• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.590-593
• /
• 2022

최근 코로나바이러스감염증-19(COVID-19)로 인해서 다양한 비대면 서비스가 증가하고 있는데 그 중에서 사람과 인공지능 간 의사소통하여 정보를 얻는 대화 시스템이 대표적인 서비스이다. 대화 시스템은 입력되는 단일 문장에 대한 정보만을 응답하기 때문에 이전 대화의 정보를 알기 위해서는 질문했던 내용을 다시 입력해야 하는 문제점이 있다. 이런 문제를 해결하고 대화 진행에 도움을 주기 위해서 본 논문에서는 대화 내 문장들의 다중 의도 탐지를 통한 공통 대화 주제 식별 시스템을 제안한다.

• Korean Institute of Interior Design Journal
• /
• v.22 no.6
• /
• pp.181-189
• /
• 2013

Space in the past had characteristics of place which are required for specific behavior to be done as we recognized it easily. However, for space in modern times, the purpose, forms and behavior space has, have changed as tools comprising the space have changed. 'Virtual space' which has been a conversation topic recently is unspecific and changeable space whose forms and geological location are not defined clearly. In addition, behaviors caused by this virtual space in combination with real space are taking place. The nature of Flash Mob which is one of the typical behaviors which take place starting from virtual space to be connected with real space, is that it is intangible game culture whose forms and behaviors are not fixed, and it is not limited to a specific place. Besides, Flash Mob is characteristic of representing game culture in modern society, and its nature can be summarized as temporariness, non-placeness, anonymity, double-sidedness and so forth. Since events generally take place in every place when man is involved in space, it's possible to generally think events derived from interpersonal relationships between man and man. We are to study spatial characteristics of Flash Mob by analyzing features and cases of the Flash Mob by means of them.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.05a
• /
• pp.27-28
• /
• 2019

Recently, a bed company detected a radon more than Red Politics and became a hot topic of conversation. This has led to increased interest in radon, and a number of free-of-charge bodies have also been established to recognize the dangers of radon. In addition, the Korean Institute of Geological and Resource Research is planning to assist the installation of radon alarm systems in 10,000 households nationwide, free of charge. Since radon is a colorless, odorless and tasteless gas that causes lung cancer, it aims to reduce lung cancer incidence by absorbing radon using bamboo activated carbon as a way to reduce it. Due to the use of bamboo activated carbon, radon concentration per hour tends to decrease as substitution rate increases, and table flow tends to decrease as substitution rate increases. Through this experiment, 30% of the replacement rate of bamboo activated carbon is judged to be the most suitable replacement rate.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.55-64
• /
• 2019

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

• Journal of Sensor Science and Technology
• /
• v.30 no.6
• /
• pp.429-435
• /
• 2021

In this study, the creation of emotional dialogue was investigated within the process of developing a robot's natural language understanding and emotional dialogue processing. Unlike an English-based dataset, which is the mainstay of natural language processing, the Korean-based dataset has several shortcomings. Therefore, in a situation where the Korean language base is insufficient, the Korean dataset should be dealt with in detail, and in particular, the unique characteristics of the language should be considered. Hence, the first step is to base this study on a specific Korean dataset consisting of conversations on emotional topics. Subsequently, a model was built that learns to extract the continuous dialogue features from a pre-trained language model to generate sentences while maintaining the context of the dialogue. To validate the model, a chatbot system was implemented and meaningful results were obtained by collecting the external subjects and conducting experiments. As a result, the proposed model was influenced by the dataset in which the conversation topic was consultation, to facilitate free and emotional communication with users as if they were consulting with a chatbot. The results were analyzed to identify and explain the advantages and disadvantages of the current model. Finally, as a necessary element to reach the aforementioned ultimate research goal, a discussion is presented on the areas for future studies.

