• Journal of Intelligence and Information Systems
• /
• v.15 no.1
• /
• pp.31-50
• /
• 2009

As the collected information which is static or dynamic is infinite in ubiquitous computing environments, information overload and invasion of privacy have been pressing issues in the recommendation service. In this study, we propose a recommendation service procedure through P2P, The P2P helps customer to obtain effective and secure product information because of communication among customers who have the similar preference about the products without connection to server. To evaluate the performance of the proposed recommendation service, we utilized real transaction and product data of the Korean mobile company which service character images. We developed a prototype recommender system and demonstrated that the proposed recommendation service makes an effect on recommending product in the ubiquitous environments. We expect that the information overload and invasion of privacy will be solved by the proposed recommendation procedure in ubiquitous environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.99-105
• /
• 2021

In addition to the OTT video production service represented by Nexflix and YouTube, a personalized recommendation system for content with artificial intelligence has become common. YouTube's personalized recommendation service system consists of two neural networks, one neural network consisting of a recommendation candidate generation model and the other consisting of a ranking network. Netflix's video recommendation system consists of two data classification systems, divided into content-based filtering and collaborative filtering. As the online platform-led content production is activated by the Corona Pandemic, the field of virtual influencers using artificial intelligence is emerging. Virtual influencers are produced with GAN (Generative Adversarial Networks) artificial intelligence, and are unsupervised learning algorithms in which two opposing systems compete with each other. This study also researched the possibility of developing AI platform based on individual recommendation and virtual influencer (metabus) as a core content of OTT in the future.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.587-590
• /
• 2016

최근 통신 기술의 발달로 온라인을 통한 대규모 콘텐츠의 유통이 가능해졌으나, 사용자들은 수많은 콘텐츠 사이에서 원하는 정보를 찾는 시간이 단축되는 것을 원했다. 이로 인해 다양한 분야에서 개인화된 콘텐츠를 추천해주는 추천 시스템(recommendation system)에 대한 요구가 점차 높아졌다. 그럼에도 불구하고 시니어를 위한 추천 시스템에 대한 연구는 매우 부족하다. 또한, 시니어 세대의 변화에 따라 시니어 관련 콘텐츠 연구도 다양하게 진행되고 있으나, 스마트 기기 및 서비스가 젊은 층에 친화적으로 개발됨으로써 시니어 층의 접근성을 감소시키고 있다. 이에 본 연구에서는 다양한 신체적 변화를 겪는 시니어 세대 위해 추천 시스템에서 인지반응 데이터를 이용하여 콘텐츠를 시청하기 적합한 환경을 제공함과 동시에 활동 이력을 중심으로 개인화 추천 시스템을 설계하여 시니어 사용자들의 개념 변화(concept drift) 문제로 사용자가 원하지 않는 콘텐츠를 추천받을 가능성을 줄일 수 있도록 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.360-361
• /
• 2017

본 논문에서는 웹 또는 앱을 통해 제공되는 무한한 정보 중에서 사용자들에게 필요한 건강 관련 정보를 맞춤형으로 제공하기 위해서 사용자 맞춤형 건강 콘텐츠 추천 알고리즘을 설계한다. 그리하여 집단 지성 알고리즘과 의사 결정 나무를 활용하여 사용자 맞춤형 건강 콘텐츠 추천 서비스를 이용하는 사용자들의 자가건강진단 정보를 활용하여 웹상의 URL 정보를 토대로 맞춤형 정보를 분석, 추천하는 알고리즘의 유용성을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1129-1131
• /
• 2013

온라인 상에서 불특정 타인과 관계를 맺을 수 있는 서비스로 소셜 네트워크 서비스(Social Network Service : SNS)가 새롭게 떠오르고 있다. 1990년대에 등장한 SNS는 최근에는 스마트폰을 이용한 모바일 서비스로 인해 이용자의 수가 급격히 늘어나고 있다. SNS에서는 '친구 찾기' 라는 서비스를 제공하는데, 이는 이용자의 개인정보를 분석하여 이용하여 친구를 찾아주는 서비스이다. 기존의 '친구 찾기' 서비스는 이용자가 제공하는 정보만을 다른 이용자의 정보와 비교하여 친구를 찾았다. 그러나 이용자가 제공하는 정보는 한정적이기 때문에 비교할 수 있는 정보의 양도 한정되어 찾을 수 있는 친구의 수에도 한계가 생긴다. 그래서 본 논문에서는 단순한 개인정보 비교를 통한 친구를 찾는 방법이 아닌 이용자가 제공하는 시공간 데이터를 활용하여 추론을 통해 친구를 추천해주는 시스템을 설계하고 구현한다.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.53-60
• /
• 2018

