• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.34 no.3
• /
• pp.202-213
• /
• 2024

Introduction: Acknowledging the global issue of diseases potentially caused by overwork, this study aims to develop an AI model to help workers understand the connection between cerebrocardiovascular diseases and their work environment. Materials and methods: The model was trained using medical and legal expertise along with data from the 2021 occupational disease adjudication certificate by the Industrial Accident Compensation Insurance and Prevention Service. The Polyglot-ko-5.8B model, which is effective for processing Korean, was utilized. Model performance was evaluated through accuracy, precision, sensitivity, and F1-score metrics. Results: The model trained on a comprehensive dataset, including expert knowledge and actual case data, outperformed the others with respective accuracy, precision, sensitivity, and F1-scores of 0.91, 0.89, 0.84, and 0.87. However, it still had limitations in responding to certain scenarios. Discussion: The comprehensive model proved most effective in diagnosing work-related cerebrocardiovascular diseases, highlighting the significance of integrating actual case data in AI model development. Despite its efficacy, the model showed limitations in handling diverse cases and offering health management solutions. Conclusion: The study succeeded in creating an AI model to discern the link between work factors and cerebrocardiovascular diseases, showcasing the highest efficacy with the comprehensively trained model. Future enhancements towards a template-based approach and the development of a user-friendly chatbot webUI for workers are recommended to address the model's current limitations.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.21-29
• /
• 2023

ChatGPT, a chatbot based on GPT large language models, has gained immense popularity among the general public as well as domain professionals. To assess its proficiency in specialized fields, ChatGPT was tested on mainstream exams like the bar exam and medical licensing tests. This study evaluated ChatGPT's ability to answer questions related to Building Information Modeling (BIM) by testing it on Korea's BIM expertise exam, focusing primarily on multiple-choice problems. Both GPT-3.5 and GPT-4 were tested by prompting them to provide the correct answers to three years' worth of exams, totaling 150 questions. The results showed that both versions passed the test with average scores of 68 and 85, respectively. GPT-4 performed particularly well in categories related to 'BIM software' and 'Smart Construction technology'. However, it did not fare well in 'BIM applications'. Both versions were more proficient with short-answer choices than with sentence-length answers. Additionally, GPT-4 struggled with questions related to BIM policies and regulations specific to the Korean industry. Such limitations might be addressed by using tools like LangChain, which allow for feeding domain-specific documents to customize ChatGPT's responses. These advancements are anticipated to enhance ChatGPT's utility as a virtual assistant for BIM education and modeling automation.

• Archives of Craniofacial Surgery
• /
• v.25 no.3
• /
• pp.116-122
• /
• 2024

Background: Due to the importance of evidence-based research in plastic surgery, the authors of this study aimed to assess the accuracy of ChatGPT in generating novel systematic review ideas within the field of craniofacial surgery. Methods: ChatGPT was prompted to generate 20 novel systematic review ideas for 10 different subcategories within the field of craniofacial surgery. For each topic, the chatbot was told to give 10 "general" and 10 "specific" ideas that were related to the concept. In order to determine the accuracy of ChatGPT, a literature review was conducted using PubMed, CINAHL, Embase, and Cochrane. Results: In total, 200 total systematic review research ideas were generated by ChatGPT. We found that the algorithm had an overall 57.5% accuracy at identifying novel systematic review ideas. ChatGPT was found to be 39% accurate for general topics and 76% accurate for specific topics. Conclusion: Craniofacial surgeons should use ChatGPT as a tool. We found that ChatGPT provided more precise answers with specific research questions than with general questions and helped narrow down the search scope, leading to a more relevant and accurate response. Beyond research purposes, ChatGPT can augment patient consultations, improve healthcare equity, and assist in clinical decision-making. With rapid advancements in artificial intelligence (AI), it is important for plastic surgeons to consider using AI in their clinical practice to improve patient-centered outcomes.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.933-942
• /
• 2024

With the development of AI, Chat GPT, an artificial intelligence chatbot that appeared in 2022, is rapidly spreading to a wide range of people and expanding its usefulness. This study was conducted to examine college students' intention to continue using Chat GPT using a technology acceptance model. As a result of the study, all of Chat GPT's features had a positive effect on college students' perceived usefulness and perceived ease of use. However, among the features of Chat GPT, system quality and relative advantages did not directly affect the intention to continue using it. However, it was confirmed that it had an effect when perceived usefulness and perceived ease of use were mediated. The perceived usefulness and perceived ease of Chat GPT were verified to have a positive effect on the intention to continue using it.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.05a
• /
• pp.623-643
• /
• 2017

최근 인공지능 기술이 발달하면서 챗봇이 글로벌 IT기업들에게 새로운 IoT플랫폼으로 주목받고 있다. 챗봇이란 대화형 인터페이스 상에서 규칙 또는 인공지능(AI)을 이용해 사용자와 상호작용(interaction)을 하는 서비스를 지칭한다. 챗봇은 현재 간단한 정보검색 및 가상비서 서비스를 제공하는 수준이지만, 향후 IoT와 O2O 영역의 핵심적인 인공지능 플랫폼으로 부상할 전망이다. 챗봇은 스마트폰 디바이스와 어플리케이션을 기반으로 빠르게 확산되어 핵심 플랫폼의 지위를 차지할 것으로 예상된다. 그러나 챗봇 사용자의 수용행태에 관한 학술적 연구는 미비한 상황이다. 이에 본 연구는 기존의 기술수용이론(TAM)보다 수용의도에 대한 설명력이 높다고 검증된 통합기술수용이론(UTAUT)을 적용하여 챗봇의 사용자 수용행동에 관한 모델을 구축하였다. 구체적으로, 수용의도의 결정요인인 성과기대, 예상노력, 사회적영향, 촉진조건이 수용의도에 긍정적인 영향을 미칠 것으로 예상하였다. 이 과정에서 수용의도 결정요인과 수용의도 간의 관계를 성별, 연령, 개인혁신성이 조절할 것으로 보았다. 본 연구는 챗봇의 수용에 영향을 미치는 결정요인과 조절변인의 효과를 검증하여 실무적 시사점을 제공하고자 한다.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.682-683
• /
• 2019

