• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.623-631
• /
• 2020

In the era of COVID-19 global pandemic, e-learning has become new standards and daily life in the name of 'new normal'. This study developed dialogue e-learning contents as opposed to monologue e-learning which is unidirectional and instructor centered and conducted qualitative user experience evaluation of dialogue e-learning contents. A total number of 20 adult students participated and were individually interviewed. Qualitative data analysis was performed. The findings include students' positive perceptions of dialogue e-learning contents such as empathy for various ideas and new format. With regard to personal preference, 55% of participants preferred dialogue e-learning contents because it enables them to focus and share real experiences. Meanwhile, in terms of learning effects, 60% participants selected monologue e-learning contents and mentioned adequate explanations of concepts and explicit information delivery. Based on the results, suggestions on the design and development of dialogue e-learning contents were presented.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.572-573
• /
• 2022

본 논문은 메타버스 환경에서 문제가 대두되고있는 AI 윤리(ethic)를 배경으로 인터랙션을 통해 사람들의 온라인과 오프라인의 결정요소에 직접적으로 영향을 미치는 대화형 AI가 어떻게 윤리적으로 진화될 수 있을지에 대한 공학적 솔루션을 UX 관점으로 찾아보는 기술 전략 연구라고 할 수 있다. 연구의 가설은 AI 의 머신러닝과정에 개별 사용자 그룹의 경험데이터가 반드시 포함되고 고려되어야 AI 는 오류값을 줄이고 윤리적으로 대응할 수 있다는 전제이다. 이를 위하여 본 논문은 기존의 머신러닝과 대화형 AI 의 UX 관점의 다이아로그 플로우 등을 연구 분석하고 사용자 데이터들을 실험하여 메타버스 서비스 환경에서의 기존에 논의되고 있는 컨택스트기반의 AI 머신러닝 과정에 사용자의 정성적 경험데이터를 추가한 윤리적 UX 접근 개념 모델을 제안 하였다. 아직은 개념모델 단계이고 시스템에서는 지금까지 다르지 않았던 비정량적인 감정과 융합적경험을 어떻게 문화적으로 코드화 하고 시스템적인 랭귀지와 연결시킬 수 있을지에 대한사용자 연구가 후속연구로 진행될 예정이다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.447-451
• /
• 2022

본 논문에서는 사용자가 대화 텍스트 방식의 입력을 주었을 때 이를 키워드 중심으로 변환하여 이미지를 생성해내는 방식을 제안한다. 대화 텍스트란 채팅 등에서 주로 사용하는 형식의 구어체를 말하며 이러한 텍스트 형식은 텍스트 기반 이미지 생성 모델이 적절한 아웃풋 이미지를 생성하기 어렵게 만든다. 이를 해결하기 위해 대화 텍스트를 키워드 중심 텍스트로 바꾸어 텍스트 기반 이미지 생성 모델의 입력으로 변환하는 과정이 이미지 생성의 질을 높이는 좋은 방안이 될 수 있는데 이러한 태스크에 적합한 학습 데이터는 충분하지 않다. 본 논문에서는 이러한 문제를 다루기 위한 하나의 방안으로 사전학습된 초대형 언어모델인 KoGPT 모델을 활용하며, 퓨샷 러닝을 통해 적은 양의 직접 제작한 데이터만을 학습시켜 대화 텍스트 기반의 이미지 생성을 구현하는 방법을 제안한다.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.151-157
• /
• 2009

A lot of E-Learning system is supplying the existent item difficulty based learning information to learner. And learner is doing learning contents according to the fixed learning course. It is difficult for learner to get efficient learning effect. Because learner has to belong to fixed item difficulty and learning course even thought learner has different degree that understand studying in learning course. This research proposed the learner adaptive E-learning system that is able to control the item difficulty and learning course to analyze the understanding degree of learner in learning course. In this result, learner is able to improve learning effect to get rid of fixed learning course using bi-directed learning such as off-line learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.11
• /
• pp.339-344
• /
• 2020

