• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.285-290
• /
• 2006

In this paper we propose a novel personalized paper search system using the relevance among user's queried keywords and user's behaviors on a searched paper list. The proposed system builds user's individual relevance network from analyzing the appearance frequencies of keywords in the searched papers. The relevance network is personalized by providing weights to the appearance frequencies of keywords according to users' behaviors on the searched list, such as 'downloading,' 'opening,' and 'no-action.' In the experimental section, we demonstrate our method using 100 users' search information in the University of Suwon.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.6
• /
• pp.628-646
• /
• 2009

Users want to browse and search various web contents with mobile devices which can be used anywhere and anytime without limitations, in the same manner as desktop. But mobile devices have limited resources compared to desktop in terms of computing performance, network bandwidth, screen size for full browsing, and etc, so there are many difficulties in providing support for mobile devices to fully use desktop-based web contents. Recently, mobile network bandwidth has been greatly improved, however, since mobile devices cannot provide the same environment as desktop, users still feel inconvenienced. To provide web contents optimized for each user device, there have been studies about analyzing code to extract blocks for adaptation to a mobile environment. But since web contents are divided into several items such as menu, login, news, shopping, etc, if the block dividing basis is limited only to code or segment size, it will be difficult for users to recognize and find the items they need. Also it is necessary to resolve interface issues, which are the biggest inconvenience for users browsing in a mobile environment. In this paper, we suggest a personalized adaptation system that extracts item blocks from desktop-based web contents based on user interests, layers them, and adapts them for users so they can see preferred contents first.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5S
• /
• pp.1696-1707
• /
• 2000

With the proliferation of electronic commerce (EC), the product items which are transacted and the user classes who utilize the EC are spread rapidly. Many users have to expend time and effort in searching of products an or the shopping malls which deal with the products. For his reason, the intelligent retrieval of both malls and products based on an intelligent software agent has been raised as a hot issue. In this paper we have constructed an ontology server that is an essential constituent for agent-based intelligent EC. And also we have designed and implemented a use adapted personalized product search function based on the ontology that are registered in the server.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.43-49
• /
• 2000

The World Wide Web has become a vast information resource where virtually any information can be found. There is a pressing need for appropriate Web search tools due to the very vastness of information space, the rate of growth, and the volatility of data. The agent technology has been studied to address these issues and led to the creation of an adaptive, Proactive. personalized search tools. This study looks into the mechanism of collaborative filtering of information and suggests a decentralized collaborating agents model for information discovery.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.545-558
• /
• 2007

This paper presents an efficient semantic service discovery scheme called UbiSearch for a large-scale ubiquitous computing environment. A semantic service discovery network in the semantic vector space is proposed where services that are semantically close to each other are mapped to nearby positions so that the similar services are registered in a cluster of resolvers. Using this mapping technique, the search space for a query is efficiently confined within a minimized cluster region while maintaining high accuracy in comparison to the centralized scheme. The proposed semantic service discovery network provides a number of novel features to evenly distribute service indexes to the resolvers and reduce the number of resolvers to visit. Our simulation study shows that UbiSearch provides good semantic searchability as compared to the centralized indexing system. At the same time, it supports scalable semantic queries with low communication overhead, balanced load distribution among resolvers for service registration and query processing, and personalized semantic matching.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.354-360
• /
• 2006

The purpose of this paper is to propose a securely personalized context-aware cooperative query that supports a multi-level data abstraction hierarchy and conceptual distance metric among data values, while considering privacy concerns around user context awareness. The conceptual distance expresses a semantic similarity among data values with a quantitative measure, and thus the conceptual distance enables query results to be ranked. To show the feasibility of the methodology proposed in this paper we have implemented a prototype system in the area of site search in a large-scale shopping mall.

