• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.2
• /
• pp.31-39
• /
• 2010

VoD(Video-on-Demand) servers have to provide timely processing guarantees for continuous media and reduce the storage and bandwidth requirements for continuous media. The compression techniques make the bit rates of compressed video data significantly variable from frame to frame. A VoD system should be able to provide the client with interactive operations such as fast forward and fast rewind in addition to normal playback of movie. However, interactive operations require additional resources such as storage space, disk bandwidth, memory and network bandwidth. In a stored video application such as VoD system, it is possible that a priori disk access patterns can be used to reserve the system resources in advance. In addition, clients of VoD server spend most of their time in playback mode and the period of time spent in interactive mode is relatively small. In this paper, I present the new buffer management scheme that provides efficient support for interactive operations in a VoD server using variable bit rate continuous media. Simulation results show that our strategy achieves 34% increase of the number of accepted clients over the LRU strategy.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.4
• /
• pp.1-6
• /
• 2023

To enhance immersive experiences for metaverse environements, background music is often used. However, the background music is mostly pre-matched and repeated which might occur a distractive experience to users as it does not align well with rapidly changing user-interactive contents. Thus, we implemented a system to provide a more immersive metaverse conversation experience by 1) developing a regression neural network that extracts emotions from an utterance using KEMDy20, the Korean multimodal emotion dataset 2) selecting music corresponding to the extracted emotions from an utterance by the DEAM dataset where music is tagged with arousal-valence levels 3) combining it with a virtual space where users can have a real-time conversation with avatars.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.84-86
• /
• 2022

Task-oriented chatbots prevail in various filed with the artificial intelligent dialogue system. The need for chatbots in customer services is growing, especially in education businesses given that there are many user inquiries and consultation requests. However, current dialogue systems only function as simple reactions or predetermined and frequently used actions. Meanwhile, the research about customized recommendation systems through artificial intelligence is very active with a wide variety of educational content. Although a dialogue system and a recommendation system is a core element in this domain, it has a limitation in that it is being conducted separately. Therefore, we present a study on a recommendation system that can recommend user-customized lectures combined with a dialogue system. With this combination, our system can respond to additional functions beyond these limitations. Through our research, we expect that work efficiency and user satisfaction will be improved by applying chatbots in education domains that are becoming more diversified and personalized.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.157-162
• /
• 2024

This study was conducted to implement Joseon Dynasty conversational style using the ChatGPT API to enhance the immersion of games set in the Joseon era. The research focuses on interactions between middle-class players and other classes. Two methods were employed: learning the dialogues from historical dramas set in the Joseon Dynasty and learning the sentence endings typical of the period. The method of learning sentence endings was rated higher based on self-evaluation criteria. Reflecting this, prompts were constructed to represent NPC dialogues in the game settings of the Joseon era. Additionally, a method was proposed for creating various NPC prompts using prompt combination techniques. This study can serve as a reference for NPC dialogue creation in games set in the Joseon Dynasty.

• Smart Media Journal
• /
• v.13 no.8
• /
• pp.26-38
• /
• 2024

This paper discusses the use of GPT and GPT API for prompt engineering in the development of the interactive smart device lock screen application "Smart Lock," aimed at enhancing literacy among young children and lower-grade elementary and middle school students during critical language development periods. In an era where media usage via smartphones is widespread among children, smartphone-based media is often cited as a primary cause of declining literacy. This study proposes an application that simulates conversations with parents as a tool for improving literacy, providing an environment conducive to literacy enhancement through smartphone use. Generative AI GPT was employed to create literacy-improving problems. Using pre-generated data, situational dialogues with parents were presented, and prompt engineering was utilized to generate questions for the application. The response quality was improved through parameter tuning and function calling processes. This study investigates the potential of literacy improvement education using generative AI through the development process of interactive applications.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.81-83
• /
• 1999

본 논문은 전자상거래에서 판매와 구매방법의 획일화된 검색기법을 이용한 상품의 검색 및 사용자 인터페이스를 지능형 대화 판매 에이전트를 설계함으로써 보다 편리하고 효율적인 사용자 인터페이스를 제공하는 시스템을 설계하였다. 기존 사이버 쇼핑몰에서 구매자의 검색에 의한 방식을 판매자와의 대화에 의한 검색방법으로 전환하여 구매자의 구매의욕을 증가시키고 검색에 소요되는 시간을 절약할 수 있을 뿐만 아니라 구매자 어휘를 분석하고 구매패턴을 파악하여 추가의 수요를 창출 할 수 있는 데이터를 축적하는 방법을 제시하고 많은 고객을 동일한 시간에 상대해야 하는 웹의 전자상거래 시스템에서 판매를 담당하는 에이전트를 설계하게 되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.1-2
• /
• 2013

본 논문에서는 안드로이드의 고질적인 문제점인 사용자 반응성 문제 해결을 위한 연구를 소개한다. 특히 여러 응용들이 동시에 수행되는 경우 대화형 응용이 다른 응용들에 밀려 원하는 만큼 CPU를 얻지 못하는 상황에서 발생하는 반응지연 문제에 초점을 맞추고 이를 극복하기 위한 연쇄적 우선순위 상승 기법을 제시한다. 이 기법은 대화형 웅용뿐만 아니라 기존 연구에서 고려하지 않은 터치 관련 이벤트 처리 스레드들과 대화형 응용의 자식 스레드들의 우선순위를 연쇄적으로 상향시킴으로써 터치에 대한 응답시간을 줄인다. 본 논문에서는 제안한 기법을 상용 스마트폰에 적용하여 유용성을 검증하였다. 실험 결과에 따르면 기존 안드로이드에 제안한 기법을 적용한 경우 평균반응시간이 기존의 31.91%로 감소하였다.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.122-124
• /
• 2017

대화시스템이 적절한 응답을 제시해 주기 위해서는 사용자의 의도를 분석하는 것은 중요한 일이다. 사용자의 의도는 도메인에 독립적인 화행과 도메인에 종속적인 서술자의 쌍으로 나타낼 수 있다. 사용자 의도를 정확하게 분석하기 위해서는 화행과 서술자를 동시에 분석하고 대화의 문맥을 고려해야 한다. 본 논문에서 제안하는 모델은 합성곱 신경망에서 공유 계층을 이용하여 화행과 서술자간 상호작용이 반영된 발화 임베딩 모델을 학습한다. 그리고 순환 신경망을 통해 대화의 문맥을 반영하여 발화를 분석한다. 실험 결과 제안 모델이 이전 모델들 보다 높은 성능 (F1-measure로 화행에 대해 0.973, 서술자 0.919)을 보였다.