• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.1349-1352
• /
• 2021

본 학술지는 기존의 공공 행정서비스에서의 복잡한 업무처리를 간단하게 처리할 수 있는 FAQ 형태의 챗봇서비스를 제안한다. 본 논문이 제안하는 주요 특징은 다음과 같다. 버튼, 대화, STT(Speech To Text)를 통한 사용자 기반 UI/UX를 제공한다. 딥러닝을 통한 Synonym, Typo를 검출하여 가장 높은 정확도의 Entity로 변환해준다. 이를 통해, 사용자는 해상물류 서비스를 이용하는데 있어 부담감을 해소하고 편리함을 얻을 수 있다.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.836-838
• /
• 2022

반려동물 시장 및 동물 의료분야의 성장, 동물병원 이용 과정 개선의 필요성으로 반려동물 질병의 시작부터 끝까지 전 과정을 함께하는 원스탑 모바일 애플리케이션을 개발하였다. 증상으로 예상 질병을 진단하는 머신러닝 모델과 자연어 문장을 인식하는 딥러닝 챗봇으로 사용자가 편리하게 반려동물 이상 증상에 대한 예상 질병을 챗봇으로 상담할 수 있도록 구현하였다. 챗봇 시스템을 기반으로 '예상 진단', '질병백과', '문진표', '동물병원' 기능을 추가하여 일관된 기능들로 유기적인 서비스를 구성하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.443-444
• /
• 2023

본 논문에서는 Microsoft의 Bot Framework v4를 활용하여 C#으로 개발한 피자 주문 챗봇에 대해 설명한다. 이 챗봇은 Azure에 호스팅 되었으며 피자 메뉴 선택, 피자 주문, 콜라 메뉴 선택, 콜라 주문, 배달 조회, 주문 종료 등의 기능을 제공한다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.1027-1028
• /
• 2023

학교상담은 학생들의 학업 및 심리적 건강을 촉진하는 핵심 구성 요소 중 하나로 자리 잡고 있으며, 코로나 19 로 인한 언택트 시대로의 전환은 비대면 상담 방식의 혁신을 촉발하였다. 본 연구는 AI 챗봇을 활용한 상담 서비스를 통해 학교상담의 효과를 높이고, 학생들의 학업 및 심리적 건강에 대한 지원을 강화하는 데 주력한다. 이러한 연구는 미래의 학교 상담 서비스 분야에 크게 이바지할 것으로 기대된다.

• Asia pacific journal of information systems
• /
• v.30 no.4
• /
• pp.832-846
• /
• 2020

Service organizations increasingly adopt data-based intelligent engines called chatbots in support of the interaction between customers and the companies. Two different types of chatbots have been suggested and introduced by companies leading the adoption of this emerging technology: rule-based chatbots and natural language processing-based chatbots. While the differences between these two types of technologies look relatively clear, the organizational and practical impacts of the differences have not been systematically explored. This study performed an experiment to compare the use of the two different types of chatbots used in practice by two comparable organizations. These two types of actual chatbots were used by Korean on-line shopping malls with similar business models (mobile shopping), length of history, size and reputation. The comparison was made based on such dimensions as usability, searchability, reliability and attractiveness. Contraty to conventional expectation that the superiority in technology will produce superior usability, the results show mixed superiority. The discussion on the reasons is presented.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.875-877
• /
• 2024

AI 기술의 발전으로 상담 및 심리치료 분야에서도 인공지능을 활용하려는 움직임이 활발해지고 있다. 정신건강 지원에 대한 수요가 증가하면서 인공지능, 특히 챗봇을 활용한 심리상담은 효율성과 접근성 측면에서 많은 이점을 가지지만 한계점 또한 존재한다. 본 연구에서는 AI 챗봇을 활용한 상담 및 심리치료 서비스의 국내 현황과 기술적 측면에서의 한계점을 분석한다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.461-466
• /
• 2021

