• 한국빅데이터학회지
• /
• 제7권2호
• /
• pp.91-102
• /
• 2022

인공지능이 발전하면서 AI 챗봇 시스템의 활용이 활발히 이루어지고 있다. 그 예로 공공기관에서는 민원, 행정 분야에서 업무 보조, 전문지식 서비스 등으로 챗봇 활용 분야가 확대되고 있으며 민간기업은 대화형 고객 응대 서비스 등으로 챗봇을 활용하고 있다. 본 연구에서는 시나리오 기반의 AI 음성 챗봇 시스템을 제안하여 박물관의 운영 비용을 절감하고 관람객에게 양방향성 안내 서비스를 제공하고자 한다. 구현한 음성 챗봇 시스템은 실시간으로 특정 디렉터리를 감시하여 사용자의 음성을 감지하는 감시자 객체와 음성 파일이 생성되면 순차적으로 모델별 추론을 수행하여 AI의 응대 음성을 출력하는 이벤트 핸들러 객체로 구성되며, 스레드와 데크를 활용한 중복 방지 기능을 포함하여 단일 GPU 환경에서 추론 중에 GPU의 연산이 중복되지 않도록 한다.

• Journal of Medicine and Life Science
• /
• 제21권3호
• /
• pp.92-101
• /
• 2024

This study investigated how the use of a conversational artificial intelligence (AI) chatbot improved medical students' patient-centered communication (PCC) skills and how it affected their motivation to learn using innovative interactive tools such as AI chatbots throughout their careers. This study adopted a one-group post-test-only design to investigate the impact of AI chatbot-based learning on medical students' PCC skills, their learning motivation with AI chatbots, and their perception towards the use of AI chatbots in their learning. After a series of classroom activities, including metaverse exploration, AI chatbot-based learning activities, and classroom discussions, 43 medical students completed three surveys that measured their motivation to learn using AI tools for medical education, their perception towards the use of AI chatbots in their learning, and their self-assessment of their PCC skills. Our findings revealed significant correlations among learning motivation, PCC scores, and perception variables. Notably, the perception towards AI chatbot-based learning and AI chatbot learning motivation showed a very strong positive correlation (r=0.72), indicating that motivated students were more likely to perceive chatbots as beneficial educational tools. Additionally, a moderate correlation between motivation and self-assessed PCC skills (r=0.54) indicated that students motivated to use AI chatbots tended to rate their PCC skills more favorably. Similarly, a positive relationship (r=0.68) between students' perceptions of chatbot usage and their self-assessed PCC skills indicated that enhancing students' perceptions of AI tools could lead to better educational outcomes.

• International Journal of Advanced Culture Technology
• /
• 제8권4호
• /
• pp.263-270
• /
• 2020

The growth of the mobile app markets has made it popular among people who recommend relevant information about restaurants. The recommendation service app based on AI Chatbot is that it can efficiently manage time and finances by making it easy for restaurant consumers to easily access the information they want anytime, anywhere. Eating out consumers use smartphone applications for finding restaurants, making reservations, and getting reviews and how to use them. In addition, social attention has recently been focused on the research of AI chatbot. The Chatbot is combined with the mobile messenger platform and enabling various services due to the text-type interactive service. It also helps users to find the services and data that they need information tersely. Applying this to restaurant recommendation services will increase the reliability of the information in providing personal information. In this paper, an artificial intelligence chatbot-based smartphone restaurant recommendation app using personalization information is proposed. The recommendation service app utilizes personalization information such as gender, age, interests, occupation, search records, visit records, wish lists, reviews, and real-time location information. Users can get recommendations for restaurants that fir their purpose through chatting using AI chatbot. Furthermore, it is possible to check real-time information about restaurants, make reservations, and write reviews. The proposed app uses a collaborative filtering recommendation system, and users receive information on dining out using artificial intelligence chatbots. Through chatbots, users can receive customized services using personal information while minimizing time and space limitations.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.9-17
• /
• 2019

As the artificial intelligence technology has developed recently, researches on chatbots that provide information and contents desired by users through an interactive interface have become active. Since chatbots require a variety of natural language processing technology and domain knowledge including typos and slang, it is currently limited to develop chatbots that can carry on daily conversations in a general-purpose domain. In this study, we propose an artificial intelligence chatbot that can provide real-time public traffic information and route information. The proposed chatbot has an advantage that it can understand the intention and requirements of the user through the conversation on the messenger platform without map application.

• 한국IT서비스학회지
• /
• 제23권5호
• /
• pp.59-72
• /
• 2024

Recent advancements in IT technology and infrastructure have led to the widespread application of AI chatbots across various fields, including education, where they have shown effectiveness in improving classroom focus and achievement [1][2]. This study analyzes the importance of quality-in-use for AI chatbots in elementary Korean language learning based on ISO/IEC 25000 Quality-in-use standards, aiming to provide quality evaluation criteria for future educational chatbot development. The research methodology involved a two-tier hierarchy of 5 main characteristics and 13 sub-characteristics of quality-in-use, with surveys conducted among industry professionals and instructors after preliminary investigations. Results showed that situational adaptability, effectiveness, and efficiency were prioritized in the main characteristics. In sub-characteristics, situational completeness, learning accuracy, and flexibility were top-ranked. Instructors emphasized the importance of risk mitigation, reflecting their concern for reducing private education costs and improving learning environments. Industry professionals prioritized completeness in chatbot outputs. These findings suggest that prioritizing instructor-valued features in subject-based learning chatbots can enhance their utility and effectiveness in educational settings. The study also highlights the potential for leveraging differences in quality evaluation priorities between industry professionals and instructors in developing learning chatbots