During COVID-19, education industry is organizing the concept of 'Edutech', which has evolved one step further from the existing e-Learning, by introducing various intelligent information technologues based on the core technology of the 4th industrial revolution and spreading it through diverse contents. Meanwhile, each industries are creating new industries by applying new technology to existing businesses and ask for needs of cultivating human resources who understand the existing traditional ICT technology and industrial business which can solve a newly rising problems. However, it is difficult to build contents for cultivating such human resources with the existing e-learning of transferring knowledge by one-way or some two-way commnication system which has established some interactive conversational system. Accordingly, this study conducted a research on a cooperative e-learning system that enables educators to communicate with learners in real time and allows problem-solving education based on the existing two-way communication system. As a result, frame for contents and prototype was developedp and artially applied to the actual class and conducted an efficiency analysis, which resulted in the validation of being applied to the actual class as a simulation-based cooperative content.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.694-702
• /
• 2022

This paper is the UX-based technology strategy research which is a solution to how conversational AI can be ethically evolved in the Metaverse environment. Since conversational AI influences people's on-offline decision-making factors through interaction with people, the Metaverse AI ethics must be reflected. In the machine learning process of conversational AI, cultural codes along with user's personal experience data must be included and considered to reduce the error value of user experience. Through this, the super-personalized Metaverse service can evolve ethically with social values. With above hypothesis as a result of the study, a conceptual model of a forward-looking perspective was developed and proposed by adding user experience data to the machine learning (ML) process for context-based interactive AI in the Metaverse service environment.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.4
• /
• pp.1-9
• /
• 2021

Segmenting the compartments of neurons, such as axons, dendrites, and cell bodies, is helpful in the analysis of neurological phenomena. Recently, there have been several studies to segment the compartments through deep learning. However, this approach has the potential to include errors in the results due to noise in data and differences between training data and actual data. Therefore, in order to use these for actual analysis, it is essential to proofread the results. The proofreading process requires a lot of effort and time because an expert must perform it manually. We propose an interactive neuron structure proofreading method that can more easily correct errors in the segmentation results of a deep learning. This method proofread the neuron structure based on the characteristics of the neuron with structural consistency, so that a high-accuracy proofreading result can be obtained with less interaction.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1092-1093
• /
• 2023

본 논문에서는 한국무역협회(KITA)의 오픈상담 자료들을 바탕으로, 딥러닝 기술을 이용하여 구현한 해상물류 대화형 챗봇 ShipMate를 제안한다. 챗봇 ShipMate는 KoGPT2를 활용한 답변과 Doc2Vec 기반의 유사 상담사례 추천이 가능하고, 무역상담을 시간제약 없이 진행할 수 있기 때문에, 기존 해상물류 서비스의 접근성을 한층 더 높일 수 있으며 이를 실험을 통해 입증하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.23-30
• /
• 2024

In this paper, we propose a deep learning-based personalized senior care service application. The proposed application uses Speech to Text technology to convert the user's speech into text and uses it as input to Autogen, an interactive multi-agent large-scale language model developed by Microsoft, for user convenience. Autogen uses data from previous conversations between the senior and ChatBot to understand the other user's intent and respond to the response, and then uses a back-end agent to create a wish list, a shared calendar, and a greeting message with the other user's voice through a deep learning model for voice cloning. Additionally, the application can perform home IoT services with SKT's AI speaker (NUGU). The proposed application is expected to contribute to future AI-based senior care technology.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.628-630
• /
• 2018

인공지능에 대한 연구가 최근 이슈가 되면서, 딥러닝 기술의 비약적인 발전 덕분에 대화형 에이전트가 인터페이스의 역할을 하고 있다. 이 중에서 최근 여러 대학에서 서비스로 지원하는 챗봇 시스템의 문제점에 대하여 개선된 시스템을 제안하고, 이를 구현하여 실험을 통해 연구하고자 한다. 기존 챗봇 시스템이 가진 문제점을 보완한 시스템은 서비스 사용자가 질의하는 의도에 더 알맞은 응답을 제공하여 서비스 사용자의 불편함을 최소화하고, 사용성과 편의성을 최대화 하는 것을 목적으로 한다.