• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.82-104
• /
• 2023

This study analyzes the effect of users' experiences using AI chatbot services on relationship quality and behavioral intention. For the study, a survey was conducted on users who experienced AI chatbot services, and the research hypothesis was verified by analyzing the final 299 copies of valid data. As a result of the analysis, it was confirmed that satisfaction and trust, which are the relationship quality dimensions of AI chatbot service, were formed in users through the cognitive experience, emotional experience, and relational experience. In addition, it was confirmed that satisfaction and trust have a positive effect on the intention to continue using and recommending AI chatbot services, which correspond to the level of consumers' behavioral intentions, respectively. In addition, in terms of relationship quality, it was significant in all paths of the road of behavior, but in satisfaction, the path coefficient of the road of continuous use of AI chatbot and recommended road was significantly higher than the path coefficient in trust. This study provided a theoretical foundation that the relationship with relationship quality that affects behavioral intention also affects AI chatbot services in the online environment, and it is significant in that it suggests that relationship quality is an important mediating factor in establishing long-term relationships with consumers.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.331-332
• /
• 2007

최근 디지털 TV방송서비스의 보급으로 채널의 수와 그에 따른 프로그램의 수가 많아짐에 따라 시청자는 모든 프로그램의 정보를 미리 알고 있는 것이 힘들어 졌다. 모든 채널과 방송 프로그램을 탐색하고 자신의 취향에 맞는 프로그램을 찾아 보기 어려워진 문제를 해결하고자 영화, 상품 등의 분야에 국한 되었던 추천연구 분야도 TV채널 까지 확대할 필요가 있다. 본 논문에서는 사용자의 TV시청 기록을 분석하여 사용자 프로파일 테이블을 구성하고, 베이시안 네트워크와 시계열 분석 이론을 접목하여 추천엔진을 구현하는 TV채널 추천 엔진을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.334-335
• /
• 2018

최근 수 년간 비디오 콘텐츠 소비 공간이 인터넷으로 확장되며 지능적 비디오 콘텐츠 추천 기술 개발이 진행되어 왔다. 하지만 지능적 비디오 콘텐츠 추천 기술은 사용자의 기호나 업로드된 비디오 콘텐츠의 제목 등을 기반으로 하여 비디오 콘텐츠 클래스에 대한 분석 없이 유사한 비디오 콘텐츠를 탐색하고 추천해주는 기술이 대부분이다. 본 논문에서는 지능적 콘텐츠 추천을 위한 딥러닝 기반 방송 콘텐츠 클래스 분류 시스템을 제안한다. 방송 콘텐츠 내 영상 정보를 이용하여 방송 콘텐츠 클래스를 분류하며 높은 분류 정확도를 보여주는 것을 확인할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.308-309
• /
• 2023

최근 반려동물을 키우는 가구가 점차 증가하고 있다. 본 논문에서는 반려동물 중 수가 가장 많은 반려견을 키우는데 가장 중요한 활동인 산책을 보조하는 어플리케이션을 제인하였다. 본 어플리케이션은 사용자의 위치에 기반해 반려견과의 산책 경로를 추천해준다. 산책은 일반산책, 추천 경로 산책으로 나누어져 있으며 주변에 있는 반려견 관련 장소의 정보도 제공한다. 또한 2km 내에 지나간 반려견의 정보도 알 수 있다. 그리고 리포트 기능을 통해 산책 데이터를 기반으로 지역 내 산책/거리 순위와 총 거리, 시간, 가장 많이 만난 반려견을 알 수 있다. 같은 지역에 등록된 유저들과 SNS 기능을 통해 정보를 주고받을 수 있다. 본 어플리케이션을 통하여 사용자들과 반려견들은 효율적이고 다양한 산책을 경험할 수 있을 것으로 기대된다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.211-221
• /
• 2024

