• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.56-61
• /
• 2022

In this paper, we classify and present AI algorithms and natural language processing methods used in chatbots. A framework that can be used to implement a chatbot is also described. A chatbot is a system with a structure that interprets the input string by constructing the user interface in a conversational manner and selects an appropriate answer to the input string from the learned data and outputs it. However, training is required to generate an appropriate set of answers to a question and hardware with considerable computational power is required. Therefore, there is a limit to the practice of not only developing companies but also students learning AI development. Currently, chatbots are replacing the existing traditional tasks, and a practice course to understand and implement the system is required. RNN and Char-CNN are used to increase the accuracy of answering questions by learning unstructured data by applying technologies such as deep learning beyond the level of responding only to standardized data. In order to implement a chatbot, it is necessary to understand such a theory. In addition, the students presented examples of implementation of the entire system by utilizing the methods that can be used for coding education and the platform where existing developers and students can implement chatbots.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1097-1100
• /
• 2020

챗봇(Chatbot)은 자연어처리기술 등 인공지능 기술을 기반으로 한 사용자 친화적인 대화 방식 인터페이스를 제공하는 장점이 있어, 금융, 상담, 주문 등 다양한 산업 분야에서 적용되고 있다. 그러나, 챗봇의 응답이 사용자의 정신 모형과 불일치하는 경우, 다음 대화를 이어가는데 어려움을 야기하게 된다. 그러므로, 챗봇의 사용성을 확보하기 위해서는 응답 오류의 제거 또는 완화가 필수적이다. 기존의 챗봇의 사용성 개선과 관련된 연구들은 설문조사와 인터뷰 등 사용성 평가를 통해 상위 수준의 개선 방향만을 제안하고 있다. 따라서, 챗봇 개발 시, 실무자들이 응답 오류의 문제점을 분석하고, 이를 해결하기 위한 구체적인 개선 방안을 제시하는 데 한계가 있었다. 본 논문에서는 FMEA(Failure Modes and Effects Analysis) 기법을 활용해, 응답 오류의 치명도를 파악하고, 치명적인 오류들에 대해서는 FTA(Fault Tree Analysis) 기법을 기반으로 원인 분석을 실시하여 구체적으로 문제를 해결하기 위한 프로세스를 제안한다. 본 프로세스의 효용성을 검증하기 위해 주문 도메인의 챗봇에 적용해 보았다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.231-232
• /
• 2021

본 논문에서는 Microsoft Bot Framework 기반의 미용실 예약 서비스 챗봇을 구현한다. 이 챗봇은 데이터 베이스 연동을 통하여 미용실 예약정보를 저장, 수정, 취소하는 기능을 제공하여 실시간으로 사용자에게 신속하고 편리한 예약 서비스를 제공하도록 설계하고 구현한다. 또한, Microsoft Bot Framework를 이용하여 채팅 인터페이스뿐만 아니라 챗봇 작업의 작동 방법과 이유를 이해하는 데 도움이 되는 독립 실행형 앱을 사용하여 미용실 예약과 예약변경 및 취소 이벤트를 발생시킬 수 있도록 구현한다. 그리고 개인 웹 서버와 카카오맵 API를 연동하여 미용실 위치 경로를 제공하여 사용자가 더욱 편리하게 서비스를 이용하도록 구현한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.367-368
• /
• 2023

최근 챗봇 시스템은 급격한 발전과 함께 사용자와 자연스러운 대화를 할 수 있는 인공지능 기술의 필요성이 대두되고 있다. 기존의 챗봇 시스템은 대화 상황을 충분히 이해하지 못하거나, 학습된 데이터를 벗어나는 문장에 대한 일관성 있는 응답을 제공하지 못하는 한계가 있다. 본 논문에서는 GPT-3와 KoBERT를 활용하여 사용자의 감정 상태를 파악하고 해당 감정을 고려한 일관성 있는 대화를 제공하는 감정 분석 기반 챗봇 시스템을 제안한다. 이를 바탕으로 긍정적인 대화를 이어 나가는데 초점을 두어 자연스러운 대화가 가능할 것으로 기대된다.