• Management & Information Systems Review
• /
• v.9
• /
• pp.81-97
• /
• 2002

In the beginning of the Web history, the main function and importance of the Internet was focused on the content of the data. However, that focus has been switched to the search engines because of the abundant, humongous amount of data that are spread all over the globe. The Webmasters are now implying flasy, beautiful graphics and newly developed technologies to make their websites attract the Internet users. The significant change was mainly caused by the companies that thought cyber shopping malls were going to be very simple and profitable. They believed that the decreasing prices of hardware and easy-to-use software were going to attract the potential customers, resulting in a new, massive market. A website needs to be extremely captivating and attractive, in order to bring in new customers and induce them to return. The Webmaster has to devise methods to find out what kinds of contents would bring in a bigger audience, as well as checking the validity and correctness of the contents. In the thesis, the necessity and concept of a personalized Internet shopping mall will be discussed through the theoretical examination of the one-to-one marketing and the concept of the current shopping malls. The scheme of the personalized shopping mall will be presented, which will encourage the formation of loyal customers, in the ever-growing competitiveness of the marketing environment, by satisfying their wants faster and more precisely.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.498-500
• /
• 2003

인터넷의 급속한 팽창으로 인해 가을 정보의 양이 폭발적으로 증가하고 있다. 웹 사용자에게 이용 가치가 없는 정보 범람(information overflow)안이 발생한다면 효율적인 정보검색이 되지 못하므로 사용자가 원하는 정보만을 얻을 수 있다면 시간과 미숙한 정보의 검색을 방지 할 수 있다. 본 논문에서는 한국어 질의 생성과 관련하여 웹 사용자의 편의성과 효율성을 고려한 한국어 질의 처리 방법론과 개인형 메타 검색 모델을 제안하고자 한다. 한국어 질의를 기본으로 하여 한국어 문장 패턴 및 개인 정보 평가 구성 요소를 이용한 방법론과 모델을 제안하고자 한다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.8
• /
• pp.620-628
• /
• 2010

With the use of the Internet pervasive in everyday life, people are now able to retrieve a lot of information through the web. However, exponential growth in the quantity of information on the web has brought limits to online search engines in their search performance by showing piles and piles of unwanted information. With so much unwanted information, web users nowadays need more time and efforts than in the past to search for needed information. This paper suggests a method of using query expansion in order to quickly bring wanted information to web users. Popularity based Term Weight Mensuration better performance than the TF-IDF and Simple Popularity Term Weight Mensuration to experiments without changes of search subject. When a subject changed during search, Popularity based Term Weight Mensuration's performance change is smaller than others.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.364-368
• /
• 2009

"소셜 네트워크(Social Network)와 검색(Search)의 만남"은 현재 인터넷 상에서 매우 의미 있는 두 영역의 결합이다. 이와 같은 두 영역의 결합을 통해 소셜 네트워크 내에서 친구들의 생각이나 관심사 및 활동을 검색하고 공유함으로써 검색의 효율성과 적합성을 높이기 위한 연구들이 활발히 수행되고 있다. 본 논문에서는 일반적인 소셜 관계 랭크(SRR : Social Relation Rank) 및 토픽이 반영된 소셜 관계 랭크(TS_SRR : Topic Sensitive_Social Relation Rank) 알고리즘을 제안한다. SRR은 소셜 네트워크 내에 존재하는 웹 사용자들의 내재적인 특성 및 검색 성향 등에 대한 관련성(또는 유사정도)을 수치로 산정한 '소셜 관계 지수(SRV : Social Relation Value)'에 랭킹(Ranking)을 부여한 것을 의미한다. 제안하는 알고리즘의 검색 적용 가능성을 검증하기 위해 첫째, 웹 사용자간 직접 또는 간접적인 연결로 구성된 소셜네트워크를 구성 한다. 둘째, 웹 사용자들의 속성에 내재된 정보를 이용하여 토픽별 SRV를 산정한 후 랭킹을 부여하고, 토픽별 변화되는 랭킹에 따라 소셜 네트워크를 재구성 한다. 마지막으로 (TS_)SRR과 웹 사용자들의 검색 패턴(Search Pattern)을 비교 실험 한다. 실험 결과 (TS_)SRR이 높은 웹 사용자 간에는 검색 패턴 또한 유사함을 확인 하였다. 결론적으로 (TS_)SRR 알고리즘을 기반으로 관심분야에 연관성이 높은, 즉 상위에 랭크 된 웹 사용자들을 검색하여 검색 패턴을 공유 또는 상속받는 다면 개인화 검색(Personalized Search) 및 소셜 검색(Social Search)의 효율성과 신뢰성 향상에 기여 할 수 있다.