• Annual Conference of KIPS
• /
• 2018.05a
• /
• pp.365-368
• /
• 2018

인공지능 기술이 발달하면서 챗봇 플랫폼이 주목받고 있다. 챗봇이란 규칙 또는 인공지능(AI)을 이용해 사용자와 상호작용을 하는 대화형 인터페이스다. 챗봇에서 대화를 처리하는 방법은 규칙기반 대화 시스템, 검색기능 대화 시스템, 생성기반 대화 시스템이 있다. 본 논문에서는 규칙 기반 대화 시스템을 바탕으로 하는 모바일 영화 챗봇 서비스를 개발하였다. 이를 통하여 사용자는 더 편리하게 영화 관련 정보를 제공받을 수 있다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.683-689
• /
• 2023

자연어 처리 분야는 최근에 큰 발전을 보였으며, 특히 초대규모 언어 모델의 등장은 이 분야에 큰 영향을 미쳤다. GPT와 같은 모델은 다양한 NLP 작업에서 높은 성능을 보이고 있으며, 특히 챗봇 분야에서 중요하게 다루어지고 있다. 하지만, 이러한 모델에도 여러 한계와 문제점이 있으며, 그 중 하나는 모델이 기대하지 않은 결과를 생성하는 것이다. 이를 해결하기 위한 다양한 방법 중, Retrieval-Augmented Generation(RAG) 방법이 주목받았다. 이 논문에서는 지식베이스와의 통합을 통한 도메인 특화형 질의응답 시스템의 효율성 개선 방안과 벡터 데이터 베이스의 수정을 통한 챗봇 답변 수정 및 업데이트 방안을 제안한다. 본 논문의 주요 기여는 다음과 같다: 1) QA Pair Passage RAG을 활용한 새로운 RAG 시스템 제안 및 성능 향상 분석 2) 기존의 LLM 및 RAG 시스템의 성능 측정 및 한계점 제시 3) RDBMS 기반의 벡터 검색 및 업데이트를 활용한 챗봇 제어 방법론 제안

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.329-330
• /
• 2024

최근 생성형 AI에 대한 수요가 상승하고 있으며, MZ세대의 자기애 성향으로 자신의 얼굴을 활용한 미디어 콘텐츠에 대한 호기심이 높아지고 있다. 이에 따라 본 논문에서는 MZ세대의 창의성과 미디어 소비를 고취시키기 위해, StyleGAN 기술을 중심으로 자신과 닮은 2세의 가상 모습을 생성하는 웹 서비스를 설계하고 구현하였다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.291-306
• /
• 2020

Nowadays, Data-Network-AI (DNA)-based intelligent services and applications have become a reality to provide a new dimension of services that improve the quality of life and productivity of businesses. Artificial intelligence (AI) can enhance the value of IoT data (data collected by IoT devices). The internet of things (IoT) promotes the learning and intelligence capability of AI. To extract insights from massive volume IoT data in real-time using deep learning, processing capability needs to happen in the IoT end devices where data is generated. However, deep learning requires a significant number of computational resources that may not be available at the IoT end devices. Such problems have been addressed by transporting bulks of data from the IoT end devices to the cloud datacenters for processing. But transferring IoT big data to the cloud incurs prohibitively high transmission delay and privacy issues which are a major concern. Edge computing, where distributed computing nodes are placed close to the IoT end devices, is a viable solution to meet the high computation and low-latency requirements and to preserve the privacy of users. This paper provides a comprehensive review of the current state of leveraging deep learning within edge computing to unleash the potential of IoT big data generated from IoT end devices. We believe that the revision will have a contribution to the development of DNA-based intelligent services and applications. It describes the different distributed training and inference architectures of deep learning models across multiple nodes of the edge computing platform. It also provides the different privacy-preserving approaches of deep learning on the edge computing environment and the various application domains where deep learning on the network edge can be useful. Finally, it discusses open issues and challenges leveraging deep learning within edge computing.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.71-77
• /
• 2021

Recently, there is a demand for efficient program development of an IoT application support frameworks considering heterogeneous hardware characteristics. In addition, the scope of hardware support is expanding with the development of neuromorphic architecture that mimics the human brain to learn on their own and enables autonomous computing. However, most existing IoT IDE(Integrated Development Environment), it is difficult to support AI(Artificial Intelligence) or to support services combined with various hardware such as neuromorphic architectures. In this paper, we design an AI component abstract model that supports the second-generation ANN(Artificial Neural Network) and the third-generation SNN(Spiking Neural Network), and implemented an autonomous IoT IDE based on the proposed model. IoT developers can automatically create AI components through the proposed technique without knowledge of AI and SNN. The proposed technique is flexible in code conversion according to runtime, so development productivity is high. Through experimentation of the proposed method, it was confirmed that the conversion delay time due to the VCL(Virtual Component Layer) may occur, but the difference is not significant.

