• Title/Summary/Keyword: 키워드-기반 시스템

Search Result 516, Processing Time 0.035 seconds

Query expansion by Similar words Using LSI (잠재적 의미 색인을 이용한 유사 질의어 확장)

  • Lim, Tae Hun;An, Dong Un;Chung, Seong Jong
    • Annual Conference on Human and Language Technology
    • /
    • 2009.10a
    • /
    • pp.165-169
    • /
    • 2009
  • 오늘날 인터넷 검색은 하루가 다르게 발전되고 있다. 주로 키워드 매칭에 의존을 둔 지금의 검색 서비스들은 사용자 중심의 아이템들을 개발해 정보검색의 경과시간 및 결과의 분류면에서 우수함을 보여주고 있다. 질의어의 의미에 유사한 검색은 아직은 발전하는 단계로, 내용에 기반을 둔 검색 환경에 초점이 맞춰지고 있다. 이와 관련하여 행렬의 특이치 분해(SVD)를 이용한 잠재적 의미 색인 기법(LSI)을 본 연구에서 다루고자 한다. 구축한 시스템의 성능 평가는 재현도 계산으로 비교되었는데 작은 크기의 특이값(singular value)들 생략에 의한 SVD의 성능과 그것을 재이용, 질의어에 대한 의미 구조상 근접한 용어들을 찾아 질의어를 확장한 후 적합한 문서들의 검색을 사용한 특이값 개수, 유사단어 확장 개수를 달리하여 실험하였다. 실험 결과, 특이값 2개를 사용한 잠재적 의미 색인이 특이값 3개를 사용한 잠재적 의미 색인보다 보다 나은 성능을 보였다. 그리고 조건을 달리한 모든 잠재적 의미 색인의 경우 단어 매칭에 의한 적합문서 검색보다 별 뚜렷한 나은 결과는 보이지 않았다. 하지만 의미적으로 관계가 깊은 유사어들을 찾아냈고, 의미적으로 가장 관계 깊은 문서를 대부분의 경우에서 순위 1위로 찾아내는 부분적 우수함을 보였다.

  • PDF

Reliable Image-Text Fusion CAPTCHA to Improve User-Friendliness and Efficiency (사용자 편의성과 효율성을 증진하기 위한 신뢰도 높은 이미지-텍스트 융합 CAPTCHA)

  • Moon, Kwang-Ho;Kim, Yoo-Sung
    • The KIPS Transactions:PartC
    • /
    • v.17C no.1
    • /
    • pp.27-36
    • /
    • 2010
  • In Web registration pages and online polling applications, CAPTCHA(Completely Automated Public Turing Test To Tell Computers and Human Apart) is used for distinguishing human users from automated programs. Text-based CAPTCHAs have been widely used in many popular Web sites in which distorted text is used. However, because the advanced optical character recognition techniques can recognize the distorted texts, the reliability becomes low. Image-based CAPTCHAs have been proposed to improve the reliability of the text-based CAPTCHAs. However, these systems also are known as having some drawbacks. First, some image-based CAPTCHA systems with small number of image files in their image dictionary is not so reliable since attacker can recognize images by repeated executions of machine learning programs. Second, users may feel uncomfortable since they have to try CAPTCHA tests repeatedly when they fail to input a correct keyword. Third, some image-base CAPTCHAs require high communication cost since they should send several image files for one CAPTCHA. To solve these problems of image-based CAPTCHA, this paper proposes a new CAPTCHA based on both image and text. In this system, an image and keywords are integrated into one CAPTCHA image to give user a hint for the answer keyword. The proposed CAPTCHA can help users to input easily the answer keyword with the hint in the fused image. Also, the proposed system can reduce the communication costs since it uses only a fused image file for one CAPTCHA. To improve the reliability of the image-text fusion CAPTCHA, we also propose a dynamic building method of large image dictionary from gathering huge amount of images from theinternet with filtering phase for preserving the correctness of CAPTCHA images. In this paper, we proved that the proposed image-text fusion CAPTCHA provides users more convenience and high reliability than the image-based CAPTCHA through experiments.

