• Title/Summary/Keyword: 온라인 대화

Search Result 98, Processing Time 0.024 seconds

The Effect of Preceding Utterance on the User Experience in the Voice Agent Interactions - Focus on the Conversational Types in the Smart Home Context - (음성 에이전트 상호작용에서 선행 발화가 사용자 경험에 미치는 영향 - 스마트홈 맥락에서 대화 유형 조건을 중심으로 -)

  • Kang, Yeseul;Na, Gyounghwa;Choi, Junho
    • The Journal of the Convergence on Culture Technology
    • /
    • v.7 no.1
    • /
    • pp.620-631
    • /
    • 2021
  • The study aim to test the effect of voice agent's preceding utterance type on the user experience in the smart home contexts by conversation types. Based on two types of conversation (task-oriented vs. relationship-oriented conversations) and two types of utterance (preceding vs. response utterances), four different scenarios were designed for experimental study. A total of 62 participants were divided into two groups by utterance type, and exposed to two scenarios of the conversation types. Likeability, psychological reactance, and perceived intelligence were measured for the user experience of conversational agent. The result showed main effects of likeability in task-oriented conversations, and of psychological reactance in preceding utterances. The interaction effect demonstrated that preceding conversation improved the likeabilitty and perceived intelligence in the task-oriented conversations.

Implementation of Interactive Online Auction System (상호대화를 통한 온라인 경매 시스템 구현)

  • 김종완;백영욱
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2000.11a
    • /
    • pp.405-408
    • /
    • 2000
  • 기존에는 기계설계 시 각종 부품에 대한 정보를 카탈로그나 인터넷의 홈페이지를 통해서 얻을 수 있었다. 본 논문에서는 인터넷을 통하여 공급자와 구매자가 필요한 형상의 부품을 상호 대화 방식으로 경매를 통하여 구매하는 시스템을 구현하였다. 제안된 시스템에서 구매자는 제품에 대한 사용방법과 여러 가지 특징을 알 수 있으며, 공급자는 자신의 회사제품의 형상을 구매자에게 보여 줄 수 있다. 또한 구매자는 다수의 공급자가 공급하는 제품의 형상과 일부분이 상이한 제품에 대하여서도 제품에 대한 가격과 납기일 등 상세한 정보를 보면서 제품을 구매 할 수 있고, 여러 제조회사와의 상담시간, 설계시간 및 원가계산 시간을 단축시킬 수 있는 온라인 시스템을 제시한다. 제시된 시스템은 Linux 6.2/윈도우 환경하에서 Java언어를 이용하여 구현하였다.

  • PDF

The Effect of Interjection in Conversational Interaction with the AI Agent: In the Context of Self-Driving Car (인공지능 에이전트 대화형 인터랙션에서의 감탄사 효과: 자율주행 맥락에서)

  • Lee, Sooji;Seo, Jeeyoon;Choi, Junho
    • The Journal of the Convergence on Culture Technology
    • /
    • v.8 no.1
    • /
    • pp.551-563
    • /
    • 2022
  • This study aims to identify the effect on the user experiences when the embodied agent in a self-driving car interacts with emotional expressions by using 'interjection'. An experimental study was designed with two conditions: the inclusion of injections in the agent's conversation feedbacks (with interjections vs. without interjections) and the type of conversation (task-oriented conversation vs. social-oriented conversation). The online experiment was conducted with the four video clips of conversation scenario treatments and measured intimacy, likability, trust, social presence, perceived anthropomorphism, and future intention to use. The result showed that when the agent used interjection, the main effect on social presence was found in both conversation types. When the agent did not use interjection in the task-oriented conversation, trust and future intention to use were higher than when the agent talked with emotional expressions. In the context of the conversation with the AI agent in a self-driving car, we found only the effect of adding emotional expression by using interjection on the enhancing social presence, but no effect on the other user experience factors.

Incremental Early Text Classification system for Early Risk Detection (조기 위험 검출을 위한 점진적 조기 텍스트 분류 시스템)

  • Bae, Sohyeun;Lee, Geun-Bae
    • Annual Conference on Human and Language Technology
    • /
    • 2021.10a
    • /
    • pp.91-96
    • /
    • 2021
  • 조기 위험 검출은 실시간으로 들어오는 텍스트를 순차적으로 처리하면서 해당 대화에 위험이 있는지 조기에 분류하는 작업으로, 정확도 저하를 최소화하는 동시에 가능한 한 빨리 대화를 분류하는 것을 목적으로 한다. 이러한, 조기 위험 검출은 온라인 그루밍 검출, 보이스 피싱 검출과 같은 다양한 영역에 활용될 수 있다. 이에, 본 논문에서는 조기 위험 검출 문제를 정의하고, 이를 평가할 수 있는 데이터 셋과 Latency F1 평가 지표를 소개한다. 또한, 점진적 문장 분류 모듈과 위험 검출 결정 모듈로 구성된 점진적 조기 텍스트 분류 시스템을 제안한다. 점진적 문장 분류 모듈은 이전 문장들에 대한 메모리 벡터와 현재 문장 벡터를 통해 현재까지의 대화를 분류한다. 위험 검출 결정 모듈은 softmax 분류 점수와 강화학습을 기반으로 하여 Read 또는 Stop 판단을 내린다. 결정 모듈이 Stop 판단을 내리면, 현재까지의 대화에 대한 분류 결과를 전체 대화의 분류 결과로 간주하고 작업을 종료한다. 해당 시스템은 micro F1과 Latency F1 지표 각각에서 0.9684와 0.8918로 높은 검출 정확성 및 검출 신속성을 달성하였다.

