• 한국항행학회논문지
• /
• 제13권1호
• /
• pp.151-155
• /
• 2009

본 논문은 비음수 행렬 분해와 군집 방법을 이용하여 개인화된 문장을 추출하여 문서요약을 하는 새로운 방법을 제안한다. 제안된 방법은 검색 문서에 군집 방법을 이용하여 문서의 주제와 세부 주제를 반영한 문장을 추출하며, 비음수 행렬 분해에 의해 분해된 문서의 고유 의미 특징을 이용하여 사용자의 흥미가 잘 반영된 문장을 추출한다. 실험결과 제안방법이 유사도, 비음수행렬분해를 이용한 방법들에 비하여 좋은 성능을 보인다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제33권4호
• /
• pp.569-577
• /
• 2009

Mobile information retrieval is an evolving branch of information retrieval that is centered on mobile and ubiquitous environments. In general, mobile devices are characterized by lightweight, low power, small memory, small display, limited input/output, low bandwidth, and so on. Some of these characteristics make it impossible to apply general information retrieval to mobile environments without any modification. In order to relieve this problem, we design and implement an information retrieval system for mobile devices like wireless phones, PDA and handheld devices. We use document summarization techniques to alleviate the limitation of small display and user profiles to retrieve the most proper documents for each individual user for personalized search. Futhermore we use meta-search to lighten some burdens visiting several portal sites. In this paper, we have implemented and demonstrated the proposed mobile information retrieval system on the domain of travel and received good evaluation from users subjectively.