• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.519-524
• /
• 2010

In this paper, we will introduce our approach for composing operation based on user tasks. It is based on Service Component Architecture (SCA). In addition, we developed ontology based on OWL and the MIT process handbook, called u-TO(universal task ontology), which can be used for users describing and specifying semantically their needs. We represent the hierarchy of tasks, and classify tasks according to views in u-TO. It aims at facilitating the modeling of complex demands or systems without regarding details of technical aspects of underlying infrastructure.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.1750-1752
• /
• 2010

본 논문에서 제안하는 초기 에이전트 기반 온톨로지 통합 프레임워크는 온톨로지 기반 응용에서의 온톨로지를 사용하는 에이전트를 위해 제안되었을 뿐만 아니라 온톨로지 통합 태스크와 관련되어 있다. 이 프레임워크에 의해, 에이전트의 행동이 상호작용 다이어그램으로 표현되어 진다. 이 프레임워크의 중요한 속성은 유연성과 확장성인데, 이것은 시스템에서 온톨로지 재사용을 허용함에 의해서 온톨로지 통합을 가능하게 한다.

• Journal of the Korean Society for information Management
• /
• v.24 no.1 s.63
• /
• pp.31-53
• /
• 2007

This paper presents a model of Task-Ontology for small unit operations(SUO) such as nongovernment organizations Despite the rapid development and extension of NGO in domestic area, most have insufficient structural domain resources in existence and underestimate the importance of information management. To improve the citizen's participation and to activate the conjoint actions among the NGO, which are critical to its social role-playing in global society, the modeling Task-Ontology is ultimately intended to implement the knowledge management system of NGO. In the perspective of ontology competency, not only the analysis of resources in vary, but also in-depth Interviews with the NGO practicing personnels and subject experts, and also the intensive observations of task-processing are required for the knowledge acquisition.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.275-281
• /
• 2012

This research proposes the method to develop the recommendation system of automobile parts using task ontology technology. The proposed intelligent recommendation system is designed to learn the assembly process of automobile parts and the automobile parts are composed by ontology method for the recommendation of the parts. Using hierarchical taxonomy based on is-a relationship, the relationship between each part that makes up automotive engine was set. Each part has each different weighted value according to the knowledge of automobile experts. The weighted value is created by the number of selection that the users of the automobile recommendation system select while using the system and the final value calculated by the multiplication of the weighted value, which is recorded within the system. As a result, the users can easily identify which factor in which part is important by the output in the order of the priority. The intelligent recommendation system for automobile parts is a system to inform of the assembly, the usage and the importance of automobile parts without any specialized knowledge by expressing the parts that are closely related with the applicable parts when selecting any part on the basis of the generated data for the automobile parts that are difficult to access by users.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.86-99
• /
• 2011

Due to the uncertainty of intention recognition for behaviors of users, the intention is differently recognized according to the situation for the same behavior by the same user, the accuracy of user intention recognition by minimizing the uncertainty is able to be improved. This paper suggests a novel ontology-based method to recognize user intentions, and able to minimize the uncertainties that are the obstacles against the precise recognition of user intention. This approach creates ontology for user intention, makes a hierarchy and relationship among user intentions by using RuleML as well as Dynamic Bayesian Network, and improves the accuracy of user intention recognition by using the defined RuleML as well as the gathered sensor data such as temperature, humidity, vision, and auditory. To evaluate the performance of robot proactive planning mechanism, we developed a simulator, carried out some experiments to measure the accuracy of user intention recognition for all possible situations, and analyzed and detailed described the results. The result of our experiments represented relatively high level the accuracy of user intention recognition. On the other hand, the result of experiments tells us the fact that the actions including the uncertainty get in the way the precise user intention recognition.

• Journal of Digital Convergence
• /
• v.11 no.8
• /
• pp.213-218
• /
• 2013

In this paper, when vehicle inspection is made, the check way is recommended based on the intelligent and personalized in the workplace, education, and other space-time according to the current situation. These results increase productivity, reduce costs, and improve performance. So we designed vehicle inspection recommendation system using ontology. Recommendation method is that components connected concept are shown according to weight value. if components are connected with other concept, the components are extended.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.435-438
• /
• 2010

오늘날 많은 연구자들은 자율적 인간형 로봇 (Autonomous symbiotic human-robot)을 보조하기 위한 지식체계로 온톨로지의 개념을 사용한다. 이러한 연구는 룰 기반의 추론시스템을 지원하기 위해 온톨로지를 저장하는 데이터베이스 스키마를 설계하는데 초점을 맞추고 있다. 이러한 연구 뿐만 아니라 온톨로지 개념을 사용하는 가장 중요한 목적 중에 하나는 상황 추론이다. 이러한 관점에서 본 논문은 로봇이라는 환경에서 좀 더 지능적인 상황 추론 서비스를 제공하기 위해, 5W1H 기반의 로봇 지능 저장소라 불리는 로봇 메모리 저장소를 설계하는데 초점을 두고 있다. 기존 연구는 체계적이고 의미론적 5W1H를 고려하지 않거나 5W1H와 다른 개념 사이의 연광성의 결여에 많은 문제점을 가지고 있으며 이를 해결하기 위해 본 논문에서는 상황, 목적, 공간, 특징, 인간 그리고 5W1H의 온톨로지 지식을 저장할 수 있는 개념적인 모델인 로봇 메모리 모델을 설계한다. 또한 본 논문에서는 상황 추론을 지원하기 위해 로봇의 인스턴스 정보라고 불리는 자전적 기억 (Episodic Memory)를 효과적으로 저장하기 위한 5W1H 모델을 정의하며 이러한 모델을 물리적으로 저장하기 위한 관계형 데이터베이스 기반의 EventsEpisodicRBS를 설계한다. 결과적으로 이러한 연구를 통해서 자율적 인간형 로봇 환경에서 로봇이 지능적 서비스 제공의 핵심 모듈인 상황 추론을 지원하는데 큰 기여를 할 수 있는 하부 시스템으로서의 의미를 가질 수 있다.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.185-192
• /
• 2013

The purpose of this study is to set the relationship between each parts that forms the engine of an automobile based on the 3D visualization technology which is able to be learned according to the skill of the operator in the industry field and to recommend the auto parts using a task ontology. A visualization method was proposed by structuring the complex knowledge by signifying the link and the node in forms of a network and using SOM which can be shown in the form of 3 dimension. In addition, by using is-a Relationship-based hierarchical Taxonomy setting the relationship between each of the parts that forms the engine of an automobile, to allow a recommendation using a weighted value possible. By providing and placing the complex knowledge in the 3D space to the user for an opportunity of more realistic and intuitive navigation, when randomly selecting the automobile parts, it allows the recommendation of the parts having a close relationship with the corresponding parts for easy assembly and to know the importance of usage for the automobile parts without any special expertise.