• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.12
• /
• pp.552-559
• /
• 2008

Computing technologies are extending the means by which people communicate. Especially, virtual worlds have recently become successful, due to rapidly improving Information Technologies. Chat is a crucial function in current virtual worlds. We need a realistic and efficient communication framework for multi-agents participating in a virtual world. The main contribution of our work is twofold. First, we propose a realistic communication framework which enables 'Complete Talk' and 'Partial Talk' in terms of spatial relationships between avatar agents. Second, our system reconstructs a dialogue graph which maintains all transcripts in the form of directed graphs with temporal(dialogue sequences) and spatial information(physical positions) about communicating agents.

• Journal of Korea Game Society
• /
• v.17 no.1
• /
• pp.99-108
• /
• 2017

Communication is one of the very important factor in MMORPGs where a large number of users participate at the same time. The voice chatting system, which was appeared in the development process of the chatting system, failed in Korea but it was a great success in China. The purpose of this study is to analyze this cause. The research scope of this study is as follows. We set the range of this study from 2003 to 2015. This period covers the beginning of the growth of the Chinese game industry up to the present. The research target games are MMORPGs, which ranked 1st in sales and concurrent users. In the research and survey analysis process, various factors such as the input speed of Chinese and Korean characters and the relationship between men and women were investigated and analyzed. In conclusion, chatting system in Chinese MMORPGs has developed into three stages and we found out that voice chatting in China was relatively popularized rather than in Korea. China's slow typing speed and excellent voice chatting system were the main factors.

• Journal of Internet of Things and Convergence
• /
• v.4 no.1
• /
• pp.31-36
• /
• 2018

In this paper, we developed a chatbot system using the Django framework using the KakaoTalk API so that college students can easily search for important information in their university. Unlike existing chatbot systems that provide only specific information, the chatbot developed in this research automatically provides search results for various types of user queries such as weather, YouTube, Naver real-time ranking search and language translation as well as important information within their own university. We developed a module using Apache, Python and Django in AWS Ubuntu server and developed a chatbot system that automatically responds to user queries by communicating with KakaoTalk server using KakaoTalk API and BeautifulSoup. The system developed in this study is expected to be applicable to the future university entrance information promotion and election promotion system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.31-39
• /
• 2023

The evolution of Natural Language Processing (NLP) and the rise of large language models (LLM) like ChatGPT have paved the way for specialized question-answering (QA) systems tailored to specific domains. This study outlines a system harnessing the power of LLM in conjunction with document search algorithms to interpret and address user inquiries using documents from the Korea Atomic Energy Research Institute (KAERI). Initially, the system refines multiple documents for optimized search and analysis, breaking the content into managable paragraphs suitable for the language model's processing. Each paragraph's content is converted into a vector via an embedding model and archived in a database. Upon receiving a user query, the system matches the extracted vectors from the question with the stored vectors, pinpointing the most pertinent content. The chosen paragraphs, combined with the user's query, are then processed by the language generation model to formulate a response. Tests encompassing a spectrum of questions verified the system's proficiency in discerning question intent, understanding diverse documents, and delivering rapid and precise answers.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.83-90
• /
• 2024

In this paper, we propose a solution to apply a proximity voice dialog system to voice dialog technology, one of the interaction systems in multimedia environments. A voice dialog between multiple users in a multimedia space is designed by adjusting the volume of the voice according to the distance between the user avatars and muting the user who is beyond the audible distance. The main feature of this research is a reliable UDP-based active server system that delivers low-quality voice data to users who are far away based on distance and does not transmit voice data to users who enter the inaudible area for economic development. The performance of the proposed system was measured in a previously completed project based on the Unity game engine, and it is expected that the system proposed in this research will be actively used in environments that provide interaction between multiple users such as met averse content and real-time battle action games.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.401-418
• /
• 2023

