• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.801-808
• /
• 2022

Research on how to embed knowledge in large-scale Linked Data and apply neural network models for entity matching is relatively scarce. The most fundamental problem with this is that different labels lead to lexical heterogeneity. In this paper, we propose an extended GCN (Graph Convolutional Network) model that combines re-align structure to solve this lexical heterogeneity problem. The proposed model improved the performance by 53% and 40%, respectively, compared to the existing embedded-based MTransE and BootEA models, and improved the performance by 5.1% compared to the GCN-based RDGCN model.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.35-48
• /
• 2022

In this study, it propose a proof theory method for expressing and reasoning knowledge in a multiagent environment. Since this method determines logical results in a mechanical way, it has developed as a core field from early AI research. However, since the proposition cannot always be proved in any set of closed sentences, in order for the logical result to be determinable, the range of expression is limited to the sentence in the form of a clause. In addition, the resolution principle, a simple and strong reasoning rule applicable only to clause-type sentences, is applied. Also, since the proof theory can be expressed as a meta predicate, it can be extended to the metalogic of the proof theory. Metalogic can be superior in terms of practicality and efficiency based on improved expressive power over epistemic logic of model theory. To prove this, the semantic method of epistemic logic and the metalogic method of proof theory are applied to the Muddy Children problem, respectively. As a result, it prove that the method of expressing and reasoning knowledge and common knowledge using metalogic in a cooperative multiagent environment is more efficient.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.33-43
• /
• 2022

Labeled graphs are used to represent entities, their relationships, and their structures in real data such as knowledge graphs and protein interactions. With the rapid development of IT and the explosive increase in data, there has been a need for a subgraph matching technology to provide information that the user is interested in. In this paper, we propose an approximate Top-k labeled subgraph matching scheme that considers the semantic similarity of labels and the difference in graph structure. The proposed scheme utilizes a learning model using FastText in order to consider the semantic similarity of a label. In addition, the label similarity graph(LSG) is used for approximate subgraph matching by calculating similarity values between labels in advance. Through the LSG, we can resolve the limitations of the existing schemes that subgraph expansion is possible only if the labels match exactly. It supports structural similarity for a query graph by performing searches up to 2-hop. Based on the similarity value, we provide k subgraph matching results. We conduct various performance evaluations in order to show the superiority of the proposed scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.81-88
• /
• 2024

Despite the rapid growth of the generative AI market and significant interest from domestic companies and institutions, concerns about the provision of inaccurate information and potential information leaks have emerged as major factors hindering the adoption of generative AI. To address these issues, this paper designs and implements a question-answering system based on the Retrieval-Augmented Generation (RAG) architecture. The proposed method constructs a knowledge database using Korean sentence embeddings and retrieves information relevant to queries through optimized searches, which is then provided to the generative language model. Additionally, it allows users to directly manage the knowledge database to efficiently update changing business information, and it is designed to operate in a private network to reduce the risk of corporate confidential information leakage. This study aims to serve as a useful reference for domestic companies seeking to adopt and utilize generative AI.

• Journal of KIISE:Databases
• /
• v.27 no.2
• /
• pp.141-150
• /
• 2000

There are three significant drawbacks in extant fuzzy rule-based expert system languages. First, they lack the functionality of composite object inference. Second, they do not support fuzzy reasoning semantically easy to understand and conceptually simple to use. Third, knowledge representation and reasoning style of their model have a great semantic gap with those of current database models. Therefore, it is very difficult for the two models to be seamlessly integrated with each other. This paper provides the formal specification of a fuzzy object inference model to solve the three drawbacks. GIS(Geographic Information System) application domain is used to demonstrate that our model naturally models complex GIS information in terms of composite objects and successfully performs fuzzy inference between them.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2001.05a
• /
• pp.184-197
• /
• 2001