• Journal of Information Technology Services
• /
• v.23 no.2
• /
• pp.99-116
• /
• 2024

Recently, interest in ChatGPT has been increasing. This study investigated the factors influencing the satisfaction of users using ChatGPT service, a chatbot system based on artificial intelligence technology. This paper empirically analyzed causality between the four major factors of service quality, system quality, information quality, and security as independent variables and user satisfaction of ChatGPT as dependent variable. In addition, the mediating effect of reliability between the independent variables and user's satisfaction was analyzed. As a result of this research, except for information quality, among the quality factors, security and reliability had a positive causality with use satisfaction. Reliability played a mediating role between quality factors, security, and user satisfaction. However, among quality factors, the mediating effect of reliability between service quality and user's satisfaction was not significant. In conclusion, in order to increase user satisfaction with new technology-based services, it is important to create trust among users. The research results sought to emphasize the importance of user trust in establishing development and operation strategies for artificial intelligence systems, including ChatGPT.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.79-85
• /
• 2018

As the utilization of chatbots grows and the AI market grows, many companies are interested. And everybody is spurring growth by offering chatbot build services so that they can create chatbots. This makes chatbots easier to service on the messenger platform, which is changing the existing application market. In this paper, we present a methodology for designing and implementing existing DB-based applications as instant messenger platform-based applications, and summarize what to consider in actual implementation to provide an optimal system structure. According to this methodology, we design and implement a chatbot that serves as an teaching advisor who provides information to the students in the curriculum. The implemented application objectively visualizes the user's desired information from the user's point of view and delivers it through the interactive interface quickly and intuitively. By implementing these services and real service, it is predicted that DB-based information providing applications will be implemented as chatbots and will be changed to bi-directional communication through an interactive interface. it is predicted that DB-based information providing applications will be implemented as chatbots and will be changed to bi-directional communication through an interactive interface. Enterprise legacy application will take chatbot technology as one of important digital transformation initiative.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.4
• /
• pp.57-69
• /
• 2022

During the 10 years from 2011 to 2021, a whopping 2,800 people were killed or injured during port work. Among them, the frequency of occurrence at the port loading and unloading business is high. Container terminal operators must conduct risk assessments and establish reasonable safety measures in accordance with laws and regulations. As a research method, the contents of risk assessment presented in the Industrial Safety and Health Act, the Serious Accident Punishment Act, and the Special Act on Port Safety are presented through literature analysis. In this study, previous studies were analyzed to examine the risk assessment method and risk factors of container terminals. The purpose is to present 'industrial safety AI chatbot technology' that can improve the risk of safety accidents.

• Journal of Korean Society of Archives and Records Management
• /
• v.19 no.4
• /
• pp.221-230
• /
• 2019

This paper aims to introduce the case of operating electronic document system and record management system as one system called i-Works at Korea Midland Power Company. i-Works combines intelligent services, such as artificial intelligence and a chatbot, as a supplementary tool for record management. As such, the preparation process and progress direction for the development of the record management system is introduced, an in-depth review of real-time transfer and utilization of the functional classification system to enhance the utilization of the current records is presented, and new technologies, such as artificial intelligence for an efficient management of the increasing number of electronic records, are established.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.3021-3027
• /
• 2010

Example-based chatBot generates a response to user's utterance by searching the most similar utterance in a collection of dialogue examples. Though finding an appropriate example is very important as it is closely related to a response quality, few studies have reported regarding what features should be considered and how to use the features for similar utterance searching. In this paper, we propose a machine learning framework which uses various linguistic features. Experimental results show that simultaneously using both semantic features and lexical features significantly improves the performance, compared to conventional approaches, in terms of 1) the utilization of example database, 2) precision of example matching, and 3) the quality of responses.