• 한국전자통신학회논문지
• /
• 제18권3호
• /
• pp.421-426
• /
• 2023

인공지능 융합기술 중 Chatbot은 인공지능 기반의 대화형 시스템이며, 인간과의 상호작용을 제공할 수 있는 시스템을 말한다. 챗봇의 발전으로 NLP, NLU 그리고 NLG로 발전하게 되면서, 챗봇이 재조명되고 있다. 하지만 인공지능 챗봇은 학습한 데이터에 따라 편향된 정보를 제공할 수 있고, 프라이버시 침해, 사이버 보안의 우려를 비롯한 심각한 피해를 줄 수 있으며, 이에 인공지능 기술의 이해와 효과적이고 책임감 있게 사용할 수 있는 능력인 AI 리터러시 함양이 필수적임을 제시했다. 인공지능의 지속적인 진화와 보편화에 따라, AI 리터리시 역시 범위를 확장하며 새로운 영역을 포함하게 될 것이다. 본 연구는 인공지능 기술에 대한 경각심을 일깨우고, 인간의 AI 리터러시 역량 함양을 통해 기술에 매몰되지 않는 인간 존중의 기술 사용을 제안하는데 그 의의가 있다고 하겠다.

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.15-24
• /
• 2023

One of the objectives and aspirations of scientists and engineers ever since the development of computers has been to interact naturally with machines. Hence features of artificial intelligence (AI) like natural language processing and natural language generation were developed. The field of AI that is thought to be expanding the fastest is interactive conversational systems. Numerous businesses have created various Virtual Personal Assistants (VPAs) using these technologies, including Apple's Siri, Amazon's Alexa, and Google Assistant, among others. Even though many chatbots have been introduced through the years to diagnose or treat psychological disorders, we are yet to have a user-friendly chatbot available. A smart generative cognitive behavioral therapy with spoken dialogue systems support was then developed using a model Persona Perception (P2) bot with Generative Pre-trained Transformer-2 (GPT-2). The model was then implemented using modern technologies in VPAs like voice recognition, Natural Language Understanding (NLU), and text-to-speech. This system is a magnificent device to help with voice-based systems because it can have therapeutic discussions with the users utilizing text and vocal interactive user experience.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.44-52
• /
• 2022

With recent scientific advances and growing interest in AI technologies, AI-based chatbots have been viewed as a practical learning aid for English language development. The purpose of this study is to examine preservice teachers' perceptions on the potential benefits of employing AI chatbots in English instruction and its pedagogical aspects. 28 preservice teachers majoring in English education were asked to use Kuki chatbots for a week with a guidance of a researcher and then report on their perceptions of AI chatbots in terms of perceived usefulness after use, applicability, and educational benefits and drawbacks. Emerging codes and themes were identified and evaluated using Thematic Analysis(TA) based on qualitative data from surveys and interviews. The findings show that six emerging themes were identified, encompassing perspectives on teacher, learner, communication, linguistic, affective, and assessment. The overall findings of this study revealed that AI-based chatbots can play a significant role as learning tools for stimulating interactive communication in a target language. Most preservice primary teachers acknowledge that AI chatbots can be useful as teaching and learning aids for both teachers and students. Furthermore, when applying various learner data to chatbot technology, such as learner assessment and diagnosis, a guided approach is necessary to perform a conversation appropriate for the learner's level and characteristics. Finally, as chatbots have a variety of benefits in terms of affective aspects, they may improve EFL learners' confidence in speaking English and learning motivation.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.696-698
• /
• 2018

본 연구에서는 메신저 플랫폼 상에서 위치정보 서비스를 제공하는 대화형 인공지능 챗봇(Chatbot)을 제안한다.별도의 애플리케이션에 들어가서 위치정보 서비스를 제공받던 기존 방식과는 달리 본 연구에서 제안하는 챗봇은 메시지 앱 내에서 대화형 방식으로 사용자에게 위치정보 서비스를 제공한다. 제안 챗봇은 Amazon Web Services 서버, Dialogflow API, ODSay API, 공공데이터 포탈 API 등을 통하여 구현되었다.

• 문화기술의 융합
• /
• 제9권3호
• /
• pp.797-802
• /
• 2023

영어가 외국어로서 사용되는 환경에서 영어 말하기 연습 활동에 AI 음성 챗봇을 사용했을 때 영어학습자들은 발화 동기가 높아지고 의사소통 연습의 기회가 많아져 결과적으로 영어 말하기 능력을 향상 시킬 수 있다. 본 연구에서는 초등학생 저학년의 경우에도 쉽게 활용 가능하고 학습효과를 높일 수 있는 가르치기 방식의 AI 음성 챗봇을 제안한다. 시제와 맥락과 기억에 기반한 활동인 언어학습에 Teachable Agent 시스템을 적용하기 위해 Teachable Agent에 학습자의 영어 발음과 수준을 반영하고, 학습자 오류에 맞추어 에이전트의 답변을 생성하는 방식을 적용하여 새로운 방식의 TA를 제안하고 이를 적용한 Teachable Agent AI 챗봇 프로토타입을 구현하였다. 실제 초등 영어 선생님과 초등학생을 대상으로 사용성 평가를 진행하여 학습 효과를 입증하였다. 본 연구 결과는 역할 전환을 통해 학습에 흥미가 없는 학생 또는 초등 저학년들이 학습에 스스로 참여할 수 있는 동기부여를 할 수 있도록 적용할 수 있다.