A Personalized Product Recommendation Agent on Mobile Internet (무선인터넷 환경에서의 개인화상품추천에이전트)

  • 이승화;이은석
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2004.04b
    • /
    • pp.145-147
    • /
    • 2004
  • 본 논문에서는 무선인터넷 환경에 적합한 개인화된 상품추천에이전트를 제안한다. 기존에 유선인터넷상의 많은 개인화 추천시스템에서는 초기 사용자 모델링을 위해 사용자에게 수많은 질의를 하고 응답을 요구하였다. 그러나 이러한 방식은 무선인터넷 환경에서 정보 전송량에 따른 높은 사용요금을 고려할 때 적용하기 힘든 방식이다. 본 제안 시스템은 사용자의 Social data률 이용하여 사용자를 비슷한 연령과 성별 그룹으로 나누고, 해당 그룹에서 구매율이 높은 상품을 우선 제시한 후, 사용자 행동을 모니터링 하여 암시적(Implicit)피드백을 통해 프로파일을 생성함으로써, 번거로운 질의-응답 과정 없이도 초기 사용자 모델링을 수행할 수 있다. 프로파일 생성 이후에는 이를 기반으로 하여 사용자몰 유사한 취향을 가진 그룹으로 다시 군집화한 후 협력적 추천을 하게 되며, 프로파일에는 해당 상품의 최종 카테고리명과 키워드를 수집함으로써, 상품의 브랜드와 규격정보를 반영한 추천이 가능하다. 또한 추천 상품과 사용자의 구매데이터와의 비교를 수행하여 사용자가 해당상품을 구매하였을 경우, 상품에 대한 취향정보는 그대로 유지하고 관련 상품을 추천하되, 구매한 상품이 중복 추천되지 않도록 하였다. 시스템 평가를 위해 프로토타입을 구현하여, 다수의 사용자에게 시스템을 이용하며 관심품목을 체크하도록 하였고. 추천횟수가 반복되며 히트율이 증가하는 결과를 통해 시스템의 학습속도와 성능을 평가하였다. 그리고 쇼핌몰에서 구매경험이 있는 사용자의 기존 구매데이터와 Social data를 이용한 초기 제시상품을 역으로 비교하여 오랜 시간과 비용 발생 없이도 초기 프로파일 생성의 유효성을 증명하였다. 포함하는 XML 질의에 대해서도 웹에서 캐쉬를 이용한 처리가 효율적임을 확인하였다.키는데 목적이 있다.RED에 비해 향상된 성능을 보여주었다.웍스 네트워크상의 다양한 디바이스들간의 네트워크 다양화와 분산화 기능을 얻을 수 있었고, 기존의 고가의 해외 솔루션인 Echelon사의 LonMaker 소프트웨어를 사용하지 않고도 국내의 순수 솔루션인 리눅스 기반의 LonWare 3.0 다중 바인딩 기능을 통해 저 비용으로 홈 네트워크 구성 관리 서버 시스템 개발에 대한 비용을 줄일 수 있다. 기대된다.e 함량이 대체로 높게 나타났다. 점미가 수가용성분에서 goucose대비 용출함량이 고르게 나타나는 경향을 보였고 흑미는 알칼리가용분에서 glucose가 상당량(0.68%) 포함되고 있음을 보여주었고 arabinose(0.68%), xylose(0.05%)도 다른 종류에 비해서 다량 함유한 것으로 나타났다. 흑미는 총식이섬유 함량이 높고 pectic substances, hemicellulose, uronic acid 함량이 높아서 콜레스테롤 저하 등의 효과가 기대되며 고섬유식품으로서 조리 특성 연구가 필요한 것으로 사료된다.리하였다. 얻어진 소견(所見)은 다음과 같았다. 1. 모년령(母年齡), 임신회수(姙娠回數), 임신기간(姙娠其間), 출산시체중등(出産時體重等)의 제요인(諸要因)은 주산기사망(周産基死亡)에 대(對)하여 통계적(統計的)으로 유의(有意)한 영향을 미치고 있어 $25{\sim}29$세(歲)의 연령군에서, 2번째 임신과 2번째의 출산에서 그리고 만삭의 임신 기간에, 출산시체중(出産時體重) $3.50{\sim}3.99kg$사이의 아

