• International Journal of Knowledge Content Development & Technology
• /
• v.8 no.1
• /
• pp.37-50
• /
• 2018

The purpose of the study is to identify the perception of the Library and Information Science (LIS) specialists about the use of mobile phones in retrieving information. It investigates the present status of the LIS specialists regarding mobile phone usage, perceptions regarding the use of mobile phones in retrieving information from libraries and points out the possible drawbacks and their solutions for embracing mobile phones in retrieving information from libraries and providing some suggestions. The methodology includes a quantitative approach. The authors used a survey method using a structured questionnaire to measure the perception of LIS specialists regarding the use of mobile phones in retrieving information from libraries. The findings confirmed that the majority (72%) of LIS specialists have the experience of using mobile phones for more than 10 years. Findings also indicate that the LIS specialists have agreed with the statements of advantages of using mobile phones. This paper concludes that the respondents also agreed regarding the possible advantages of introducing mobile phones in retrieving information from libraries. The paper explores the original perceptions of LIS specialists regarding the use of mobile phones in retrieving information from libraries.

• KIISE Transactions on Computing Practices
• /
• v.23 no.11
• /
• pp.611-616
• /
• 2017

In the area of Information Retrieval, Query Expansion is a well-known technique that uses external knowledge to increase an inquiry generated by users. However, ambiguous words used in the query decrease the performance of search tools. In this paper, we propose a solution to the above problem, by using domain knowledge which identifies the meaning of words in the query. In particular, we present a domain centered query expansion technique that magnifies a query using domains. By comparing with various query expansion models, we demonstrate that the proposed model performs better than the other models.

• The Journal of Society for e-Business Studies
• /
• v.3 no.2
• /
• pp.57-71
• /
• 1998

In this paper, we describe the approaches of shopping agents and directory services for online comparison shopping on the web, and propose an information indexing and retrieval system, named InfoEye, with a new method for automatic extraction of product information. The developed method is based on the knowledge about presentation of the product information on the Web. The method from the knowledge about presentation of the product information is derived from both the point that online stores display their products to customers in easy-to-browse ways and heuristics made of analyses of product information look-and-feel of domestic online stores. In indexing process, the method is applied to product information extraction from Hypertext Markup Language (HTML) documents collected by a mirroring robot from online stores. We have made InfoEye to a readily usable stage and transferred the technology to Webnara commercial shopping engine. The proposed system is a cutting-edge solution to help customers as a shopping expert by providing information about the reasonable price of a product from dozens of online stores, saving customers shopping time, giving information about new products, and comparing quality factors of products in a same category.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.3
• /
• pp.5-27
• /
• 2017

Retrieval of scholarly articles about a specific research issue is a routine job of researchers to cross-validate the evidence about the issue. Two articles that focus on a research issue should share similar terms in their core contents, including their goals, backgrounds, and conclusions. In this paper, we present a technique CCSE ($\underline{C}ore$ $\underline{C}ontent$ $\underline{S}imilarity$ $\underline{E}stimation$) that, given an article a, recommends those articles that share similar core content terms with a. CCSE works on titles and abstracts of articles, which are publicly available. It estimates and integrates three kinds of similarity: goal similarity, background similarity, and conclusion similarity. Empirical evaluation shows that CCSE performs significantly better than several state-of-the-art techniques in recommending those biomedical articles that are judged (by domain experts) to be the ones whose core contents focus on the same research issues. CCSE works for those articles that present research background followed by main results and discussion, and hence it may be used to support the identification of the closely related evidence already published in these articles, even when only titles and abstracts of the articles are available.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.57-64
• /
• 2003

Achieving the beneficiary goal of recent discovery in human genome project still needs a way to retrieve and analyze the exponentially expanding bio-related information. Research on bio-related fields naturally applies knowledge discovered to the current problem and make inferences to extract new information where shared concepts and data containing information need to be defined and used in a coherent way. In such a professional domain, while the need to help users reduce their work and to improve search results has been emerged. methods for systematic retrieval and adequate exchange of relevant information are still in their infancy. The design of our system aims at improving the quality of information retrieval in a professional domain by utilizing both corpus-based and concept-based ontology. Meta-rules of helping users to make an adequate query are formed into an ontology in the domain. The integration of those knowledge permits the system to retrieve relevant information in a more semantic and systematic fashion. This work mainly describes the query models with details of GUI and a secondary query generation of the system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1701-1707
• /
• 2010