Recently, the socio-economic interest in Large Language Models (LLMs) has been growing due to the emergence of ChatGPT. As a type of generative AI, LLMs have reached the level of script creation. In this regard, it is important to address the issue of discrimination (sexism, racism, religious discrimination, ageism, etc.) in the performing arts in general or in specific performing arts works or organizations in a large language model that will be widely used by the general public and professionals. However, there has not yet been a full-scale investigation and discussion on the issue of discrimination in the performing arts in large-scale language models. Therefore, the purpose of this study is to textually analyze the perceptions of discrimination issues in the performing arts from LMMs and to derive implications for the performing arts field and the development of LMMs. First, BBQ (Bias Benchmark for QA) questions and measures for nine discrimination issues were used to measure the sensitivity to discrimination of the giant language models, and the answers derived from the representative giant language models were verified by performing arts experts to see if there were any parts of the giant language models' misperceptions, and then the giant language models' perceptions of the ethics of discriminatory views in the performing arts field were analyzed through the content analysis method. As a result of the analysis, implications for the performing arts field and points to be noted in the development of large-scale linguistic models were derived and discussed.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.347-373
• /
• 2023

As the significance of ESG (Environmental, Social, and Governance) management amplifies in driving sustainable growth, this study delves into and compares ESG trends and interrelationships from both corporate and societal viewpoints. Employing a combination of Latent Dirichlet Allocation Topic Modeling (LDA) and Semantic Network Analysis, we analyzed sustainability reports alongside corresponding social media datasets. Additionally, an in-depth examination of social media content was conducted using Joint Sentiment Topic Modeling (JST), further enriched by Semantic Network Analysis (SNA). Complementing text mining analysis with the assistance of ChatGPT, this study identified 25 different ESG topics. It highlighted differences between companies aiming to avoid risks and build trust, and the general public's diverse concerns like investment options and working conditions. Key terms like 'greenwashing,' 'serious accidents,' and 'boycotts' show that many people doubt how companies handle ESG issues. The findings from this study set the foundation for a plan that serves key ESG groups, including businesses, government agencies, customers, and investors. This study also provide to guide the creation of more trustworthy and effective ESG strategies, helping to direct the discussion on ESG effectiveness.

• Journal of The Korean Association For Science Education
• /
• v.38 no.6
• /
• pp.885-899
• /
• 2018

As 'Science Inquiry Experiment' is newly introduced in the high school curriculum, where inquiry and experiment oriented education is insufficient, this study aims to analyze teacher's practice of 'Science Inquiry Experiment' in depth and identify contradictions during its process in the perspective of Cultural Historical Activity Theory. The research participant is teacher SHIN who is exclusively responsible for Science Inquiry Experiment. Starting with reflection on the practice of Science Inquiry Experiment class conducted in the first semester, interviews with participants, participatory observation and local materials were used during the 2nd semester's Science Inquiry Experiment class. A descriptive analysis of the teacher SHIN's practice of Science Inquiry Experiment was carried out and the contradictions in the activity system of the teacher SHIN were identified. The result reveals that in the overall practice of teaching Integrated Science and Science Inquiry Experiment, there were contradictions between teacher SHIN's recognition about cooperation(subject) and shared responsibility with other teachers(division of labor), and between teacher SHIN's recognition about the subjects(subject) and contrasting contents in teacher training courses(community). In the practice of teaching Science Inquiry Experiment, there were specific contradictions between teacher SHIN's recognition about the subject(subject) and time of job assignment(rule), between experimental activities(object) and experimental tools(tool), and between purpose of the subject(object) and directions about assessment(rule). These contradictions directly or indirectly influence the practice of teaching Science Inquiry Experiment. There needs to be support for constructing an activity system capable of supporting and promoting teachers' practice of Science Inquiry Experiment, and we made several suggestions to resolve the problems.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.315-316
• /
• 2020

본 논문에서는 현재 이슈가 되고 있는 코로나에 대해서 사람들이 실생활에서 궁금해할 정보들을 Seq2seq 기술을 사용한 챗봇으로 정보를 제공한다.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.355-360
• /
• 2004

This study is aimed at developing the system to manage the process and metadata of spatial data construction. The process of spatial data construction is standardized by analyzing knowhow of major firms and the provisions of MOCT(Ministry of the Construction and Transportation), and by appling the development methodology of information system. The system from this study has the capability to manage efficiently the process and metadata of spatial data construction. The process is shown by using index map. Also, it is shown by using Gantt chart and PERT chat after developing the interface for MS Project. The metadata is generated from the process, and managed systematically.