  • PDF

A Technique for Requirements Normalization and Selection based on Practical Approach (사례 기반의 요구사항 정형화 및 선정 평가 기법)

  • Byun, Jung-Won;Rhew, Sung-Yul;Kim, Jin-Su
    • Journal of the Korea Society of Computer and Information
    • /
    • v.17 no.11
    • /
    • pp.149-161
    • /
    • 2012
  • In the customer-centered world, which is used internet and social network services actively, it is important that their needs should be embraced into systems. Our study proposes a technique to normalize and select 1,800 customer's needs at C company. In order to normalize the requirements, we have specified requirements by considering a standard for requirements specification, have identified a set of keywords of requirements and have constructed a relation-graph of requirements. The graph presents objectives to design and build a system, and shows a degree of relative importance for each requirement. And then, we propose a techniques for requirements selection according to their contribution points, which are calculated using relative degree. We demonstrates our techniques by a case study of C company.

Food Ontology Model for a Healthcare Service (헬스케어 서비스를 위한 푸드 온톨로지 모델)

  • Lee, Byung Mun
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.17 no.6
    • /
    • pp.31-40
    • /
    • 2012
  • Ubiquitous technology influences on various firms of contents needed for self-healthcare, as it fuses into medical services. Particularly, rapid changes in the web and mobile environment, requiring various sorts of healthcare and its related contents, make efficiency of search more important. Personalized contents needs to be more refined as well as the existing simple keyword-centered searching method needs to be more effective in order to meet both requirements and characteristics of each patient or each user. A precise semantic searching method is required for a system to understand promptly the meaning of a contents. In this respect, to build a healthcare ontology has its own significance. This study builds up a system model that can be utilized practically in existing systems by setting up the Food Class and its sub-class among the healthcare contents with Protege tool and then materializing constraints and its relationships between each class. The healthcare contents ontology provides patients or users with a platform which can search the needed information promptly and precisely.

A VoiceXML-based EPG Retrieval System (VoiceXML기반 EPG 검색 시스템)

  • 김한수;황인준
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.10 no.4
    • /
    • pp.351-363
    • /
    • 2004
  • Recent commencement of digital broadcasting has enabled various TV programs through hundreds of channels. As a result, it becomes a time-consuming job for the TV audience to look up newspaper or TV magazines for the schedule of a specific TV program. To relieve this problem, digital broadcasting usually provides an EPG(Electronic Program Guide) for the audience. Currently. most EPG services are focusing on the visual delivery of information through a web site, digital TV or mobile devices. However, this approach could cause a serious restriction to some users including drivers or visually handicapped persons, who can't input keywords for the search. In order to solve this problem, in this paper, we propose a VoiceXML-based EPG retrieval system that enables even such special users to browse EPG. conveniently using a mobile phone. We implemented a prototype system and proved its effectiveness through experiments.

Automatic Electronic Medical Record Generation System using Speech Recognition and Natural Language Processing Deep Learning (음성인식과 자연어 처리 딥러닝을 통한 전자의무기록자동 생성 시스템)

  • Hyeon-kon Son;Gi-hwan Ryu
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.3
    • /
    • pp.731-736
    • /
    • 2023
  • Recently, the medical field has been applying mandatory Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) systems that computerize and manage medical records, and distributing them throughout the entire medical industry to utilize patients' past medical records for additional medical procedures. However, the conversations between medical professionals and patients that occur during general medical consultations and counseling sessions are not separately recorded or stored, so additional important patient information cannot be efficiently utilized. Therefore, we propose an electronic medical record system that uses speech recognition and natural language processing deep learning to store conversations between medical professionals and patients in text form, automatically extracts and summarizes important medical consultation information, and generates electronic medical records. The system acquires text information through the recognition process of medical professionals and patients' medical consultation content. The acquired text is then divided into multiple sentences, and the importance of multiple keywords included in the generated sentences is calculated. Based on the calculated importance, the system ranks multiple sentences and summarizes them to create the final electronic medical record data. The proposed system's performance is verified to be excellent through quantitative analysis.

