• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.726-727
• /
• 2012

본 논문에서는 스마트 디바이스기반의 실시간 지식공유 시스템 설계를 제안한다. 스마트 디바이스기반의 실시간 지식공유 시스템은 사용자의 스마트 디바이스에 저장되어있는 지인들을 연결하여 실시간으로 질문과 답변을 할 수 있는 기능을 제공하고 사용자 질문에 대한 웹 검색 결과를 제공한다. 또한 사용자간의 질문, 답변 결과를 서버에 저장하여 축적시키고 추천 기능을 제공하여 다른 사용자가 유사한 질문을 할 경우 축적된 질문과 답변을 제공한다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.347-350
• /
• 2019

인공지능 관련 기술의 발달로 다양한 분야에서 인공지능 활용에 대한 관심이 고조되고 있으며 전문영역에서도 기계학습 기법을 활용한 연구들이 활발하게 이루어지고 있다. 특허청에서는 분야별 전문지식을 가진 분류담당자가 출원되는 모든 특허에 국제특허분류코드(이하 IPC) 부여 작업을 수행하고 있다. IPC 분류와 같은 전문적인 업무영역에서 딥러닝을 활용한 자동 IPC 분류 서비스를 제공하기 위해서는 기계학습을 이용하는 분류 모델에 분야별 전문지식을 직관적으로 반영하는 것이 필요하다. 이를 위해 본 연구에서는 딥러닝 기반의 IPC 분류 모델과 전문지식이 반영된 분류별 어휘사전을 활용한 규칙기반 분류 모델을 병행하여 특허문서의 IPC분류를 자동으로 추천하는 방법을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.489-498
• /
• 2012

This paper consists of two parts: In the first part, we describe our work to build hierarchical knowledge base of digital library patron's research interests and learning topics in various scholarly areas through analyzing well classified Electronic Theses and Dissertations (ETDs) of NDLTD Union catalog. Journal articles from ACM Transactions and conference web sites of computing areas also are added in the analysis to specialize computing fields. This hierarchical knowledge base would be a useful tool for many social computing and information service applications, such as personalization, recommender system, text mining, technology opportunity mining, information visualization, and so on. In the second part, we compare four grouping algorithms to select best one for our data mining researches by testing each one with the hierarchical knowledge base we described in the first part. From these two studies, we intent to show traditional verification methods for social community miming researches, based on interviewing and answering questionnaires, which are expensive, slow, and privacy threatening, can be replaced with systematic, consistent, fast, and privacy protecting methods by using our suggested hierarchical knowledge base.

• The Journal of Society for e-Business Studies
• /
• v.12 no.1
• /
• pp.99-122
• /
• 2007

The rule based system is inference engine which can correspond quickly to new business model change and improvement requirement by dealing with the business know-how and expert knowledge as well as business process of enterprise and has been trying to apply to the various industries. As a part of application cases for rule-based system, we develop and implement the rule-based insurance product recommend and design system for the efficient decision making of insurance product in insurance industry which is sensitively affected by needs of customers, various kinds of product, and environment changes. The process of fuzzy inference of the developed system helps to recommend and design the proper Insurance product using the information of the present customer and the previous members. This approach is expected that it will be the core technology for the recommendation and design of the tailored insurance product by deciding and corresponding needs of various kinds of customer quickly in future insurance industry.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.1
• /
• pp.31-36
• /
• 2019

A chatbot is an important area of mobile service, which understands informal data of a user as a conversational form and provides a customized service information for user. However, there is still a lack of a service way to fully understand the user's natural language typed query dialogue. Therefore, in this paper, we extract meaningful words, such a region, a food category, and a restaurant name from user's dialogue sentences for recommending a restaurant. and by comparing the extracted words against the contents of the knowledge database that is built from the hashtag for recommending a restaurant in SNS, and provides user target information having statistically much the word-similarity. In order to evaluate the performance of the restaurant recommendation chatbot system implemented in this paper, we measured the accessibility of various user query information by constructing a web-based mobile environment. As a results by comparing a previous similar system, our chabot is reduced by 37.2% and 73.3% with respect to the touch-count and the cutaway-count respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.91-102
• /
• 2012