Domestic public e-procurement has been recognized excellence at home and abroad. However, it is difficult for procurement companies to check the related announcements and to grasp the status of procurement announcements at a glance. In this paper, we propose an e-Procurement Announcement Analysis Support System using the HDFS, HDFS, Apache Spark, and Collaborative Filtering Technology for procurement announcement recommendation service and procurement announcement and contract trend analysis service for effective e-procurement system. Procurement announcement recommendation service can relieve the procurement company from searching for announcements according to the characteristics and characteristics of the procurement company. The procurement announcement/contract trend analysis service visualizes the procurement announcement/contract information and procures It is implemented so that the analysis information of electronic procurement can be seen at a glance to the company and the demand organization.

• Korea Real Estate Review
• /
• v.24 no.1
• /
• pp.91-104
• /
• 2014

This paper studied condo selection attributes that affected satisfaction, recommendation and revisitation, in particular, investigated gender and age differences. Research target is the group who revisited time-sharing condominium within one year. The paper seeks to understand factors that affect and contribute to customer satisfaction and intentions for reuse. This study model was analyzed by the basic statistical analysis, factor analysis, reliability analysis and multiple analysis, using SPSS 18.0 and AMOS 18.0. We found that 5 condo selection attributes that have significant affect on user satisfaction: facility, service, product, accessibility and expense. Furthermore it was evident that user satisfaction has a significant effect on condo recommendation and intentions of reuse. With regard to sex, for male users expense, accessibility and service had a significant effect on their satisfaction level, while for female users, product was most important. User satisfaction both have a significant effect on recommendation and intentions of reuse but for females this was more evident. Regarding the age, for 20~30 age band, service and product factor had a significant effect on user satisfaction in order, whereas, for the age band of over 40s, expense, product and facility factors were important. User satisfaction of both have a significant effect on recommendation and intentions of reuse. In the meantime user satisfaction of 20~30 age band had a bigger positive significant effect on recommendation and intentions of reuse than the age band over 40s.

• KIISE Transactions on Computing Practices
• /
• v.23 no.1
• /
• pp.65-73
• /
• 2017

Advances in Internet of Things Technology lead to the increasing number of daily-life things that are interconnected over the Internet. Also, several smart services are being developed by utilizing the connected things. Among the daily-life things surrounding user, the mirror can supports broad range of functionality and expandable service as it plays various roles in daily-life. Recently, various smart mirrors have been launched in certain places where people with specific goals and interests meet. However, most mirrors give the user limited information. Therefore, we designed and implemented a smart mirror that can support customized service. The proposed smart mirror utilizes information provided by other existing internet services to give user dynamic information as real_time traffic information, news, schedule, weather, etc. It also supports recommendation service based on user usage information.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.69-86
• /
• 2021

As artificial intelligence technology advances, personalized recommendation systems using big data have attracted huge attention. In the case of beauty products, product preferences are clearly divided depending on customers' skin types and sensitivity along with individual tastes, so it is necessary to provide customized recommendation services based on accumulated customer data. Therefore, by employing deep learning methods, this study proposes a neural network-based recommendation model utilizing both product search history and context information such as gender, skin types and skin worries of customers. The results show that our model with context information outperforms collaborative filtering-based recommender system models using customer search history.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.193-195
• /
• 2021

최근 우리나라에서 재배되고 있는 농작물은 지구 온난화 등의 영향으로 점점 북상하고 있다. 이러한 농업 환경의 변화에 적극적으로 대처하기 위해 본 논문에서는 농업 재배지의 환경 데이터를 수집하고 분석하여 현재 농업 재배지에 최적화된 농작물을 추천할 수 있는 농작물 추천 서비스를 제안한다. 이를 위해 농작물 추천 서비스에 활용하기 위해 농업 환경 데이터의 모니터링과 농작물 데이터 관리 스마트팜 모형을 설계 및 구축한다.