• pp.67-97
• /
• 2013

The purpose of this study is to design and evaluate an individual instance-based ontology retrieval system for archival records of the "Saemaul Movement". We used Protege editor 4.1 to design an individual instance-based ontology. To evaluate the proposed ontology retrieval system, five short queries and ten narrative queries were used and compared their precision and recall against the NARA keyword-based retrieval system. The performance results showed that the individual-based ontology retrieval system outperformed the keyword-based retrieval system in terms of the measurement of precision and recall.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.217-235
• /
• 2021

As 49% of the world's population uses social media platforms, communication and content sharing within social media are becoming more active than ever. In this environmental base, the one-person media market grew rapidly and formed public opinion, creating a new trend called sell-sumer. This study defined new types of influencers by product category by analyzing the subject concentration of the commercial/non-commercial keywords of influencers and the impact of the ratio of commercial postings on sales. It is hoped that influencers working within social media will be helpful to new sales strategies that are transformed into sell-sumers. The method of this study classifies influencers' commercial/non-commercial posts using Python, performs text mining using KoNLPy, and calculates similarity between FastText-based words. As a result, it has been confirmed that the higher the keyword theme concentration of the influencer's commercial posting, the higher the sales. In addition, it was confirmed through the cluster analysis that the influencer types for each product category were classified into four types and that there was a significant difference between groups according to sales. In other words, the implications of this study may suggest empirical solutions of social media sales strategies for influencers working on social media and marketers who want to use them as marketing tools.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.767-776
• /
• 2009

The purpose of this paper is to design, implement and test the automatic marking system for programming languages using key-words and boolean operations to solve the processing problems of natural languages. There are accurate grammar systems and key-words in programming languages. Using these characteristics, We have designed, programmed, and tested automatic marking system for programming languages through key-words and boolean operations in this paper. We have categorized programming languages into 7 types as the type of answer and when a professor input any key-words, the system make him put conjunction with the special character. It can be logical expressions instantly so that the system easily operates. We asked 10 students who are majoring in computer engineering to take a test on the paper and web to show how well automatic marking system that we have programmed works. Then We requested 3 professors if the subject problems marked objectively. As a result, automatic marking system proved to be appropriate. We have proposed the way of using key-words and boolean operation for prohibiting huge natural language processing in marking of subjective question. It promotes efficiency rate of programming, objectivity and speed through the transferal to the web for marking since the system prohibits marker to include personal opinion on marking and gives feedback quickly