• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.95-99
• /
• 2008

유비쿼터스 환경에서 사용자는 개인용 디바이스를 이용하여 보이지 않는 수많은 자원들과 서로 연결하여 원하는 서비스를 제공 받기를 원한다. 이러한 요구사항을 만족시키기 위하여 유비쿼터스 지능 공간에 존재하는 자원들 사이의 공유가 필요하며 이를 효율적으로 수행하기 위한 연구는 새로운 연구 주제이다. 그러나 동일한 환경이라 할 지라도 각 사용자들의 상황은 서로 다르며 개인적인 성향 역시 다양하다. 그러므로 동일한 공간에서 동일한 서비스를 원하는 사용자들이라 할 지라도 현재의 상황과 사용자 개개인의 개성에 따라 필요로 하는 자원이 다른 것이 현실이다. 그러므로 본 논문에서는 사용자의 상황을 인지하여 맞춤형 자원을 추천하는 시스템을 개발한다. 추천 시스템은 사용자의 상황을 인지하기 위한 방법으로 온톨로지 기반 추론을 수행하고, 개인화 추천 서비스를 제공하기 위하여 규칙들 이용한 규칙 기반 추론 방법을 수행한다.

• The KIPS Transactions:PartD
• /
• v.10D no.7
• /
• pp.1225-1230
• /
• 2003

Many cyber-shopping malls use various commodity recommendation methods. Although the detailed algorithms are not disclosed to the public, they mostly rely on relatively simple and straightforward methods. This paper intends to improve the commodity recommendation by using a multi-stage algorithm which considers factors that are characteristics of the commodity itself, of the consumer group, and of the individual customer. A comparison table is provided which shows whether there is a change in commodity recommendation as we consider more factors about the customer.

• Journal of the Korean Society for information Management
• /
• v.23 no.4 s.62
• /
• pp.179-196
• /
• 2006

This study proposes an expanded model of personalized search service based on community activities on a Korean Web portal. The model is composed of defining subject categories of users, providing personalized search results, and recommending additional subject categories and queries. Several experiments were performed to verify the feasibility and effectiveness of the proposed model. It was found that users' activities on community services provide valuable data for identifying their Interests, and the personalized search service increases users' satisfaction.

• Information Systems Review
• /
• v.25 no.4
• /
• pp.67-87
• /
• 2023

Many online shopping sites now offer personalized recommendation systems to improve consumers' shopping experiences by lowering costs (time, cost, etc.), catering to consumers' tastes, and stimulating consumers' potential shopping needs. So far, domestic and foreign research on the personalized recommendation system has mainly focused on the field of computer science, which is advantageous for obtaining accurate personalized recommendation results for users but difficult to continuously track the users' psychological states or behavioral intentions. This study attempted to investigate the effect of the characteristics of the personalized recommendation system in the online shopping environment on consumer perception and purchase intention for consumers using the Stimulus-Organism-Response (S-O-R) model. The analysis results adopted all hypotheses on the effect of the quality of the personalized recommendation system and information quality on trust and perceived value. Through the empirical results of this study, the factors influencing consumers' use of personalized recommendation system can be identified. In order to increase more purchase, online shopping companies need to understand consumers' tastes and improve the quality of the personalized system by improving the recommendation algorithm thus to provide more information about products.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.28-30
• /
• 2001

현 인터넷상에서 취향에 맞는 항목(상품) 정보를 사용자에게 추천해 주는 개인화 기술은 대부분 특정 사용자와 유사한 선호도를 갖는 다른 사용자들의 특정 항목에 대한 선호도를 바탕으로 항목의 선호도를 추정하는 협력적 추천 기술을 적용하고 있다. 이중 최근접 이웃 방법은 적용하기가 용이한 반면 항목간의 가중치를 고려하지 못함으로써 추천의 정확도가 크게 떨어지는 문제점이 있다. 연관규칙 방법은 다른 항목에 대한 선호도 자료로부터 데이터 마이닝 기법을 적용하여 항목 선호에 대한 연관규칙을 추출하고 그 규칙을 사용하여 어떤 항목의 선호도를 추정한다. 따라서 항목들 간의 중요도가 연관규칙의 지지도나 신뢰도 등으로 나타난다고 할 수 있으나, 단순히 항목들간의 연관관계 즉 표면적인 연관관계에 의하여 선호도를 결정함으로써 항목들간의 어떤 내용적인 공통성 또는 어떤 상위개념에 의한 선호도가 고려되지 않음으로써 역시 정확도가 떨어지는 문제점이 있다. 본 논문에서는 추천의 정확도를 향상시키기 위한 신경망 추천 방법에 대해 분석하고, 내용기반 추천과 협력적 추천을 병합한 신경망 추천 방법을 제안한다. 또한, 다른 협력적 추천 방법과의 비교를 통하여 본 추천 방법의 장점과 성능의 우수함을 보인다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.19-26
• /
• 2011

