• Archives of design research
• /
• v.20 no.3 s.71
• /
• pp.129-140
• /
• 2007

This study attempts to investigate the personalized schemes of interface for the interactive TV sonics enhancing the satisfaction of users from the standpoints of the user and to suggest designing guidelines. In the preface, firstly, the purpose as well as structure of the study were described, the characteristics of the interactive TV and the personalization were defined. Also, it was attempted to understand the development directions of the basic media for services. In addition, the data and elements that became the ground for this study were arranged, including the elements for designing interface, the appraisal method of usability to evaluate the requirements of users, etc. Then, the interfaces of "SkyTouch", an interactive TV sonics by Skylife having the number of users reaching one million at the moment, that is the representative runner in the interactive TV, were analyzed. Then the needs central to the navigation structure and layout for the convenience of users through the evaluation of usability were examined and arranged. In addition, the designing directions of personalized interfaces were studied in the interactive TV by analyzing the web portal sites which were being carried out prior to the personalized services. Based on the data investigated and analyzed previously, the guidelines for the interface design for the personalization of the interactive TV were suggested by classifying the navigation structure and layout, and the personalized interface design was proposed according to the suggested guidelines by applying them directly to "SkyTouch" that is currently carrying out the interactive sonics although it provides limited services in an independent style.

• Journal of the Korean Society for information Management
• /
• v.22 no.4 s.58
• /
• pp.197-220
• /
• 2005

This research aims to explore faculty research support systems in university libraries, assess their service performance for faculty research, and suggest the need and roadmap for new service development. We perform in-depth analyses of not only the current university library evaluation criteria as part of the overall university evaluation criteria, but also ten university libraries in the United States and two university libraries in Korea. Thorough benchmarking studies reveal the problems of the current university library evaluation criteria in its advances and limitations of current faculty support service systems. Especially this research suggests to develop a one-stop service execution wheel for the roadmap for the faculty research support system which is based on customer relationship management(CRM) for one-to-one, mass-personalized services to the faculty.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1304-1310
• /
• 2008

The purpose of this study is to propose the system architecture of intelligent ubiquitous house which is able to team the human behavior by itself and to predict the forthcoming situation, and to provide the customized and personalized service based on human behavior. The suggestions for advanced intelligent ubiquitous house are as follows; 1) Service should be combined with dwellers' behavior pattern, location moving pattern and service pattern in order to provide the personalized and customized service. 2) The system should be equipped with 4 components such as Agent, Database, Working Memory, and Log Data. Especially. This proposed system architecture of advanced ubiquitous house, which are equipped with these 4 components, will be the basis of providing customized service to every dwellers by learning dwellers' behavior pattern, accumulating dwellers' information, and recognizing dweller's lift style as time goes by.

• 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.

• Journal of Internet Technology
• /
• v.21 no.3
• /
• pp.733-741
• /
• 2020

Consistency of web service composition is a challenge for developing business applications. As web services are naturally changeable, the way to deliver consistent web services composition over unreliable web services could pose a significant problem. We propose a framework for semantic web services in healthcare domain that automatically performs web service discovery, composition and quality of service assurance, and, performs error handling through the replacement policy and fault-tolerant composition of web services that mixes both exception managing and transaction approaches. The framework enables the development of personalized healthcare systems.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.206-206
• /
• 2006

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.449-451
• /
• 2000

본 논문에서는 분산 이기종 시스템들로 구성되는 다수의 독립된 인터넷 상점들과 이들을 연합하여 공동 포인트 적립, 공동 상품 검색 등의 통합된 서비스를 제공하는 인터넷 쇼핑몰 허브 싸이트에서 고객 개개인에게 맞춤 상품 정보 및 광고를 제공하기 위한 방법을 제시한다.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.29-56
• /
• 2021

Recently, various types of products have been launched with the rapid growth of the e-commerce market. As a result, many users face information overload problems, which is time-consuming in the purchasing decision-making process. Therefore, the importance of a personalized recommendation service that can provide customized products and services to users is emerging. For example, global companies such as Netflix, Amazon, and Google have introduced personalized recommendation services to support users' purchasing decisions. Accordingly, the user's information search cost can reduce which can positively affect the company's sales increase. The existing personalized recommendation service research applied Collaborative Filtering (CF) technique predicts user preference mainly use quantified information. However, the recommendation performance may have decreased if only use quantitative information. To improve the problems of such existing studies, many studies using reviews to enhance recommendation performance. However, reviews contain factors that hinder purchasing decisions, such as advertising content, false comments, meaningless or irrelevant content. When providing recommendation service uses a review that includes these factors can lead to decrease recommendation performance. Therefore, we proposed a novel recommendation methodology through CNN-based review usefulness score prediction to improve these problems. The results show that the proposed methodology has better prediction performance than the recommendation method considering all existing preference ratings. In addition, the results suggest that can enhance the performance of traditional CF when the information on review usefulness reflects in the personalized recommendation service.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.1
• /
• pp.117-127
• /
• 2005

Numerous internet pop advertisement are being provided according to the rapid development of e-commercial and a rise in users. However, it has not been based on analysis of users' inclination but just one-sided providing. With that reason, many web-site provider want to advertis e more efficient and distinguished Internet-advertisement as analyzing Server's Log accessed. In this thesis, we have studied and tested relatively simply adoption system to provide personalized advertisement service. In order to influence personal disposition to system as the most effective way, it first of all uses History files as source data and after refining it, it can search not only visitors' inclination but also the others' visit-list on the other server. As a result of it, it can make advertisement more reality and activity.

• The Journal of the Korea Contents Association
• /
• v.11 no.7
• /
• pp.219-224
• /
• 2011

To improve medical service and customers' satisfaction by reducing actual waiting time for medical inspection by personalized examination guidance contents (PEGC) linked with medical information system (MIS). The suggested PEGC was completed with preparing transmission for data and PEGC by using transmission control protocol internet protocol (TCP/IP) which can be built up creditable data transmission service. When patient signal event appeared in MIS while the communication was in standby, the ID and data of the customer were shown as text and image on monitors in waiting room. Guiding inspections, steps of examination, and undressing information extracted from the PEGC was also shown to the appropriate patient. After installation of the suggested PEGC, we rechecked satisfaction rates of 60 customers who visited the hospital with a same method as initial survey. The results of this study suggest that 3.6 point of waiting time satisfaction index were improved, after installation of the suggested PEGC, as 4.6 point.