• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.27-38
• /
• 2023

In this paper, we propose a conversational AI agent based on continual learning that can continuously learn and grow with new data over time. A continual learning-based conversational AI agent consists of three main components: Task manager, User attribute extraction, and Auto-growing knowledge graph. When a task manager finds new data during a conversation with a user, it creates a new task with previously learned knowledge. The user attribute extraction model extracts the user's characteristics from the new task, and the auto-growing knowledge graph continuously learns the new external knowledge. Unlike the existing conversational AI agents that learned based on a limited dataset, our proposed method enables conversations based on continuous user attribute learning and knowledge learning. A conversational AI agent with continual learning technology can respond personally as conversations with users accumulate. And it can respond to new knowledge continuously. This paper validate the possibility of our proposed method through experiments on performance changes in dialogue generation models over time.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.1
• /
• pp.137-161
• /
• 2024

Professional competencies serve to demonstrate and develop expertise. As such, the study summarized theories on the concept of competency and competency model development and utilization, proposing ways to utilize the competency system to strengthen domestic archivists' expertise through a case study of international archivist competency systems. Five competency frameworks for archivists developed by international archivist associations were analyzed. Results showed that the archival profession's competency frameworks were primarily utilized in two ways. First, they are used to verify professional definitions, which are used as verification standards for registering certified professionals at the archivist association level. Second, they are used to enhance expertise in conjunction with individual professional self-assessment and continuing professional development program design. These two applications can operate in a complementary relationship to utilize the competency framework in demonstrating and strengthening competencies.

• The Journal of Society for e-Business Studies
• /
• v.26 no.4
• /
• pp.37-52
• /
• 2021

Due to the spread of COVID-19, it is rapidly changing from face-to-face to non-face-to-face work environments and is changing to a digital work environment that can be accessed anytime, anywhere, providing convenience to all lives. However, the number of breaches, personal information leakage, and technology leakage targeting SMEs that are vulnerable to security continues to increase. Accordingly, the government has been continuously promoting the information security consulting support project for SMEs every year since 2014. Therefore, this study intends to develop a performance model and measurement methodology for continuous and more systematic support and efficient management of information protection support projects in consideration of the importance of information security for SMEs. It is intended to be used as basic data when setting future operational directions and goals. The main method of this study is to derive performance models and indicators for SME information security support projects based on domestic literature, case studies, and survey results, utilize expert advice to verify the developed performance measurement indicators, and use pilot-test questionnaires. Conduct evaluation through surveys. Based on the verified indicators, we would like to present a performance model and measurement index for the information security support project for SMEs.

• TTA Journal
• /
• s.139
• /
• pp.40-43
• /
• 2012

주로 컴퓨터 자원(Platform, HDD, CPU)의 가상화를 통한 IT 인프라 관리 및 아웃소싱의 효율성을 추구하던 클라우드 컴퓨팅이 이제는 다양한 서비스 분야로 전환되고 있다. 심지어 사용자의 개인 데이터, 홈 가전기기, 헬스 기기 등의 모든 디지털화된 IT 자원이 스마트 폰, 태블릿 PC, IP-TV 중심의 N-Screen 등의 사용자 단말 기술들과 연계 및 진화하여 더욱 편리한 디지털 라이프의 변화를 주도하고 있다. 따라서 본 특집에서는 더욱 발전하는 클라우드 컴퓨팅의 주요 분야들 - 모바일 클라우드, DaaS(Desktop as a Service: 데스크톱 클라우드), 공공 부문의 SLA(Service Level Agreement), 퍼스널 클라우드 보안과 프라이버시 - 대해 기술적 동향과 이슈 등을 고찰하고자 한다. 특히 작금의 국제적 표준화가 ITU-T, ISO에서 조직과 체계를 구체적으로 마련하고 2012년부터는 본격적인 경쟁에 들어가는 중요한 시대적 위치에 있으므로 본 특집을 통해 국내 연구자 및 개발자들에게 표준화된 기술 및 서비스 개발에 동기를 부여하고자 한다. 본 특집을 기획하면서 클라우드 컴퓨팅은 IT의 인프라에서 응용까지 연계되어 서비스 산업의 좋은 모델로서 국가적 경쟁력을 끌어올릴 수 있는 중요한 기술임이 자명하며, 단기적으로 끝나는 기술이 아님을 다시 한 번 확인할 수 있는 좋은 기회로 산업의 많은 분야에 뿌리 깊이 내려지길 기대해 본다. 이를 위해 기업과 국가의 지속적인 개발과 지원에 대한 결정이 그 어느 때보다 필요하다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.285-301
• /
• 2023