본 논문에서는 인공지능 Watson 기반의 챗봇 시스템에서 효율적인 자연어 처리를 위한 시나리오 설계 방법을 제안하고자 한다. 주제별 시나리오 구성을 단순히 무작위 순서로 배치하는 것 보다 연관도가 높은 노드를 가깝게 연결하는 것이 주제 전환 속도와 효율성 측면에서 유의미한 것으로 나타났다. 시스템의 구성 요소를 연결해주는 어플리케이션은 빠르게 질문과 답변 전달이 가능하도록 모듈화하여 PaaS 클라우드에 연결하도록 한다. 그 결과 경제적이고 단순한 개발 환경에서 어플리케이션을 구현하는 것이 가능했다. API를 호출하여 답변을 전달하는 경우에는 약 2.005초 정도로 빠른 응답 속도를 보였다. 따라서 본 논문에서 설명하는 챗봇 시스템 설계 방법을 사용할 경우 저비용으로 효율성 있는 서비스 제공 플랫폼을 구축할 수 있다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.219-240
• /
• 2023

Conversational AI which allows users to interact with satisfaction is a long-standing research topic. To develop conversational AI, it is necessary to build training data that reflects real conversations between people, but current Korean datasets are not in question-answer format or use honorifics, making it difficult for users to feel closeness. In this paper, we propose a conversation dataset (KOMUChat) consisting of 30,767 question-answer sentence pairs collected from online communities. The question-answer pairs were collected from post titles and first comments of love and relationship counsel boards used by men and women. In addition, we removed abuse records through automatic and manual cleansing to build high quality dataset. To verify the validity of KOMUChat, we compared and analyzed the result of generative language model learning KOMUChat and benchmark dataset. The results showed that our dataset outperformed the benchmark dataset in terms of answer appropriateness, user satisfaction, and fulfillment of conversational AI goals. The dataset is the largest open-source single turn text data presented so far and it has the significance of building a more friendly Korean dataset by reflecting the text styles of the online community.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.5
• /
• pp.273-283
• /
• 2022

Banking and finance is a broad term that incorporates a variety of smaller, more specialized subjects such as corporate finance, tax finance, and insurance finance. A virtual assistant that assists users in searching for information about banking and finance terms might be an extremely beneficial tool for users. In this study, we explored the process of searching for information, seeking opportunities, and developing a virtual assistant in the first stages of starting learning and understanding Vietnamese to increase effectiveness and save time, which is also an innovative business practice in Use-case Vietnam. We built the FIBA2020 dataset and proposed a pipeline that used Natural Language Processing (NLP) inclusive of Natural Language Understanding (NLU) algorithms to build chatbot applications. The open-source framework RASA is used to implement the system in our study. We aim to improve our model performance by replacing parts of RASA's default tokenizers with Vietnamese tokenizers and experimenting with various language models. The best accuracy we achieved is 86.48% and 70.04% in the ideal condition and worst condition, respectively. Finally, we put our findings into practice by creating an Android virtual assistant application using the model trained using Whitespace tokenizer and the pre-trained language m-BERT.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.173-180
• /
• 2024

Along with its importance, the real estate market poses risks of various fraudulent activities. Recently, a surge in real estate-related scams, such as lease fraud, has caused great financial damage to many ordinary people. These problems are often caused by the complexity of real estate transactions and information imbalance. Therefore, there is an urgent need to secure reliability and improve transparency in the transaction process. In this paper, to solve this real estate fraud problem, we propose a chatbot system using digital technology and artificial intelligence, especially GPT (Generative Pre-Trained Transformer). This system serves to protect users from fraud by providing them with precautions and confirmations in the lease transaction process. In addition, GPT-based chatbots respond to questions from users in time, contributing to reducing uncertainty in the transaction process and increasing reliability.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.765-776
• /
• 2018

Artificial Intelligence is a rapidly growing technology with the latest developments in computing technology and is considered as one of the next major technologies. Chat-Bot is a system that is designed to respond to user's input according to the rules that are set up in advance and it provides more services through simple and repetitive tasks such as counseling, ordering and others. Accordingly, the study aims to present a model of a celeb-bot using Artificial Intelligence. Celeb-Bot is a combination of Celeb, which are short for Celebrity and Chat-bot. Celeb-Bot provides a Chat-Bot service that allows people to talk to a celebrity. The celeb is the best thing to build a relationship and has the advantages of being accessible to anyone. At the same time, Artificial Intelligence is a technology that can be seen as a person, not a product. Based on this, we believe that Celeb's Characteristic and Chat-bot based on artificial intelligence technologies need to be combined, so variety of products can generate synergy. It is predicted that there will be variety of derivatives that utilize this technology, and it is going to present a celeb-bot model accordingly.