• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.156-159
• /
• 2013

본 논문에서는 시간 개념이 포함된 역사적 지식을 표현할 수 있는 사건 온톨로지(event ontology) 기반의 역사 온톨로지 모형인 Y-HisOnto 를 제안한다. 제안한 역사 온톨로지 모형은 기존의 온톨로지에서 사용되는 이진 관계(binary-relationship)로 표현된 단편적 지식들을 조합하여 다진 관계(n-ary relationship)를 이용하여 역사적 사건 관련 지식을 표현한다. 제안한 온톨로지 모형에 기반하여 사건 중심의 지식을 온톨로지로 구축하고, 사건 관련 질의에 대해 온톨로지 논리 검색 실험을 수행함으로써 제안한 온톨로지 모형이 Q&A 시스템에서 효과적으로 활용될 수 있음을 확인한다.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.126-129
• /
• 2009

YKanto (Ontology Construction System of Yeungnam University & KAIST)[1,2]는 웹 기반 온톨로지 구축 시스템으로써 다수의 온톨로지 구축자가 신문, 사전, 코퍼스 등의 지식 자원으로부터 대용량의 온톨로지를 구축하고 관리할 수 있는 환경을 제공한다. 본 논문에서는 YKanto에서 개발 중인 온톨로지를 2차원 그래프로 시각화 할 수 있는 온톨로지 시각화 도구(Visualization Tool for Ontology)를 설계하고 개발한다. 개발한 온톨로지 시각화 도구는 기존의 개념 및 관계 중심의 시각화 도구와 달리 사건 기반의 온톨로지(event-based ontology)의 가독성을 높이기 위한 사건(event) 중심의 시각화 도구이다. 또한, Java Applet으로 구현하며, YKanto과 연동시킴으로써 개발 중인 온톨로지를 웹 상에서 실시간으로 확인할 수 있도록 한다.

• Journal of Korean Society of Archives and Records Management
• /
• v.18 no.4
• /
• pp.231-257
• /
• 2018

This paper aims to suggest a facet-based ontology model that can help sort and access records of dispersed families to address these problems. The facet systematically defines the categories of target concepts, which can create diverse and multiple access points. Using the top-down and bottom-up approaches, the facets, which consist of five upper classes and 18 lower classes, were derived for the records of dispersed families. The proposed ontology model was evaluated by real users. The results show that, overall, the ontology is complete and relevant in terms of access points, availability of context information of the records, and description elements for search and use of the records on dispersed families.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.143-150
• /
• 2010

Ontologies, which are consist of entities and their relationships, have been used to implement various scenarios of information services. That is because an entity can be understood well when the surrounding entities and the relationships are known. In describing historical events. The spatio-temporal locations connote the historical context comprehensively. Therefore spatio-temporal locations are one of the most important carriers to connect the historical events. In this paper we analyzed the usage scenarios to access and retrieve historical information, and proposed the design of ontologies for historical information services for making historical stories based on spatio-temporal reference frame.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.477-481
• /
• 2018

본 논문은 범죄 수사 기록 문서로부터 추출한 정보를 트리플로 구성하여 특정 분야의 온톨로지를 구축하고, 더 나아가 온톨로지 기반의 검색 서비스를 구현하는 일련의 과정을 설명한다. 특히 비정형 데이터로 부터 얻어낸 정보를 통해 온톨로지를 구축하고, 이를 토대로 실제 사용할 수 있는 레벨의 서비스를 구현하는 것이 특징이다. 서비스의 성능을 확인하기 위하여 사건 검색에 대한 정확도 측정 방법 중 하나인 Top-K 방식의 정확도 측정 실험을 수행하였으며, 실험 결과 완전 일치 실험에서는 약 93.52%, 유사 필드 활용 실험에서는 약 88.91%의 결과를 얻어낼 수 있었다.