Computer aided language learning has become popular. But the level of automation of constructing a Korean learning assistant system is not so high because a practical language learning system needs large scale knowledge resources, which is very hard to acquire. In this paper, we propose a Korean learning assistant system that utilizes easily obtainable knowledge resources like a corpus, web documents and a lexicon. Our system has three modules - problem solving, pronunciation marker and writing assistant. Automatic problem generator uses a corpus and a lexicon to make problems with one correct answer and three distracters, then verifies their suitability by utilizing frequency information from web documents. We analyze pronunciation rules for a pronunciation marker and recommend appropriate words and sentences in real-time by using data extracted from a corpus. In experiment, we evaluate 400 automatically generated problems, which show 89.9% problem suitability and 64.9% example suitability.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.1
• /
• pp.11-21
• /
• 2008

In advance of Knowledge Information Society, mentoring is becoming an efficient method for developing and managing human resources. There are several factors to improve the effect of mentoring. Among them, a matching mechanism that connects a mentee and a mentor is the most important in mentoring. In the existing e-mentoring systems, administrators rarely consider personal data. They match suitable mentors for mentees in a mandatory way, which reflects bad effects in the e-mentoring. In this paper, we propose new recommendation algorithms for matching by analyzing personal preferences for secondary school students to improve the effects of the mentoring. In addition, we compare our algorithms with the existing algorithms in terms of elaborateness, accordance, and diversity in order to prove the effectiveness of the proposed algorithms.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.5
• /
• pp.390-394
• /
• 2009

The semantic web-based social network is highly useful in a variety of areas. In this paper we make diverse analyses of the FOAF-based social network, and propose an expert recommendation system. This system presents useful method of ontology-based social network using SparQL, RDFS inference, and visualization tools. Then we apply it to real social network in order to make various analyses of centrality, small world, scale free, etc. Moreover, our system suggests method for analysis of an expert on specific field. We expect such method to be utilized in multifarious areas - marketing, group administration, knowledge management system, and so on.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.99-102
• /
• 2008

현재 우리나라에서는 영어에 대한 중요성과 관심이 점점 커지고 있으며, 영어 능력을 평가하는 다양한 시험이 시행 중에 있다. 이런 시험들을 준비하기 위해 많은 문제들은 웹 상에서 손쉽게 구할 수 있는 반면에, 획득한 문제에 대한 정답을 원하는 순간에 구하는 것은 쉽지 않아 영어 문제를 푼 후에 정답을 확인할 수 없는 경우가 많다. 이런 불편함을 줄이기 위해 본 논문은 영어 문제의 정답을 추천해 주는 시스템에 대해서 논의한다. 단문 빈칸 채우기 형식의 문제에 대해서 해당 문제의 문장의 의미에 대한 이해없이도 특정 어휘의 쓰임새나 빈칸 주변의 문맥 정보, 단어들 간의 공기빈도 정보를 이용하여 문제의 정답을 추천한다. 시스템에 필요한 정보를 위한 자료를 웹 상의 수많은 영어 문서들에 기술된 표현을 이용하여 수동 지식 구축과정 없이 문제를 해결한다.

• Journal of KIISE:Software and Applications
• /
• v.35 no.10
• /
• pp.608-615
• /
• 2008

In Knowledge Q&A services where information is created by unspecified users, document quality is an important factor of user satisfaction with search results. Previous work on quality prediction of Knowledge Q&A documents evaluate the quality of documents by using non-textual information, such as click counts and recommendation counts, and focus on enhancing retrieval performance by incorporating the quality measure into retrieval model. Although the non-textual information used in previous work was proven to be useful by experiments, data sparseness problem may occur when predicting the quality of newly created documents with such information. To solve data sparseness problem of non-textual features, this paper proposes new features for document quality prediction, namely text-confidence features, which indicate how trustworthy the content of a document is. The proposed features, extracted directly from the document content, are stable against data sparseness problem, compared to non-textual features that indirectly require participation of service users in order to be collected. Experiments conducted on real world Knowledge Q&A documents suggests that text-confidence features show performance comparable to the non-textual features. We believe the proposed features can be utilized as effective features for document quality prediction and improve the performance of Knowledge Q&A services in the future.