Due to the increasing demand and importance of non-face-to-face education, open online learning platforms are getting interests both domestically and internationally. These platforms exhibit different characteristics from online courses by universities and other educational institutions. In particular, students engaged in these platforms can receive more learner autonomy, and the development of tools to assist learning is required. From the past, researchers have attempted to utilize process mining to understand realistic study behaviors and derive learning patterns. However, it has a deficiency to employ it to the open online learning platforms. Moreover, existing research has primarily focused on the process model perspective, including process model discovery, but lacks a method for the process pattern and instance perspectives. In this study, we propose a method to identify learning patterns within an open online learning platform using process mining techniques. To achieve this, we suggest three different viewpoints, e.g., model-level, variant-level, and instance-level, to comprehend the learning patterns, and various techniques are employed, such as process discovery, conformance checking, autoencoder-based clustering, and predictive approaches. To validate this method, we collected a learning log of machine learning-related courses on a domestic open education platform. The results unveiled a spaghetti-like process model that can be differentiated into a standard learning pattern and three abnormal patterns. Furthermore, as a result of deriving a pattern classification model, our model achieved a high accuracy of 0.86 when predicting the pattern of instances based on the initial 30% of the entire flow. This study contributes to systematically analyze learners' patterns using process mining.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.319-325
• /
• 2019

The importance of social responsibility is growing, and as a result of social awareness, many universities and institutions are carrying out community service activities. Although the volunteer portal site has excellent performance and good accessibility, the overall service performance of a specific organization cannot be managed because of personal information. Almost community service managers of a organization manually manage their community service activities without the support of a community service management program. In this study, have been feature analysis of existing portal site for volunteer coordination, then a prototype was designed and developed as a model of social contribution management system so that universities and organizations can systematically support and manage the social service activities of members based on the questionnaire about social contribution management system.

• Journal of Information Management
• /
• v.40 no.1
• /
• pp.199-215
• /
• 2009

The web 2.0 concept rapidly spreads to the various field which is based on an opening, the participation, and a share. And the research about the recommendation system, that is the personalize feature, and social network is very active. In the case of the recommendation system and social network, it had been developing in the respectively different area and the new research toward the service model of a form that it fuses these is insignificant. In this paper, I'm going to introduce efficient social network which is called the researcher connection network. It is possible to recommend the researcher intellectually who studies the similar field by analyzing the usage log and user profile. Through this study, we could solved the network expandability problem which is due to the user passive participation and the difficulty of the initial network construction that is the conventional social network problem.

• Journal of Platform Technology
• /
• v.10 no.1
• /
• pp.20-28
• /
• 2022

Artificial intelligence-based health data verification has become an essential element not only to help clinical research, but also to develop new treatments. Since the US Food and Drug Administration (FDA) approved the marketing of medical devices that detect mild abnormal diabetic retinopathy in adult diabetic patients using artificial intelligence in the field of medical diagnosis, tests using artificial intelligence have been increasing. In this study, an artificial intelligence model based on image classification was created using a Teachable Machine supported by Google, and a predictive model was completed through learning. This not only facilitates the early detection of cataracts among eye diseases occurring among patients with chronic diseases, but also serves as basic research for developing a digital personal health healthcare app for eye disease prevention as a healthcare program for eye health.

• The KIPS Transactions:PartA
• /
• v.10A no.4
• /
• pp.381-388
• /
• 2003

Location tracking is used to keep track of the location information of a mobile terminal in an idle state for a cail setup between mobile terminals. In this paper, we introduce a location update algorithm based on the call arrival history, which is appropriate for a variable call arrival rate over time. The location tracking strategy which uses the proposed algorithm can find changes in the call arrival rate by maintaining a call arrival history of a mobile terminal, from which a mobile terminal can calculate an appropriate timeout interval for a variable call arrival rate. We show that the proposed scheme is appropriate for a variable call arrival rate by presenting a simple analytical model and analytical results to investigate its performance for both a fixed and a variable call arrival rate.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.139-147
• /
• 2013

As the use of wired and mobile Internet is on the increase, organizational activities for customers as well as individual life style are changing rapidly from the past. Specifically, mobile advertising in organizations thanks to remarkable growth in smartphone users, continuous development of mobile Internet technologies, and enhancement of information delivery capability regardless of time and place, has become a competitive weapon for presenting new products and services, promoting marketing programs, and communicating with customers. The study is to investigate what characteristics of mobile advertising are affecting the acceptance toward mobile advertising, and to analyse if the country type of mobile Internet users has a moderating effect on the relationship between these characteristics of mobile advertising and user acceptance.