• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.14-17
• /
• 2022

Due to the development of IT technology and the on-going Coronavirus disease, non-face-to-face services have been activated. To overcome the inconvenience of non-face-to-face service, service providers have adopted chatbots as a way to feel like a human being. As the increasing chatbot services, chatbot builders have emerged, which can help non-developers to build them. Although its popularity has increased, its performance evaluation has not been conducted on such chatbot builders. In this paper, we implement a prototype chatbot that classifies hospital departments in the medical field using Dialogflow and Rasa, which are popular chatbot builders. By measuring the accuracy of the chatbot's classification of medical subjects, we evaluated the level of accuracy that the most used chatbot builder can have when they are used to build a chatbot service. The simulation results showed that Dialogflow had 87%, 65%, and 60%, and Rasa did 64%, 70%, and 63% in surgery dermatology, and otolaryngology, respectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.29-35
• /
• 2023

In this paper, we propose a SW-EDU bot, a chatbot learning model for coding education by using a chatbot system. The same scenario-based models are created on the basis of Dialogflow and Kakao i Open Builder, which are representative chatbot builders. And then a SW-EDU bot is designed and implemented by selecting the builder more appropriate to our purpose. The implemented chatbot system aims to learn effective learning methods while encouraging self-direction of users by providing learning type selection, concept learning, and problem solving by difficulty level. In order to compare the usability of chatbot builders, five indicators are selected, and based on these, a builder with a comparative advantage is selected, and SW-EDU bot is implemented based on these. Through usability evaluation, we analyze the feasibility of SW-EDU bot as a learning support tool and confirm the possibility of using it as a new coding education learning tool.

• Korean Journal of Acupuncture
• /
• v.41 no.1
• /
• pp.27-32
• /
• 2024

Objectives : This study developed an AI-based patient chatbot and examined the usability and educational effectiveness of the chatbot in the context of Korean medicine education. Methods : The patient chatbot was developed using the AI chatbot builder 'Danbee', and a total of five experts were surveyed and interviewed to determine the usability, effectiveness, advantages, disadvantages, and improvement points of the chatbot. Results : The patient chatbot was found to have high usability and educational effectiveness. The advantages of the patient chatbot were 1) it provided students with practical experience in performing clinical skills, 2) it provided instructors with assessment materials while reducing their teaching burden, and 3) it could be effectively used for horizontal and vertical integration education. The disadvantages and improvements of the patient chatbot were 1) improving the accuracy of intention inference, 2) providing students with specific instructions for problem-solving activities, and 3) providing assessment results and feedback about students' activities. Conclusions : This study is significant in that it proposes a new training method to overcome the limitations of the existing doctor-patient simulation. It is hoped that this study will stimulate further research on the improvement of students' clinical skills using artificial intelligence.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.185-186
• /
• 2020

최근 제품을 주문하거나 상품을 조회하는 등의 간단한 상담을 챗봇을 이용하여 자동화하는 온라인 쇼핑몰들이 늘어나고 있다. 이는 고객을 상담하는 상담원의 업무를 줄여줄 뿐 아니라 고객 상담을 즉각적이고 효율적으로 진행할 수 있다. 또한 사용자의 입장에서 챗봇은 처음 이용하는 사람도 사용하기가 쉽고, 상담원과의 연결까지 기다리지 않고 사용자가 원하는 시간에 커뮤니케이션이 가능하고, 기업 측면에서는 인건비가 감소되고 고객관리가 용이해진다는 장점이 있다. 그러나 챗봇은 주어진 질문에만 대답할 수 있고, 처음 메뉴를 파악하기 힘들다는 단점이 있다. 따라서 본 논문에서는 카카오톡 오픈빌더를 사용하여 질문의도를 파악하는 intent와 entity를 추출한 뒤 딥러닝을 통해 체계적으로 학습을 진행한다. 이를 통해 주어지지 않은 질문들을 파악한다. 또한, 오픈빌더의 시나리오 선택 기능을 활용하여 초기에 선택할 수 있는 메뉴를 파악하기 쉽도록 구현하였다. 사용자는 본 논문에서 제안하는 챗봇을 통해 사용자는 상담에 필요한 도움을 받을 수 있을 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.29-30
• /
• 2019

본 논문에서는 카카오i 오픈빌더 API를 활용하여 언제 어디서나 손쉬운 접근 방법으로 날씨 정보를 얻을 수 있는 챗봇을 설계하고 구현한다 이 챗봇은, 플러스 친구를 통해 친구 추가 후 이용 가능하며, Python의 Flask 웹 프레임워크를 통하여 날씨에 관한 기온, 미세 먼지 농도, 강수량, 자외선 지수, 캐스팅 정보 등을 네이버에서 사용자가 검색한 지역별로 크롤링 후 가공하여 서비스 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.235-236
• /
• 2021

본 논문에서는 Microsoft Visual Studio의 Bot Builder SDK Template, Bot Emulator, KaKao Map 서비스를 활용하여 제주도 여행지를 추천하는 챗봇을 구현한다. 이 챗봇은 제주도 여행을 계획하고 있는 사용자에게 적절한 서비스를 제공하는 챗봇이다. 사용자에게 여행지 관련 테마를 제시하고, 사용자는 챗봇이 제시한 선택지 중 자신이 가장 선호하는 선택지를 선택한다. 사용자가 선택지를 결정하면 이를 바탕으로 챗봇 데이터베이스에 있는 적절한 여행지를 추천한다. 사용자가 테마를 고르지 않고 모든 데이터를 보고자 하는 경우 목록보기를 선택하여 챗봇이 가진 모든 여행지 목록을 볼 수 있다. 이 과정을 통해 사용자는 자신이 원하는 분야의 제주도의 적절한 여행지를 추천받을 수 있다.

• East Asian mathematical journal
• /
• v.39 no.2
• /
• pp.229-250
• /
• 2023

The purpose of this study is to investigate the impact of project learning using chatbots on artificial intelligence literacy. The subjects of the study were a total of 41 students from 1st to 3rd grade of general high school in Gyeonggi-do. Classes were held after school for a total of 6 hours, and the contents of the classes consisted of the concept and characteristics of artificial intelligence, the concept and expression of knowledge, OBT application for Kakao i open builder, guidance on how to create chatbots, and chatbot production practice. As a result of the pre- and post-test of the experimental group, the quantitative value of artificial intelligence literacy increased in all three grades. In the case of second-year students who set up a comparison group, when compared with the results of the comparison group, there was a significant positive effect on the AI literacy result, and female students were found to be more effective than male students.