In this paper, we provide the formal specification of a fuzzy object inference language and propose ICOT(Integrated C-Object Tool) as its implementation for knowledge-based programming with the disjunctive fuzzy information. The novelty of our model is that it seamlessly combines object inference and fuzzy reasoning into a unified framework without compromising a compatibility with extant databases, especially object-relational ones. In this model most of the object-oriented paradigm is successfully expressed in terms of relational constructs, tailoring fuzzy reasoning style to be well suited to the framework of the databases. It turns out to be useful in preserving its conceptual simplicity as well, since simple-to-use is one of important criteria in designing the databases. Additionally this model considerably enhanced the semantic expressiveness of data allowing disjunctive fuzzy information.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.991-998
• /
• 2002

With the advent of XML and database languages armed with the object-oriented concept and deductive logic, the problem of efficient query processing for them has become a major issue. We describe a way of processing semi-structured XML data through an implementation of a Deductive and Object-oriented Database (DOODB) language with the explanation of query processing. We have shown how to convert an XML data model to a DOODB data model. We have then presented an efficient query processing method based on Connection Graph Resolution. We also present a knowledge-based query processing method that uses the homomorphism of objects in the database and the associative rule of substitutions.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.6
• /
• pp.57-68
• /
• 2017

The Linked Open Data(LOD) cloud is quickly becoming one of the largest collections of interlinked datasets and the de facto standard for publishing, sharing and connecting pieces of data on the Web. Data publishers from diverse domains publish their data using Resource Description Framework(RDF) data model and provide SPARQL endpoints to enable querying their data, which enables creating a global, distributed and interconnected dataspace on the LOD cloud. Although it is possible to extract structured data as query results by using SPARQL, users have very poor in analysis and visualization of RDF data from SPARQL query results. Therefore, to tackle this issue, based on Formal Concept Analysis, we propose a novel approach for analyzing and visualizing useful information from the LOD cloud. The RDF data analysis and visualization technique proposed in this paper can be utilized in the field of semantic web data mining by extracting and analyzing the information and knowledge inherent in LOD and supporting classification and visualization.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.922-925
• /
• 2019

기계 독해 기술은 기계가 주어진 비정형 문서 내에서 사용자의 질문을 이해하여 답변을 하는 기술로써, 챗봇이나 스마트 스피커 등, 사용자 질의응답 분야에서 핵심이 되는 기술 중 하나이다. 최근 딥러닝을 이용한 기학습 언어모델과 전이학습을 통해 사람의 기계 독해 능력을 뛰어넘는 방법론들이 제시되었다. 하지만 이러한 방식은 사람이 인식하는 질의응답 방법과 달리, 개체가 가지는 의미론(Semantic) 관점보다는 토큰 단위로 분리된 개체의 형태(Syntactic)와 등장하는 문맥(Context)에 의존해 기계 독해를 수행하였다. 본 논문에서는 기존의 높은 성능을 나타내던 기학습 언어모델에 대규모 지식그래프에 등장하는 개체 정보를 함께 학습함으로써, 의미학적 정보를 반영하는 방법을 제시한다. 본 논문이 제시하는 방법을 통해 기존 방법보다 기계 독해 분야에서 높은 성능향상 결과를 얻을 수 있었다.

• Journal of The Korean Association of Information Education
• /
• v.11 no.3
• /
• pp.317-327
• /
• 2007

The purpose of this study is to consider ontology theory and get to forge design and implementation of ontology-based access system which is support to the nutrition and food guide tower of Home Economics textbooks in middle school in order to offer the way of effective learning performance. It offers a model by establishing a nutrition and food guide tower access system based on Protege-2000 framework. This system is on the basis of XML, and it makes possible to work with semantic web, a next generation internet technology, and provides a meaning structure that can be shared in the field of nutrition in order to build up the fundament of knowledge an information system for the mutual operations. A learner can systemize the knowledge through a self-information access and an instructor can also check out the degree of learner's learning-accomplishment and interests, directly putting the access system into the teaching and learning process. In addition, it is supposed that the learner can maintain a balance and healthy life by internalizing his or her knowledge throughout ontology not only in a teaching and learning process but also in a daily life.