• Journal of the HCI Society of Korea
• /
• v.4 no.1
• /
• pp.1-10
• /
• 2009

The knowledge creation in early stages of new service development plays a critical role in the success of the service. The user is a crucial resource in creating knowledge in early stages of development, and user involvement is necessary. There are three roles the user can take part as in service development: informative, consultative, or participative. Based on these different roles, the process of knowledge creation varies. With this background, we proposed to investigate which creative processes need to be passed through in order to positively affect service development based on the role of the user in early stages of Internet service development. This case study was undertaken based on two new projects. The results of this study reveal the relationship between the knowledge creation process and user in early stages of development and at the same time provide guidelines regarding user involvement in actual service development.

• 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.

• Asia pacific journal of information systems
• /
• v.28 no.3
• /
• pp.220-239
• /
• 2018

The purpose of the paper is empirically to explore 'design manner', focusing on the designer's knowledge boundary on the designer-user interactions in the design process. This study conducts a field study and observed designer's interactions with actual users in a leading user-centered design firm over three months. The observations revealed how designers bring ideas about users into design without physically interacting with users during the design process. Based on Bourdieu's theory of practice and the concept of boundary objects, this study introduces the concept of 'design manner', by which designers incorporate user's ideas into the design process without actual involvement of users in the process. This paper contributes to the body of knowledge by introducing the design manner in-between designer's and user's knowledge boundaries and argue bridge between theoretical and actual designer-user interactions in the IS design process.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.75-89
• /
• 2021

A knowledge map should be able to support the referential navigation of knowledge inquiries, i.e., cross- and sequential searches and queries on content relevance-based associated knowledge. This study performs a user-oriented test to verify which type of knowledge map, hierarchical or networked, exhibits superior performance in supporting knowledge inquiries required for problem solving. Both the effectiveness identified by the correct answer rate and the efficiency identified by the number of completion time and reference documents have been revealed superior performance in the networked knowledge map. This study's result can underpin the basic steps to develop more user-friendly and reasonable knowledge services.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.21-32
• /
• 2010

User query formation highly acts on the effectiveness of information retrieval when we retrieve documents from the general domain as a web. This thesis proposes a intelligent information retrieval method based on a cross-lingual knowledge base to effectively perform a cross-lingual text retrieval from the web. The inferred knowledge from the cross-lingual knowledge base helps user's word association to make up user query easily and exactly for effective cross-lingual text information retrieval. This thesis develops user's query reformation algorithm and experiments it with Korean and English web. Experimental results show that the algorithm based on the proposed knowledge base is much more effective than without knowledge base in the cross-lingual text retrieval.

• Knowledge Management Research
• /
• v.9 no.2
• /
• pp.147-167
• /
• 2008

This paper aims to explore the success factors of knowledge management in the perspectives of knowledge management integration into operations and to examine the effect of those factors on the knowledge management performance of individual users and organizations in order to link knowledge management performances to operational performances. I found two factors such as "knowledge management integration into operation processes" and "knowledge management integration into application systems" and their measures by means of literature review and modified Delphi research. Exploratory and confirmatory factor analysis confirmed that those two factors and their measures are statistically valid. Besides, the structural equation modeling analysis showed that the relationship between "knowledge management integration into operation processes" and "individual user's performance on knowledge management" and the relationship between "individual user's performance of knowledge managemen" and "organizational performance of knowledge management" are significant.

• The Journal of Society for e-Business Studies
• /
• v.10 no.3
• /
• pp.111-134
• /
• 2005

Knowledge management is a core factor to achieve competitive advantage and improve the business performance. New information technology is also a core factor enabling the innovation of knowledge management. Semantic Web of which the goal is to realize machine-processable Web can't help affecting the knowledge management. Therefore, we empirically analyze the relationship between user's dissatisfaction and barriers or limitations of knowledge management and present methods allowing Semantic Web to overcome the limitations and to support knowledge management processes. Based on a questionnaire survey of 222 respondents, we found that the limitations of system qualities such as user inconvenience of knowledge management systems, search and integration limitations, and the limitations of knowledge qualities such as inappropriateness and untrust significantly affected the user dissatisfaction of knowledge management systems. Finally, we suggest a conceptual model of knowledge management systems of which components are resources, metadata, ontologies, and user & query layers.

• Journal of Korean Library and Information Science Society
• /
• v.35 no.4
• /
• pp.423-449
• /
• 2004

In the knowledge society the main resource is knowledge, and the role of library to manage knowledge and information is very important. Therefore it is necessary to knowledge and information management that provides on demand service to user. The purpose of this research is to design model for web-based help-desk knowledge management system. This study used Qualitative methods as interviews and surveys through BBS and e-mail on information service in the university libraries. Here the investigated component factors are followings Q/A service user's education service to use the library, user's online reference service, e-mail service, FAQ service electronic service(BBS), lecture and research service for faculty, my library, SDI service, and open data service. This study was financially supported by Chonnam National University in the program, Post-Doc. 2002.

• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.1-18
• /
• 2024

With the increasing demand for and utilization of large language models (LLMs), the risk of user sensitive information being inputted and leaked during the use of LLMs also escalates. Typically recognized as a tool for mitigating the hallucination issues of LLMs, knowledge graphs, constructed independently from LLMs, can store and manage sensitive user information separately, thereby minimizing the potential for data breaches. This study, therefore, presents a knowledge graph-based chatbot that transforms user-inputted natural language questions into queries appropriate for the knowledge graph using LLMs, subsequently executing these queries and extracting the results. Furthermore, to evaluate the functional validity of the developed knowledge graph-based chatbot, performance tests are conducted to assess the comprehension and adaptability to existing knowledge graphs, the capability to create new entity classes, and the accessibility of LLMs to the knowledge graph content.

• Journal of Information Technology Applications and Management
• /
• v.12 no.4
• /
• pp.45-57
• /
• 2005

In order to provide personalized knowledge recommendation services, most web portals for organizational knowledge management use category or keyword information that portal users explicitly express interests in. However, it is usually difficult to collect correct preference data for all users with this approach, and, moreover, users' preferences may easily change over time, which results In outdated user profiles and impaired recommendation qualify. In order to address this problem, this paper suggests knowledge recommendation methods for portals using user profiles that are automatically constructed from users' activities such as posting or uploading of articles and documents. The result of our experiment shows that the Proposed method can provide equivalent performance with the manual category or keyword selection method.