This study is intended for implementing the system environment that can help integrate and retrieve various types of data in real-time by providing semantic interoperability among distributed heterogeneous information systems. The semantic interoperability is made possible by providing a TMDR(Topicmaps Metadata Registry), a set of ontologies. TMDR, which has been made by combining MDR(MetaData Registry) and TopicMaps and storing them in the database, is able to generate distributed query and provide efficient knowledge. MDR is a metadata management technique for distributed data management. TopicMaps is an ontology representation technique that takes into consideration the hierarchy and association for accessing knowledge data. We have created TMDR, a kind of ontology, that is fit for any system and able to detect and resolve semantic conflicts on the level of data and schema. With this system we propose a query-processing technique to integrate and access heterogeneous information sources. Unlike existing retrieval methods this makes possible efficient retrieval and reasoning by providing association focusing on subjects.

• The Journal of Information Technology
• /
• v.4 no.2
• /
• pp.69-81
• /
• 2001

In this paper, we examine work in the evolution of content-based retrieval systems that rely on an intelligent infrastructure. Here, we refer to intelligence as the capabilities of the systems to build and maintain situational or world models, utilize dynamic knowledge representations, exploit context and overage advanced reasoning and learning capabilities. We argue that these elements are essential to producing effective systems for retrieving visual information at semantic levels matching those of human perception and cognition. In this paper, we review relevant research on the understanding of human intelligence and construction of intelligent systems in the fields of cognitive psychology, artificial intelligence, semiotics. We also discuss how some of the principal ideas from these fields lead to new opportunities and capabilities for content-based retrieval systems. Finally, we discribe some of our efforts in these directions. In particular, we present MediaNet, a multimedia knowledge presentation framework that facilitate and enable intelligent content-based retrieval.

• Journal of the Korean Society for information Management
• /
• v.20 no.1
• /
• pp.417-455
• /
• 2003

Ontologies are formal theories that are suitable for implementing the semantic web. which is a new technology that attempts to achieve effective retrieval, integration, and reuse of web resources. Ontologies provide a way of sharing and reusing knowledge among people and heterogeneous applications systems. The role of ontologies is that of making explicit specified conceptualizations. In this context, domain and generic ontologies can be shared, reused, and integrated in the analysis and design stage of information and knowledge systems. This study aims to design an ontology for international organizations. and build an Internet web retrieval system based on the proposed ontology. and finally conduct an experiment to compare the system performance of the proposed system with that of internet search engines focusing relevance and searching time. This study found that average relevance of ontology-based searching and Internet search engines are 4.53 and 2.51, and average searching time of ontology-based searching and Internet search engines are 1.96 minutes and 4.74 minutes.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.2
• /
• pp.255-279
• /
• 2017

In a qualitative approach, this study investigated users' perceptions associated with their satisfactions in the process of using the scholarly resource search functions of the academic version of the NAVER search engine. For this study, the data was collected from a group of undergraduate students, who conducted academic information searches in the field of own major disciplinary areas, using the Web portal. Based on the data, students' satisfactions and dissatisfactions along with the reasons of their perceptions were analyzed. The results presented users' perceptions in various evaluation criteria based on the three major domains: system interfaces, retrieval mechanisms and search results. Based on the results, the study proposed the following suggestions: 1) the enhancements of the system interfaces and HELP guidances based the limited user knowledge on basic system terminologies 2) the improvements of the retrieval mechanisms associated with understanding the contexts of the search terms presented by users 3) the necessity of the user education due to the insufficient user knowledge of the retrieval mechanisms and the search functions.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.81-88
• /
• 2024

Despite the rapid growth of the generative AI market and significant interest from domestic companies and institutions, concerns about the provision of inaccurate information and potential information leaks have emerged as major factors hindering the adoption of generative AI. To address these issues, this paper designs and implements a question-answering system based on the Retrieval-Augmented Generation (RAG) architecture. The proposed method constructs a knowledge database using Korean sentence embeddings and retrieves information relevant to queries through optimized searches, which is then provided to the generative language model. Additionally, it allows users to directly manage the knowledge database to efficiently update changing business information, and it is designed to operate in a private network to reduce the risk of corporate confidential information leakage. This study aims to serve as a useful reference for domestic companies seeking to adopt and utilize generative AI.