Users want to receive customized service using users' personal device. To fulfill this requirement, the mobile device has to support a lot of functions. However, the mobile device has limitations such as tiny display screens. To solve this limitation problem and provide customized service to users, this paper proposes the environment to provide services by sharing resources and the method to recommend user-suitable resources among sharable resources. For the resource recommendation, This paper analyzes user's behavior pattern from usage history and proposes the method for recommending customized resources. This paper also shows that the approach is reasonable one for resource recommendation through the satisfaction evaluation.

• Journal of the Korean Society for information Management
• /
• v.23 no.3 s.61
• /
• pp.91-125
• /
• 2006

Recent advancements in information technology and the Internet have caused an explosive increase in the information available and the means to distribute it. However, such information overflow has made the efficient and accurate search of information a difficulty for most users. To solve this problem, an information retrieval and filtering system was developed as an important tool for users. Libraries and information centers have been in the forefront to provide customized services to satisfy the user's information needs under the changing information environment of today. The aim of this study is to propose an efficient information service for libraries and information centers to provide a personalized recommendation system to the user. The proposed method overcomes the weaknesses of existing systems, by providing a personalized hybrid recommendation method for multimedia contents that works in a large-scaled data and user environment. The system based on the proposed hybrid method uses an effective framework to combine Association Rule with Collaborative Filtering Method.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2005.05a
• /
• pp.393-408
• /
• 2005

인터넷의 성장은 고객에게 많은 혜택을 주었지만, 방대한 양의 정보는 오히려 장시간의 상품 탐색과 제품 선택을 어렵게 만들었다. 이에 따라, 정보의 양을 줄여 줄 수 있는 서비스를 고객들은 요구를 하기 시작하였고, 이에 따라 다양한 방법들이 고객에게 제시 되어졌다. 제시되어진 방법 중의 하나가 개인화 추천 시스템이다. 추천 시스템은 고객의 취향과 관심에 적합한 상품을 추천 해 주는 서비스로서 상품 검색 노력을 줄여 주고, 고객의 취향에 적합한 제품을 제시 해 줌으로써 고객충성도 제고에도 많은 도움을 주고 있다. 이러한 추천 시스템에서 가장 많이 사용되어지고 있는 기법은 협업 필터링이다. 협업 필터링은 협업에서도유용한 기법으로 인정을 받았다. 하지만 희박성과 확장성이라는 문제점으로 인해 추천의 정확도가 다소 떨어진다는 것이 단점이다. 본 연구에서는 이러한 단점을 극복할 수 있는 방법으로써 Hybrid 협업 필터링 기법을제시하고, 이를 토대로 추천 기법이 혼합되어진 Hybrid 추천 시스템에 대한 개념을 제시하고자 한다.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.113-127
• /
• 2021

The purpose of this study is to propose a personalized book recommendation system to promote the use of university libraries. In particular, unlike many recommended services that are based on existing users' preferences, this study proposes a method that derive evaluation metrics using individual users' book rental history and tendencies, which can be an effective alternative when users' preferences are not available. This study suggests models using two matrix decomposition methods: Singular Value Decomposition(SVD) and Stochastic Gradient Descent(SGD) that recommend books to users in a way that yields an expected preference score for books that have not yet been read by them. In addition, the model was implemented using a user-based collaborative filtering algorithm by referring to book rental history of other users that have high similarities with the target user. Finally, user evaluation was conducted for the three models using the derived evaluation metrics. Each of the three models recommended five books to users who can either accept or reject the recommendations as the way to evaluate the models.

• Journal of KIISE:Databases
• /
• v.41 no.4
• /
• pp.209-216
• /
• 2014

Various characteristics of social network contents such as real-time, people relationship and big data can help to improve personalized recommender systems. Among them, 'people relationship' is a key factor of recommendation, so many personalized recommender systems utilizing it have been proposed. However, existing researches can not reflect personal tendency and are unable to provide precise recommendations in various domains, because they do not consider intimacy among people. In this paper, to solve these problems, we propose PReAmacy, a Personalized Recommendation Algorithm, considering intimacy among users and various characteristics of social network contents. Our experimental results indicate that not only the precision of PReAmacy is higher than that of existing algorithms, but intimacy is of great importance in PReAmacy.