• 한국컴퓨터정보학회논문지
• /
• 제13권7호
• /
• pp.247-256
• /
• 2008

본 연구에서는 웹 문서에서의 단순 키워드 매칭으로 검색하는 전자상거래시스템의 문제점을 해결하기 위한 방안으로 도메인 온톨로지를 자동으로 생성하고 이를 기반으로 지능형 에이전트기술을 접목함으로서 의사소통이 단일화된 상품검색시스템을 개발한다. 온톨로지 개발은 국제상품분류코드(UNSPSC)와 귀금속 보석 사이트들의 분류정보를 기반으로 대표용어를 추출하고 유사관계 시소러스 적용하여 표준화된 온톨로지를 구축하며 지능형에이전트 기술을 검색 단계에서 접목시켜 사용자에게 정보수집의 효율성을 지원하도록 시맨틱 웹을 지원하는 상거래 시스템을 설계하고 구현한다. 또한 개인화된 검색 환경을 지원하기 위해 사용자 프로파일을 설계하고, 개인화 검색 에이전트와 추론기능을 이용한 검색 환경을 제공함으로서 정보수집의 신속성과 정확한 정보검색이 가능하도록 지원한다.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.721-738
• /
• 2012

The Internet has become an increasingly important source for finding the right employees, so more and more companies post their job openings on the Web. The large amount and dynamic nature of career recruiting information causes information overload problems for job seekers. To assist Internet users in searching for the right job, a range of research and commercial systems were developed over the past 10 years. Surprisingly, the majority of existing job search systems support just one, rarely two ways of information access. In contrast, our work focused on exploring a value of comprehensive access to job information in a single system (i.e., a system which supports multiple ways). We designed Proactive, a recommendation system providing comprehensive and personalized information access. To assist the varied needs of users, Proactive has four information retrieval methods - a navigable list of jobs, keyword-based search, implicit preference-based recommendations, and explicit preference-based recommendations. This paper introduces the Proactive and reports the results of a study focusing on the experimental evaluation of these methods. The goal of the study was to assess whether all of the methods are necessary for users to find relevant jobs and to what extent different methods can meet different users' information requirements.

• 한국인공지능학회지
• /
• 제12권2호
• /
• pp.9-16
• /
• 2024

In this study, we delve into the effects of personalization algorithms on the creation of "filter bubbles," which can isolate individuals intellectually by reinforcing their pre-existing biases, particularly through personalized Google searches. By setting up accounts with distinct ideological learnings-progressive and conservative-and employing deep neural networks to simulate user interactions, we quantitatively confirmed the existence of filter bubbles. Our investigation extends to the deployment of an LSTM model designed to assess political orientation in text, enabling us to bias accounts deliberately and monitor their increasing ideological inclinations. We observed politically biased search results appearing over time in searches through biased accounts. Additionally, the political bias of the accounts continued to increase. These results provide numerical evidence for the existence of filter bubbles and demonstrate that these bubbles exert a greater influence on search results over time. Moreover, we explored potential solutions to mitigate the influence of filter bubbles, proposing methods to promote a more diverse and inclusive information ecosystem. Our findings underscore the significance of filter bubbles in shaping users' access to information and highlight the urgency of addressing this issue to prevent further political polarization and media habit entrenchment. Through this research, we contribute to a broader understanding of the challenges posed by personalized digital environments and offer insights into strategies that can help alleviate the risks of intellectual isolation caused by filter bubbles.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.104-110
• /
• 2023