A Technique for Extracting GeoSemantic Knowledge from Micro-blog (마이크로 블로그기반의 공간 지식 추출 기법연구)

  • Ha, Su-Wook;Nam, Kwang-Woo;Ryu, Keun-Ho
    • Spatial Information Research
    • /
    • v.20 no.2
    • /
    • pp.129-136
    • /
    • 2012
  • Recently international organizations such as ISO/TC211, OGC, INSPIRE (Infrastructure for Spatial Information in Europe) make an effort to share geospatial data using semantic web technologies. In addition, smart phone and social networking services enable community-based opportunities for participants to share issues of a social phenomenon based on geographic area, and many researchers try to find a method of extracting issues from that. However, serviceable spatial ontologies are still insufficient at application level, and studies of spatial information extraction from SNS were focused on user's location finding or geocoding by text mining. Therefore, a study of extracting spatial phenomenon from social media information and converting it into geosemantic knowledge is very usable. In this paper, we propose a framework for extracting keywords from micro-blog, one of the social media services, finding their relationships using data mining technique, and converting it into spatiotemopral knowledge. The result of this study could be used for implementing a related system as a procedure and ontology model for constructing geoseem antic issue. And from this, it is expected to improve the effectiveness of finding, publishing and analysing spatial issues.

User Preference based Intelligent Program Guide (사용자 선호도 기반 지능형 프로그램 가이드)

  • 류지웅;김문철;남제호;강경옥;김진웅
    • Journal of Broadcast Engineering
    • /
    • v.7 no.2
    • /
    • pp.153-167
    • /
    • 2002
  • With the advent of digital broadcasting, a large number of program channels become available at the user terminals such as set-top-box or PC. Channel navigation and searching become more difficult at TV terminal sides using a conventional device such as a TV remote controller. The MPEG-7 MDS (Multimedia Description Scheme) and TV Anytime set up a standard about how to describe user preferences for genre, channel, actor/actress, keyword, etc. of the TV programs, and how to describe usage history for user's program consumption behaviors and preferences. But they do not describe how to use them. In this paper, we describe an IPG (Intelligent Program Guider) system that provides TV program and channel information based on user preferences and suggest easy access to TV program that user wants. The IPG monitors user's behaviors of interacting to programs and automatically updates the user's preference changes according1y. The IPG utilizes user preferences description scheme specified in both MPEG-7 MDS and TV Anytime metadata specifications.

A Study on Organizing the Web Using Facet Analysis (패싯 분석을 이용한 웹 자원의 조직)

  • Yoo, Yeong-Jun
    • Journal of the Korean BIBLIA Society for library and Information Science
    • /
    • v.15 no.1
    • /
    • pp.23-41
    • /
    • 2004
  • In indexing and organizing Web resources, there have been two basic methods: automatic indexing by extracting key words and library classification schemes or subject directories of search engines. But, both methods have failed to satisfy the user's information needs, due to the lack of standard criteria and the irrationality of its structural system. In this paper I have examined the limits of library classification scheme's structures and the problems related to the nature of Web resources such as specificity and exhaustivity. I have also attempted to explain the logicality of Web resources organization by facet analysis and its strengths and limitations. In so doing, I have proposed three specific methods in using facet analysis: firstly, indexing system by facet analysis; secondly, the alternative transformation of the enumerative classification scheme into facet classification scheme; and finally, the facet model of subject directory of domestic search engine. After examining the three methods, my study concludes that a controlled vocabulary by facet analysis can be employed as a useful method in organizing Web resources.

  • PDF