• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.55-57
• /
• 2001

캐쉬 대체 알고리즘은 캐쉬 적재공간의 한계성을 극복하는 방법 중에 하나이다. 기존의 많은 대체 알고리즘의 문제점인 대체 기준치의 부정확성 및 불충분성을 해결하기 위해 인기도를 제안하였다. 인기도는 인기 검색어의 순위를 정규화 한 값으로, 대량의 자료를 바탕으로 얻어진 통계치이다. 인기도 산출의 기반이 되는 인기 검색어는 시간적 흐름에 민감하고, 사회 전반적인 경향을 반영하며, 많은 중복을 가지고 있다. 인기도는 각 검색 엔진별로 단일 인기도와 누적 인기도를 산출한 후에, 이를 모두 병합하여 산출된다. 이것을 병합 인기도라고 하며, 이는 임의의 검색어에 0에서 1사이의 소수값으로 부여된다. 인기도는 메타 검색 엔진에서 캐쉬 대체를 수행할 때 적용될 수 있으며, 다수의 자료 입력 경향에 관한 정보가 존재하는 문제 영역에 사용될 수 있다.

• Journal of KIISE
• /
• v.44 no.8
• /
• pp.782-790
• /
• 2017

The service, 'Hot Search Keywords', provides a list of the most hot search terms of different web services such as Naver or Daum. The service, bases the changes in rank of a specific search keyword on changes in its users' interest. This paper introduces a temporal modelling framework for predicting the rank change of hot search keywords using past rank data and machine learning. Past rank data shows that more than 70% of hot search keywords tend to disappear and reappear later. The authors processed missing rank value, using deletion, dummy variables, mean substitution, and expectation maximization. It is however crucial to calculate the optimal window size of the past rank data. We proposed an optimal window size selection approach based on the minimum amount of time a topic within the same or a differing context disappeared. The experiments were conducted with four different machine-learning techniques using the Naver, Daum, and Nate 'Hot Search Keywords' datasets, which were collected for 2 years.

• Journal of Information Management
• /
• v.42 no.4
• /
• pp.155-174
• /
• 2011

This study aims to focus on classifying the search engine queries according to web query topic and the different user intents behind web queries. First, we classified 10,000 web query data set by topic. The results showed that there was significant differences in interesting topics across time. Also, we categorized 500 popular queries in web search engine as informational, navigational, or transactional. As a result, 82 percent of web queries are informational in nature, with about 10.8 percent for navigational and 7.2 percent for transactional. This results will help establish the policy to provide internet contents based on user's intent and also find out the social and cultural characteristics.

• Journal of KIISE:Databases
• /
• v.29 no.2
• /
• pp.148-157
• /
• 2002

Caching in meta-search engines can improve the response time of users' request. We describe the cache scheme in our meta-search engine in terms of its architecture and operational flow. In particular, we propose a popularity-driven cache algorithm that utilizes popularities of queries to determine cached data to be purged. The popularity is a value that represents the normalized occurrence frequency of user queries. This paper presents how to collect popular queries and how to calculate query popularities. An empirical performance evaluation of the popularity-driven caching with the traditional schemes (i.e., least recently used (LRU) and least frequently used (LFU)) has been carried out on a collection of real data. In almost all cases, the proposed replacement policy outperforms LRU and LFU.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.250-253
• /
• 2007

본 논문에서는 현재 검색 엔진의 랭킹 방식의 문제점과 인터페이스의 문제점을 해결하기 위하여 노력하였다. 기존의 페이지간 링크와 같은 부가적 정보를 이용한 인기도 기반 랭킹의 문제점을 단어간의 수식 관계를 이용한 의미 기반 랭킹 알고리즘의 제시를 통해 해결하였다. 또한 검색어와 연관된 단어를 수식 관계를 이용하 계산, 시각화하여 제공함으로써 사용자가 잘못된 검색어로 검색을 시작하였더라도 항상 올바른 검색 결과를 얻을 수 있도록 도왔으며 각 검색 결과와 함께 원문을 요약해 제공함으로써 검색 결과를 일일이 클릭해 보지 않고도 내용을 쉽게 유추할 수 있도록 도왔다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.53-57
• /
• 2010