본 연구에서는 DECO(Dictionnaire Electronique du COreen) 한국어 전자사전과 LGG(Local-Grammar Graph)에 기반한 반자동 언어데이터 증강(Semi-automatic Symbolic Propagation: SSP) 방식에 입각하여, 핀테크 분야의 CS(Customer Service) 챗봇 NLU(Natural Language Understanding)을 위한 주석 학습 데이터를 효과적으로 생성하고, 이를 기반으로 RASA 오픈 소스에서 제공하는 DIET(Dual Intent and Entity Transformer) 아키텍처를 활용하여 핀테크 CS 챗봇 NLU 시스템을 구현하였다. 실 데이터을 통해 확인된 핀테크 분야의 32가지의 토픽 유형 및 38가지의 핵심 이벤트와 10가지 담화소 구성에 따라, DECO-LGG 데이터 생성 모듈은 질의 및 불만 화행에 대한 양질의 주석 학습 데이터를 효과적으로 생성하며, 이를 의도 분류 및 Slot-filling을 위한 개체명 인식을 종합적으로 처리하는 End to End 방식의 멀티태스크 트랜스포머 모델 DIET로 학습함으로써 DIET-only F1-score 0.931(Intent)/0.865(Slot/Entity), DIET+KoBERT F1-score 0.951(Intent)/0.901(Slot/Entity)의 성능을 확인하였으며, DECO-LGG 기반의 SSP 생성 데이터의 학습 데이터로서의 효과성과 함께 KoBERT에 기반한 DIET 모델 성능의 우수성을 입증하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.3
• /
• pp.561-570
• /
• 2018

Artificial Intelligence is one of the technologies that are being discussed in the Fourth Industrial Revolution, attracting the attention from companies around the world and this technology is being applied to various industries such as education, finance, automobile, etc. AI integrated ChatBot is a system designed to respond to user questions according to defined response rules. This system is gradually expanded from simple inquiry responses for intelligent virtual assistant service, weather, traffic, schedule, etc. to service provisions through user pattern analysis, to solidify its position as a life-style service. As a result, research on AI integrated ChatBot platform has become necessary. Therefore, this study suggests the design and implementation of an intelligent chatbot service platform for small businesses.

• The Journal of Economics, Marketing and Management
• /
• v.6 no.1
• /
• pp.1-8
• /
• 2018

Purpose - Local social commerce market has grown up remarkably. And, Coupang has shown new delivery strategy of rocket delivery. Making new paradigm at local market, Coupang has expanded market scale. This study investigated state of local social commerce market, weight and promotion strategy of Coupang market to find out competitiveness edge of Coupang. Research design, data, and methodology - The study investigated state and concept of social commerce to find out state, problems and competitiveness of social commerce. New distribution service was short of precedent studies. Statistical analysis and experimental analysis were not used, and interview was done to investigate three of social commerce businesses. Results - CRM construction is insufficient to have poor system, Local delivery system could not be made enough at overnight delivery and customers were dissatisfied with ties with another company. Promotion shall be done by delivery system for increase of profitability, funding for more investment, chatbot to build new customer control system, and new delivery system to produce profit. Conclusions - Coupang and others have grown up rapidly to worsen profit and to jeopardize survival. Excessive initial investment has threatened the businesses, for instance, low sales of Amazon, excessive expenses, bench marking of logistics system, and others.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.1
• /
• pp.155-178
• /
• 2021

In the era of the 4th industrial revolution, public libraries need a strategy for promoting intelligent library services in order to actively respond to changes in the external environment such as artificial intelligence. Therefore, in this study, based on the concept of artificial intelligence and analysis of domestic and foreign artificial intelligence related trends, policies, and cases, we proposed the future direction of introduction and development of artificial intelligence services in the library. Currently, the library operates a reference information service that automatically provides answers through the introduction of artificial intelligence technologies such as deep learning and natural language processing, and develops a big data-based AI book recommendation and automatic book inspection system to increase business utilization and provide customized services for users. Has been provided. In the field of companies and industries, regardless of domestic and overseas, we are developing and servicing technologies based on autonomous driving using artificial intelligence, personal customization, etc., and providing optimal results by self-learning information using deep learning. It is developed in the form of an equation. Accordingly, in the future, libraries will utilize artificial intelligence to recommend personalized books based on the user's usage records, recommend reading and culture programs, and introduce real-time delivery services through transport methods such as autonomous drones and cars in the case of book delivery service. Service development should be promoted.