• Journal of Smart Tourism
• /
• v.3 no.1
• /
• pp.41-47
• /
• 2023

Tourism and hospitality have encountered significant changes in recent years as a result of the rapid development of information technology (IT). Customers now expect more expedient services and customized travel experiences, which has intensified competition among service providers. To meet these demands, businesses have adopted sophisticated IT applications such as ChatGPT, which enables real-time interaction with consumers and provides recommendations based on their preferences. This paper focuses on the AI support-prompt middleware system, which functions as a mediator between generative AI and human users, and discusses two operational rules associated with it. The first rule is the Information Processing Rule, which requires the middleware system to determine appropriate responses based on the context of the conversation using techniques for natural language processing. The second rule is the Information Presentation Rule, which requires the middleware system to choose an appropriate language style and conversational attitude based on the gravity of the topic or the conversational context. These rules are essential for guaranteeing that the middleware system can fathom user intent and respond appropriately in various conversational contexts. This study contributes to the planning and analysis of service design by deriving design rules for middleware systems to incorporate artificial intelligence into tourism services. By comprehending the operation of AI support-prompt middleware systems, service providers can design more effective and efficient AI-driven tourism services, thereby improving the customer experience and obtaining a market advantage.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.335-336
• /
• 2022

본 논문에서는 시간대와 대화 주제를 활용하여 카테고리별로 적절한 SNS 광고 시간대 예측 방법을 제시한다. 위의 분석으로 광고주들에게 적절한 광고시간을 제안할 수 있다. 연관규칙분석 알고리즘인 apriori를 사용하였다. 주제는 상거래(쇼핑), 미용과 건강, 시사/교육, 식음료, 여가생활로 추려서 분석하였다. 연관분석 결과, 미용과 건강이 18시, 17시, 16시에 가장 활발히 대화를 나누었다. 상거래(쇼핑)이 14시, 16시, 17시 순으로 가장 활발히 대화를 나누었으며, 시사/교육이 15시, 17시, 16시 순으로 많은 대화를 나누었으며, 식음료가 18시, 17시, 19시 순으로 대화를 많이 나눈 것을 확인했다. 마지막으로, 여가생활은 22시, 23시, 21시 순으로 각각의 대화 주제별로 가장 많이 대화를 나눈 시간대가 달라지는 것을 확인할 수 있었다. 이를 통해 소비자 입장에서는 알맞은 광고를 적절한 시간대에 추천받을 수 있다.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.256-262
• /
• 2020

Since the discussion of Korean writing education began in earnest, the biggest topic of conversation has been genre writing education. And academic writing has become one of the most important research topics in Korean writing education in the past and present days as demand for academic-purpose Korean language education has increased. Academic writing is an area of writing, which is distinct from literary writing as well as practical writing. It takes place with a set of information provided on a particular academic topic or research problem, which generally includes arguments and views on the subject, analyses and criticisms of the issue in question, and alternatives for new perspectives and problem solving. Academic Purpose Korean learners learn Korean for the purpose of academic training. Academic-purpose Korean learners will use the Korean language to write academic articles, and inevitably carry out analytical writing tasks in the process. This paper aims to explore what is the task of analytical writing given to foreign students and to grasp the research problems necessary to educate them. When foreign students encountered analytical writing as an academic writing task, they wanted to clarify what areas of education should be conducted with attention.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.257-262
• /
• 2013

In mobile market which has been developed drastically, short distance mobile Near Field Communication is becoming the conversation topic. Google adopted this NFC technology to Android 플랫폼 for securing the leadership and many another countries including domestic companies are putting spurs to develop service and technology by connecting mobile carrier and the financial. Within this circumstance, most noticeable issue is securing stability of nfc application service. Android 플랫폼 is operating system of mobile device and also a software stack which is required limited hardware and immediate response. However, since its structural characteristic which is suitable for limited hardware, the response is not quite stable for real time process. That is, this paper researches by analyzing real time response of NFC related library provided from Android 플랫폼 and applying the result to NFC application for securing stable data process and response.

• The Journal of Korean Association of Computer Education
• /
• v.13 no.3
• /
• pp.77-90
• /
• 2010

e-learning standardization has already had a major impact on budget reduction goals through the application of national policy projects such as Cyber Home Learning System and Digital Textbook. It also corresponds with green paradigm, recently attracting more attention, by contributing to reduce carbon dioxide through preventing duplicate development. In the 21st century the concept of convergence and the role of e-learning standardization to unite education and technology have gained popularity on conversation topic agendas. This research is aimed at establishing strategic countermeasures for international standards and help plot the direction for future standardization policy through the development of a mid-to long term roadmap using delphi research targeted at e-learning standardization experts. In addition, it attempts to establish a broad base to improve standardization awareness and diffusion.