Live streaming commerce has emerged as an innovative e-commerce model. This study, based on the Elaboration Likelihood Model (ELM), aims to explore the impact of Key Opinion Consumers' (KOCs) attributes in live streaming commerce on purchase intentions on short video platforms. A survey was conducted with 411 consumers, and data analysis and hypothesis testing were performed using SPSS 24.0 and AMOS 23.0 software. Research has found that differences in consumers' information processing abilities lead to different pathway selections. Central route factors such as recommendation consistency, product involvement, and professionalism, as well as peripheral route factors such as recommendation timeliness, all have significant positive effects on consumers' purchase intention. However, visual cues in the peripheral route do not have a significant impact. This study aims to provide theoretical support and practical guidance for the development of the live streaming commerce industry, and to help companies adjust their promotion strategies based on differences in consumer information processing, thereby improving purchase conversion rates.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.542-545
• /
• 2010

In this paper, we propose a parking information system which suggests an available parking lot on the shortest path between an entrance and adestination. In order to analyse the change of the parking management efficiency of each model as the number of unavailable parking lots increases from 10% to 99%, we compare the experimental results of three parking information system: an entrance-oriented system, a destination-oriented system, and the proposed system. Also, we compare user's satisfaction according to whether 50 user park their car with the proposed system or not.

• The Journal of the Convergence on Culture Technology
• /
• v.1 no.1
• /
• pp.79-85
• /
• 2015

According to the growing use of the personal GPS in the mobile device recently, the LBS (Local bases service), which processes and refines the GPS information, such as a position-tracking service, a public safety service, a local based information service, has increased steadily. Due to the refraction or reflection of GPS, however, it is impossible to use GPS around or in buildings. Therefore, it is necessary to correct the errors of GPS. We propose the method which corrects the errors of GPS and creates the refined trajectory using intersection region indexing. After analyzing the trajectory, receiving trajectories from many people and identifying the similarity between of trajectories, we will recommend the favorite route and useful information such as restaurant, convenience store, bus station and emergency call service.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.1
• /
• pp.31-40
• /
• 2020

In this study, we developed an algorithm for automatic travel itinerary planning based on expert recommendation. The proposed algorithm generates an itinerary by patterning a number of travel routes based on the automatic itinerary generation method based on the routes recommended by travel experts. To evaluate the proposed algorithm, we generated 30 itinerary for Singapore, Bankok, and Da Nang using both algorithms and analyzed the mean difference of trip distances with t-test and interater reliability of those itineraries. The result shows that the itineraries based on the proposed algorithm is not different from that of VRP(Vehicle routing problem) algorithm and interater reliability is high enough to show that the proposed algorithm is effective enough for real-world usage.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.151-160
• /
• 2022

In this paper, we propose an algorithm that enables near-field delivery at a faster and lowest cost to meet the growing demand for delivery services. The algorithm proposed in this study involves subway passengers (shipper) in logistics movement as delivery sources. At this time, the passenger may select a delivery logistics matching subway route. And from the perspective of the service user, it is possible to select a delivery man whose route matches. At this time, the delivery source recommendation is carried out in a text similarity measurement method that combines TF-IDF&N-gram and BERT. Therefore, unlike the existing delivery system, two-way selection is supported in a man-to-man method between consumers and delivery man. Both cost minimization and delivery period reduction can be guaranteed in that passengers on board are involved in logistics movement. In addition, since special skills are not required in terms of transportation, it is also meaningful in that it can provide opportunities for economic participation to workers whose job positions have been reduced.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.419-430
• /
• 2015

This study is to conceptualize nurses' satisfaction, patient satisfaction about nurses and hospital, and patients' revisit and recommendation intention as linear structural equation model, and then, identify the significance of the path coefficient and goodness of the research model. Data were collected from 2,079 nurses and 6,776 patients in 5 university hospitals. The results were as follows: The research model was generally found to be good in terms of goodness of fit. The significance of the path coefficients are as follows. 1)A nurse's satisfaction has great influence on a patient's satisfaction about nurses, 2)A patient's satisfaction about nurses has influence on patient's satisfaction about the hospital, 3)A patient's satisfaction about the hospital has great influence on patient's revisit intention, 4)A patient's satisfaction about the hospital has great influence on patient's recommendation intention. These results will provide basic data for the hospital managers practicing customer satisfaction strategies in their health care marketing.