• Journal of the Society of Disaster Information
• /
• v.7 no.3
• /
• pp.220-228
• /
• 2011

Disaster sign data is confirmed data by the experts to the collected data from web and users. In this paper, we focused to make the risk scores to the data based on ontology technology. To analyse the data, first of all, we defined the ontological structure for 4 kinds of disaster types which consists of the bridges, workplaces, buildings, and walls. Base on the ontologies, collected the accidents examples, and then extract the risk rules from the examples. The rules are adjusted with frequencies and weights, and managed to the ontology DB. The rules apply to the disaster sign data, and then calculates the risk scores. It plays role of the index to the risk rates. The disaster sign data management system was implemented and the rules were verified to the system. Because the quality of the risk scores to the disaster sign data depends on the data of the accidents examples's qualities, we assure that the system's performance will be monotonic increasing following up the data upgrades. Continuously, data management is needed. Also the quality control of the rules are needed.

• Journal of KIISE:Software and Applications
• /
• v.36 no.7
• /
• pp.509-522
• /
• 2009

The W3C Ontology Working Group has recently developed OWL as an ontology language for the Semantic Web. OWL, however, fails to perform the process of reasoning about temporal knowledge because it lacks full-pleadged semantics for temporal language. Entities in the real world are changing as time passes, while new facts are being introduced as new events occur. KBs without temporal information are incomplete and incorrect. In this paper, we propose an extended temporal ontology language called TL-OWL which provides an abstract syntax and semantics for representing and reasoning about temporal information in the Semantic Web.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.347-353
• /
• 2008

The realization of intelligence by using ontology is getting attention recently. However, it is necessary to design ontology models suitable to their purpose in order to use efficiently the intelligence realized by ontology. In this paper, we define a cognition cycle for intelligent agents representing a process that the intelligent agents recognize an event and react to it. Moreover, we design an ontology-based intelligent agent, and propose an ontology model that is possible to change the agent's states, to express its emotions, and to expand its intelligence through ontological inference. Finally, we develop an intelligent agent named Helen, confirm the change of her inner states according to the environment and situation, and show the easiness of the extension of her intelligence.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1687-1692
• /
• 2009

Cyber forensics is used the process and technology of digital forensics as a criminal investigation in cyber space. Cyber crime is classified into cyber terror and general cyber crime, and those two classes are connected with each other. The investigation of cyber terror requires high technology, system environment and experts, and general cyber crime is connected with general crime by evidence from digital data in cyber space. Accordingly, it is difficult to determine relational crime types, collect evidence and the legal admissibility of evidence. Therefore, we considered the classifications of cyber crime, the collection of evidence in cyber space and the application of laws to cyber crime. In order to efficiently investigate cyber crime, it is necessary to integrate those concepts for each cyber crime-case. In this paper, we constructed a cyber forensics domain ontology for cyber criminal investigation using the concepts, relations and properties, according to categories of cyber crime, laws, evidence, and information of criminals and crime-cases. This ontology can be used in the process of investigating of cyber crime-cases, and for data mining of cyber crime; classification, clustering, association and detection of crime types, crime cases, evidences and criminals.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.1
• /
• pp.57-81
• /
• 2019

An ontology is a complex structure dictionary that defines the relationship between terms and terms related to specific knowledge in a particular field. There have been attempts to construct various ontologies in Korea and abroad, but there has not been a case in which a large scale crime investigation record is constructed as an ontology and a service is implemented through the ontology. Therefore, this paper describes the process of constructing an ontology based on information extracted from instrusion theft field of unstructured data, a crime investigation document, and implementing an ontology-based search service and a crime spot recommendation service. In order to understand the performance of the search service, we have tested Top-K accuracy measurement, which is one of the accuracy measurement methods for event search, and obtained a maximum accuracy of 93.52% for the experimental data set. In addition, we have obtained a suitable clue field combination for the entire experimental data set, and we can calibrate the field location information in the database with the performance of F1-measure 76.19% Respectively.