• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.440-448
• /
• 2019

In this paper, we propose an ordering chatbot that can process multiple keywords based on recursive slot-filling method. In general, in case of an order service using chatbots, the whole order process is performed only according to the sequence defined by the developer. That is, among all the information needed for the whole order process, only one input can be processed at one time. In order to reduce processing step for the order, we propose a recursive slot-filling method which fills out multiple slots per one time by extracting multiple keywords. First, a keyword array for the order is created according to the order related information. Next, from the input sentence of a user, multiple keywords is extracted. Corresponding slots for a keyword array will be filled with the extracted keywords. Finally, recursive routine will be executed to fill out all the blank in the keyword array. The usability and validity of the proposed method will be shown from the implementation of a smartphone application.

• Journal of Information Management
• /
• v.23 no.1
• /
• pp.39-62
• /
• 1992

In this paper about 60 auxiliary words and 320 stopwords are selected from analysis of sample data, four types of stop word are classified left, right and - auxiliary word truncation & normal. And a keyword extraction system is suggested which undertakes efficient truncation of auxiliary word from words, conversion of Chinese word to Korean and exclusion of stopword. The selected keyeords in this system show 92.2% of accordance ratio compared with manually selected keywords by expert. And then compound words consist of $4{\sim}6$ character generate twice of additional new words and 58.8% words of those are useful as keyword.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.170-171
• /
• 2008

연속적인 음성 인식 결과는 띄어쓰기를 하지 않은 연속 음절 문장들로 이루어져 있다. 본 논문은 음성 인식 후처리 단계에서 연속 음절 문장을 조사/어미 사전을 이용한 어절 생성 과정과 형태소 분석기를 이용하여 어절을 생성한 후 키워드를 추출한다. 실험 결과, 어절 생성기만 적용한 방식보다 제안된 알고리즘의 인식률이 향상되는 것을 확인하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.07a
• /
• pp.50-52
• /
• 2015

특허는 기술에 대한 광범위한 정보를 포함하고 있다. 기존의 기술예측은 정량적분석으로 시도되었지만 특허분석을 활용하여 정성적분석을 실시하였다. 특허분석을 시행하기 위하여 R 프로그램을 이용하여 주성분분석과 다중선형회귀분석을 실행하였다. 주성분분석과 다중선형회귀분석을 통하여 키워드를 추출하고 추출된 키워드를 통해 기술예측을 실시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.462-465
• /
• 2021

본 연구는 최근 ICT분야 R&D 동향을 파악하기 위하여 NTIS에서 제공하는 국가연구개발사업 과제정보를 텍스트 마이닝 기법을 통해 분석하였다. 2017년부터 2020까지의 과제 정보에서 키워드를 추출하고 연결 관계 마이닝을 통해 키워드 네트워크를 시각화하였다. 분석 결과는 다음과 같다. 첫째, 정보통신 각 분야에서 핵심 연구주제가 기술의 발전에 따라 변화하고 있음을 관찰하였다. 둘째, 키워드 네트워크 상에서 허브 역할을 하는 키워드를 통해 분야 간 융합의 매개 기술을 파악할 수 있었다. 마지막으로, 연도별 키워드 네트워크를 비교·분석함으로써 새롭게 등장하거나 연결 상태의 변화를 보이는 이머징(Emerging) 키워드를 통해 미래 유망 기술이나 최신 연구 방향성을 감지할 수 있음을 보였다.

• Spatial Information Research
• /
• v.23 no.1
• /
• pp.69-77
• /
• 2015

The aim of this study is to examine the research trends of global scientific production of Geospatial Information (GI) papers from 1998 to 2013 by using keyword network analysis. This study constructed keyword network model through papers and keywords related to GI research retrieved from the Web of Science DB and performed keyword network analysis such as Degree Centrality, Betweenness Centrality, and Closeness Centrality. The results show that GI has been steadily applied to various fields, and also the research trends of GI techniques could be quantitatively characterized through keyword network analysis. This study result can be applied to establish the policies and the national R&D planning of geospatial information.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.95-105
• /
• 2009

There are various studies to provide useful information for users on huge data of web-sites. Web usage mining among them is a method to extract meaningful patterns based on web users' log data. Most of existing patterns of web usage mining, however, had not considered users' diverse inclination but created general models. Web users' keywords can have various meaning upon their tendency and background knowledge. This study is for generating Multi Concept Keyword Model (MCK-Model) by analyzing web usage information on users' keywords of interest. MCK-Model can supply web page network for various inclination based on users' keywords of interest. Also, MCK-Model can be used to recommend the most proper web pages and it has been confirmed that the suggested method is useful enough.

• Journal of the Korean Society for information Management
• /
• v.36 no.2
• /
• pp.105-131
• /
• 2019

The purpose of this study is to investigate the development direction of future scholarship by analyzing recent research trends in collection development and management field using keyword network analysis. Data was collected from four journals in library and information science field during period of 2003 to 2017. Related articles of Collection Development and Management field were retrieved, and author keywords were extracted from selected papers. Keyword network analysis using NetMiner4 program was performed based on frequency analysis, connection-centered analysis, and parametric analysis. The analysis covers all sections from 2003 to 2017 to look at the changes in research over time, and three sections on five-year basis. As a result, main keywords such as 'open access', 'institutional repository' and 'academic journals' were identified, and topics to be continuously researched were identified.

• Journal of the Korean Society for Library and Information Science
• /
• v.58 no.1
• /
• pp.285-302
• /
• 2024

For this article, we conducted frequency analysis, topic modeling, and network analysis on eleven texts related to collection development policy found in the National Library of Korea. We deduced the main keywords related to collection development policies and analyzed the relationship between them. We subsequently conducted a pie coefficient analysis to identify the characteristics of collection development policies of university libraries and public libraries by category. The results showed that keywords such as "material," "library," "collection development," "user," and "collection" were the main keywords in frequency analysis and network centrality. Meanwhile, the pie coefficient analysis revealed that keywords such as "university," "construction," "student," "target," and "cost" were prevalent in university libraries, indicating that the academic needs of users and the discussion of digital resources were primary issues, while keywords related to the information needs of various user groups-including "adults," "survey," "feature," and "religion" -appeared in public libraries.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.305-306
• /
• 2016

식품안전 사고가 발생했을 때 뉴스, 인터넷 기사를 통해 정보를 인지하기 전에 그 음식을 섭취하는 경우가 발생하는 문제점 최소화하기 위하여 실시간 트윗 분석으로 현재 발생한 식품안전 키워드와 어느 지역에서 발생했는지를 신속하게 파악하고, 키워드 연관관계 분석 프로그램을 활용하여 정확한 정보를 추출한다. 이와 더불어, SNS 등 다양한 정보 소스로부터 추출한 정보를 간단명료하게 파악하기 위해서 워드 클라우드 등 데이터 시각화 기법을 활용하여 시각화로 정보를 제공한다. 이 기법은 식품안전 뿐만 아니라 최근 발생한 콜레라 감염 발생과 같은 문제를 해결하기 위한 방법으로 활용될 수 있을 것이다.