In the user-centered design paradigm, information systems are created entirely tailored to the users who will use them. When the functions of a complex system meet a simple user interface, users can use the system conveniently. While web personalization services are emerging as a major trend in portal services, portal companies are competing for a second service, such as introducing 'integrated communication platforms'. Until now, the role of the portal has been content and search, but this time, the goal is to create and provide the personalized services that users want through a single platform. Personalization service is a login-based cloud computing service. It has the characteristic of being able to enjoy the same experience at any time in any space with internet access. Personalized web services like this have the advantage of attracting highly loyal users, making them a new service trend that portal companies are paying attention to. Researchers spend a lot of time collecting research-related information by accessing multiple information sources. There is a need to automatically build interest information profiles for each researcher based on personal presentation materials (papers, research projects, patents). There is a need to provide an advanced customized information service that regularly provides the latest information matched with various information sources. Continuous modification and supplementation of each researcher's information profile of interest is the most important factor in increasing suitability when searching for information. As researchers' interest in unstructured information such as technology markets and research trends is gradually increasing from standardized academic information such as patents, it is necessary to expand information sources such as cutting-edge technology markets and research trends. Through this, it is possible to shorten the time required to search and obtain the latest information for research purposes. The interest information profile for each researcher that has already been established can be used in the future to determine the degree of relationship between researchers and to build a database. If this customized information service continues to be provided, it will be useful for research activities.

• Journal of Computational Design and Engineering
• /
• 제1권3호
• /
• pp.161-172
• /
• 2014

This paper presents three different search engines for the detection of CAD-parts in large databases. The analysis of the contained information is performed by the export of the data that is stored in the structure trees of the CAD-models. A preparation program generates one XML-file for every model, which in addition to including the data of the structure tree, also owns certain physical properties of each part. The first search engine is specializes in the discovery of standard parts, like screws or washers. The second program uses certain user input as search parameters, and therefore has the ability to perform personalized queries. The third one compares one given reference part with all parts in the database, and locates files that are identical, or similar to, the reference part. All approaches run automatically, and have the analysis of the structure tree in common. Files constructed with CATIA V5, and search engines written with Python have been used for the implementation. The paper also includes a short comparison of the advantages and disadvantages of each program, as well as a performance test.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권6호
• /
• 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.

• 경영과정보연구
• /
• 제9권
• /
• 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.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권2호
• /
• pp.232-236
• /
• 2010

최근의 모바일 단말기 사용자들은 많은 양의 멀티미디어 콘텐츠를 가지고 있다. 또, 인터넷과 컴퓨터 기술의 발전으로 언제 어디서든 모바일 단말기를 가지고 이를 이용할 수 있다. 하지만 현재 파일 시스템 기반의 방식에서 사용자는 원하는 멀티미디어 콘텐츠를 찾고 관리하기 위해 많은 시간을 소비해야 한다. 특히, 모바일 단말기의 작고 불편한 인터페이스는 멀티미디어 콘텐츠 검색 및 관리를 더욱 힘들게 한다. 따라서 다량의 멀티미디어 콘텐츠를 보다 효과적으로 사용하기 위한 지능형 멀티미디어 콘텐츠 관리 기법이 필요하다. 본 논문에서는 개인화된 모바일 멀티미디어 콘텐츠를 제공하기 위해서 사용자의 상황과 심리를 이용한 방법과 이를 적용한 개인화된 모바일 멀티미디어 콘텐츠 제공 시스템(Personalized Mobile Multimedia Contents Provider)을 제안한다.

• 한국시뮬레이션학회논문지
• /
• 제19권4호
• /
• pp.59-66
• /
• 2010

이 논문에서는 온톨로지로 표현한 트랜잭션으로부터 연관 규칙을 생성하고 이를 기반으로 추론을 수행하여 개인화 의류 추천을 제공하는 시스템을 제안한다. Onto-Apriori 알고리즘을 이용한 연관 규칙 생성은 유행에 따른 구매성향 변동을 능동적으로 분석할 수 있다. 생성된 규칙은 온톨로지에 메타 노드로 표현하고 이를 기반으로 추론함으로써 사용자의 질의에 맞는 추천 항목을 찾아낼 수 있다. 시스템을 평가하기 위하여 추론 소요시간과 추천 정확도 2가지 요소를 기준으로 시뮬레이션을 수행하여 유효성을 증명하였다.

• 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.