  • PDF

Trust and facial information in online negotiation (온라인 협상에서 얼굴 정보에 따른 신뢰감 비교)

  • Ji, Jae-Yeong;Han, Gwang-Hui
    • Proceedings of the Korean Society for Emotion and Sensibility Conference
    • /
    • 2007.05a
    • /
    • pp.153-156
    • /
    • 2007
  • 본 연구는 온라인으로 이루어지는 협상에서 얼굴정보가 협상의 신뢰 수준에 영향을 주는지 보고자 한다. 협상의 진행이 실시간 문자 대화(Synchronous text communication) 또는 음성(Voice)으로 이루어지는 조건과 얼굴 정보가 추가된 조건을 비교한 결과, 얼굴 정보가 추가되었을 때 신뢰의 수준이 높게 나타났다.

  • PDF

A Virtual World Communication Framework Using Avatar Spatial Information (아바타의 공간 정보를 이용한 가상세계 커뮤니케이션 프레임워크)

  • Park, Soo-Hyun;Ji, Seung-Hyun;Ryu, Dong-Sung;Cho, Hwan-Gue
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.35 no.12
    • /
    • pp.552-559
    • /
    • 2008
  • Computing technologies are extending the means by which people communicate. Especially, virtual worlds have recently become successful, due to rapidly improving Information Technologies. Chat is a crucial function in current virtual worlds. We need a realistic and efficient communication framework for multi-agents participating in a virtual world. The main contribution of our work is twofold. First, we propose a realistic communication framework which enables 'Complete Talk' and 'Partial Talk' in terms of spatial relationships between avatar agents. Second, our system reconstructs a dialogue graph which maintains all transcripts in the form of directed graphs with temporal(dialogue sequences) and spatial information(physical positions) about communicating agents.

Action Research to Improve Experimental Activities and Interactions in Online Science Class (온라인 과학 수업에서 실험 활동과 상호작용의 개선을 위한 실행연구)

  • Noh, Ja-Heon;Son, Jun-Ho;Kim, Jong-Hee
    • Journal of the Korean Society of Earth Science Education
    • /
    • v.14 no.2
    • /
    • pp.159-172
    • /
    • 2021
  • This study is an action study that plans a instructional strategy for improving experimental activities and interactions in online science classes and suggests improvement plans based on the results. To this end, from July 7 to September 9, 2020, the 'Earth and the Moon' unit class was conducted for 20 6th grade elementary school students located in G Metropolitan City. For the class, smart devices and alternative experiments were planned in the experimental activity category, and an online chat room and Q&A strategy were planned in the interaction category. Among the collected data, class activity papers, homework assignments, reflection journals, online conversation contents, and Q&A contents were input into the matrix and analyzed by writing analytical texts. As a result of the implementation, smart devices and alternative experiments provided opportunities for exploration, but there was a risk of misconception formation and hindered experimental activities. The online chat room and Q&A provided opportunities for communication and examination and feedback on scientific concepts. Through this action study, the researcher was able to reflect on the class while writing class reflection notes, and suggested the role of smart devices in terms of the effectiveness and efficiency of science classes.

Emotion Classification System for Chatting Data (채팅 데이터의 기분 분류 시스템)

  • Yoon, Young-Mi;Lee, Young-Ho
    • Journal of the Korea Society of Computer and Information
    • /
    • v.14 no.5
    • /
    • pp.11-17
    • /
    • 2009
  • It's a trend that the proportion of using an internet messenger among on-line communication methods is getting increased. However, there are not many applications which efficiently utilize these messenger communication data. Messenger communication data have specific characteristics that reflect the user's linguistic habits. The linguistic habits are revealed through frequently used words and emoticons, and user's emotions can be grasped by these. This paper proposes the method that efficiently classifies the emotions of a messenger user using frequently used words or symbols. The emotion classifier from repeated experiments achieves high accuracy of more than 95%.

유행몰입도에 따른 아바타 꾸미기에 관한 연구

  • 이현정;김미영;이민경
    • Proceedings of the Costume Culture Conference
    • /
    • 2004.04a
    • /
    • pp.28-30
    • /
    • 2004
  • 정보 기술의 발전으로 인해 서로 다른 곳에 있는 사람들이 인터넷을 통하여 하나의 가상 공간을 공유할 수 있게 되었고, 인터넷의 발달은 사람들이 가상공간에서 머무는 시간을 길어지게 하였다. 사람들은 오프라인의 편지보다는 온라인의 메일을 더 선호하게 되었으며, 얼굴을 마주하고 앉아 대화를 나누는 것보다 스크린을 마주하고 온라인에서 채팅을 하는 것이 자연스러운 생활의 일부가 되었다. (중략)

  • PDF

Analysis of the Social Communication on Online Social Media -Comparison of Bridging and Bonding Social Capital- (온라인 사회관계 유형에 따른 사회적 소통 차이 연구 -연결형과 결속형 관계를 중심으로-)

  • Kim, Mi-Sun;Kim, Suk
    • The Journal of the Korea Contents Association
    • /
    • v.15 no.8
    • /
    • pp.448-459
    • /
    • 2015
  • This study discusses on the social communication phenomenon on online social media by comparative analysis among bridging and bonding social capital. It examined the social media usage, social communication recognition, social communication satisfaction and intent social participation by exploring social capital which are the main influential factors of online social media. The online survey was conducted on 500 adults over the age of 20. As a result, in a quantitative respect a high rate of online media usage was observed all social capital. On the other hand, in a qualitative aspects 'understand' and 'trust' was came out in the bonding capital, but 'agreement' was not observed in all social capital. Also the influential factors of intent social participation were different in the social capital. The bonding was affected by 'understanding' but the bridging was affected by 'trust' and 'agreement'. Therefore, it was able to discuss that the understanding of online social media user and social communication characteristic must be preceded and the activator policy of social communication must consider the different features of online social capital.