• Journal of Advanced Technology Convergence
• /
• v.1 no.2
• /
• pp.01-09
• /
• 2022

Recently, safety issues in companies and public institutions are no longer a task that can be postponed, and when a major safety accident occurs, not only direct financial loss, but also indirect loss of social trust in the company and public institution is greatly increased. In particular, in the case of a fatal accident, the damage is even more serious. Accordingly, as companies and public institutions expand their investments in industrial safety education and prevention, open AI learning model creation technology that enables safety management services without being affected by user behavior in industrial sites where high-risk situations exist, edge terminals System development using inter-AI collaboration technology, cloud-edge terminal linkage technology, multi-modal risk situation determination technology, and AI model learning support technology is underway. In particular, with the development and spread of artificial intelligence technology, research to apply the technology to safety issues is becoming active. Therefore, in this paper, an open cloud platform design method that can support AI model learning for high-risk site safety management is presented.

• Knowledge Management Research
• /
• v.25 no.3
• /
• pp.145-171
• /
• 2024

Literacy initially referred to the ability to read and understand written documents and processed information. With the advancement of digital technology, the scope of literacy expanded to include the access and use of digital information, evolving into the concept of digital literacy. The application and purpose of digital literacy vary across different fields, leading to the use of various terminologies. This study focuses on generative artificial intelligence (AI), which is gaining increasing importance in the AI era, to assess users' literacy levels. The research aimed to extend the concept of literacy proposed in previous studies and develop a tool suitable for Korean users. Through exploratory factor analysis, we identified that generative AI literacy consists of four factors: AI utilization ability, critical evaluation, ethical use, and creative application. Subsequently, confirmatory factor analysis validated the statistical appropriateness of the model structure composed of these four factors. Additionally, correlation analyses between the newly developed literacy tool and existing AI literacy scales and AI service evaluation tools revealed significant relationships, confirming the validity of the tool. Finally, the implications, limitations, and directions for future research are discussed.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.707-708
• /
• 2024

최근 디지털 헬스케어 기술과 서비스가 널리 활용되면서 의료 인공지능 성능 향상에 대한 관심이 높아지고 있다. 그러나 양성 데이터 대비 질병 데이터가 희소하여 학습 과정에서 과적합이 발생하거나 질병 예측 모델의 성능이 떨어진다는 한계가 있다. 본 논문에서는 데이터가 균질하지 않은 상황에서 생성형 인공지능 모델을 사용하여 합성 데이터를 생성하는 방안을 제안한다. 실험 결과에 따르면, 종래 방법 대비 제안한 방법의 정확도가 약 5.8% 향상되었고, 재현율이 약 21% 개선되었다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.1204-1205
• /
• 2023

본 논문은 소비자의 리뷰 데이터를 기반으로 한 새로운 감성 분석 방법을 제안한다. 긍정, 부정, 중립으로 분류하는 전통적 감성 분석방법은 텍스트에 나타난 감정의 섬세한 차이를 파악하기 어렵다. 이에 본 연구에서는 GPT 모델을 사용하여 텍스트에서 사용자의 감정을 8 가지의 카테고리로 세분화한다. 부정적 정서를 가진 리뷰에서 분노, 혐오, 실망과 같은 구체적인 감정들을 직관적으로 파악할 수 있었고, 감정의 강도까지 파악할 수 있었다. 제안된 방법을 통해 기업은 고객의 요구 사항을 정확하게 인지할 수 있으며, 고객 맞춤형 서비스 개선에 기여할 수 있다는 점이 기대된다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.803-808
• /
• 2024

As a service that creates graphic work images with AI, DALL-E2, Midjourney, Stable Diffusion, BING image generator, and Playground AI are widely used. It is that graphic also enables learner-led customized education. With this, it is worth studying detailed design customized learning materials and methods for designing efficient design in future 2D graphic work, and it is necessary to explore the areas of application. The current situation is that it is necessary to develop a design education system that can indicate the lack of AI technology through text security and questions. In this study, a successful proposal for a process that is produced through a process of creating AI design work through proxy work can be presented as a conclusion. Design, advertisement, and visual content companies are already using and adapting, and the trend is to reflect the AI graphic utilization ability and results in the portfolio along with interviews when hiring new employees. In line with this, detailed consideration and research on visual and design production methods for AI convergence between instructors and learners are currently needed. In this paper, proposals and methods for image quality production were considered in the main body and conclusions, and conclusive directions were proposed for five alternatives and methods for future applications.