현재 많은 포털 사이트에서는 인기가 있거나 중요도가 높은 키워드에 대해 정보를 제공해주는 태그 클라우드나 연관 검색어 등의 기능이 제공되고 있다. 하지만 대부분의 뉴스기사 페이지들은 날짜와 분야별로 기사들이 나열되어 있으며 사용자는 카테고리별로 나누어진 기사를 읽을 수만 있을 뿐 그 기사와 연관된 다른 기사의 정보에 대해서 한눈에 알아 볼 수 있는 방법은 미흡한 실정이다. 또한 연관 검색어 서비스도 사용자가 검색한 입력 내용을 기반으로 연관성 정도를 분석하여 객관성을 보장하지 못하고 있다. 본 논문에서는 기존의 태그 클라우드 방식에서 좀 더 나아가 축적된 뉴스 기사로 부터 검색 키워드와 밀접히 연관된 키워드를 추출하여 제공하는 기사 검색 시스템을 소개한다. 이 시스템은 사용자가 기사 검색을 하였을 때, 키워드와 가장 밀접한 기사를 검색해 주는 것뿐만 아니라 검색어와 관련된 연관 키워드들을 보여주고 연관된 키워드간의 관계성을 보여줌으로써 뉴스 기사들 속에 숨겨진 연관정보의 탐색을 가능하게 한다.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.59-64
• /
• 2019

This study used the Google Trends site to analyze selection information that users expect from prominent Toothbrushes and Toothpastes through related search keywords that users wanted to obtain. From 2006 to 2018(sep), searches for Toothbrushes and Toothpastes were arranged in the order of popularity of related searched words. The total number of searches words exposed was each 25, total 325 collected. The analysis was conducted using two methods, first, by search function. second, by a word network using a Big Data program. The study has shown that toothbrushes there are high expectations for brands, toothpaste there are high expectations in the function. In order to increase the motivation for oral health education, it is recommended to use and provide knowledge about the brand of toothbrushes and Toothpastes by the function.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.1
• /
• pp.19-29
• /
• 2011

As people have heightened attention to blogs that are individual media, a variety rank algorithms was proposed for the blog search. These algorithms was modified for structural features of blogs that differ from typical web sites, and measured blogs' reputations or popularities based on the interaction results like links, comments or trackbacks and reflected in the search system. But actual blog search systems use not only blog-ranks but also search words, a time factor and so on. Nevertheless, those might not produce desirable results. In this paper, we suggest a topic-rank technique, which can find blogs that have significant degrees of association with topics. This technique is a method which ranks the relations between blogs and indexed words of blog posts as well as the topics representing blog posts. The blog rankings of correlations with search words are can be effectively computed in the blog retrieval by the proposed technique. After comparing precisions and coverage ratios of our blog retrieval system which applis our proposed topic-rank technique, we know that the performance of the blog retrieval system using topic-rank technique is more effective than others.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1311-1317
• /
• 2007

Recently, due to the popularity and explosive growth of the Internet, the information exchange is increasing so rapidly over the Internet. Also the XML is becoming a standard as well as a major tool of data exchange on the Internet and thus we propose the new indexing technique for evaluating a path-oriented query and design and implementation of Path-oriented Query Processing System to give useful for users. In proposed indexing technique, which combined a binary trio structure with a path signature file to improve performance of XML document retrieval.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.6
• /
• pp.63-71
• /
• 2011

The current Web portal sites provide significant keywords with high popularity or importance; specifically, user-friendly services such as tag clouds and associated word search are provided. However, in general, since news articles are classified only with their date and categories, it is not easy for users to find other articles related to some articles while reading news articles classified with categories. And the conventional associated keyword service has not satisfied users sufficiently because it depends only upon user queries. This paper proposes a way of searching news articles by utilizing the keywords tightly associated with users' queries. Basically, the proposed method discovers a set of keyword association patterns by using the association rule mining technique that extracts association patterns for keywords by focusing upon sentences containing some keywords. The method enables users to navigate the space of associated keywords hidden in large news articles.