• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.15 no.1
• /
• pp.43-67
• /
• 2004

The purpose of this study is to design semantic web and policy direction for national knowledge and information management. The paper describes all the components needed to accomplish the objective: 1) creating unchangeable and unique identifiers for metadata elements, resources, and ontology classes and properties; 2) recommending active use of XML namespaces; 3) establishing metadata and application profile standards for national integrated searching; 4)developing a metadata registry to promote semantic interoperability among metadata; 5) discussing the need of creating ontologies using W3C OWL and ISO Topic Maps; 6) providing intelligent search services based on metadata; and 7) presenting future directions and tasks of national knowledge and information management.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.387-392
• /
• 2006

온톨로지는 시맨틱 웹의 핵심 기술 요소로서 지식을 개념화하고 명세화해서 의미론적 지식체계를 구축한다. 온톨로지는 개념적 모델링(Conceptual Modeling)을 통해 실제 세계의 지식(Real World Knowledge)을 표현하는 중요한 수단으로 제안되었고, 수많은 정보에 대한 지식관리를 효과적으로 수행할 수 있는 토대를 제공한다. 본 연구에서는 연구과제회의를 대상으로 온톨로지를 설계 및 구축한다. 과제 진행에 수반되는 다양한 회의와 관련자료는 과제의 성공적인 수행을 위해 반드시 관리되어야 한다. 일반적으로 회의에서 참석자들 사이에 정보 공유 및 자료 검색이 어렵고 회의일정 조정이 번거로우며 회의자료 관리가 체계적이지 못하다. 따라서 연구과제 진행과정의 회의와 관련자료들을 분석/분류해서 개념적 모델링을 통해 연구과제회의 온톨로지를 구축하고자 한다. 향후 이를 활용하여 지능형 반응 공간에서 회의 관리 및 서비스 제공을 할 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.824-826
• /
• 2003

지능형 개념기반 검색시스템(Intelligent Concept Based Retrieval System)은 구문적 서술(Syntactic Description)과 의미적 서술(Semantic Description)과 의한 상호 융합으로 이뤄질 수 있는데 컬러 히스토그램, Curvanature 히스토그램등과 같은 구운적 서술(Syntactic Description) 내용의 추출은 현재의 기술들로 잘 이를 수 있다. 또한 특정 응용 분야에서뿐만 아니라 미디어 타입에 따라서도 쉽게 사용될 수 있다. 이미 MPEG-7에서 표준화된 Description Scheme을 제공하고 있다. 그러나 기술 구조 레벨과 개요 레벨등과 같은 다양한 기술 레벨들에 의해 구문적 서술(Syntactic Description) 이질성은 발생한다. 따라서 본 연구에서는 Polygonal mesh 기반 미디어 객체 표현방법을 제시하고 이를 통해 간접적 서술 변환을 할 수 있는 방안을 제시하여 구문적 서술(Syntactic Description)에서의 이질성 문제를 해결하였다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.

• Journal of Korea Multimedia Society
• /
• v.12 no.10
• /
• pp.1499-1507
• /
• 2009

With the abundance of digital contents, the necessity of precise indexing technology is consistently required. To meet these requirements, the intelligent software entity needs to be the subject of information retrieval and the interoperability among intelligent entities including human must be supported. In this paper, we analyze the unifying framework for multi-modality indexing that Snoek and Worring proposed. Our work investigates the method of improving the authenticity of indexing information in contents-based automated indexing techniques. It supports the creation and control of abstracted high-level indexing information through ontological concepts of Semantic Web skills. Moreover, it attempts to present the fundamental model that allows interoperability between human and machine and between machine and machine. The memory-residence model of processing ontology is inappropriate in order to take-in an enormous amount of indexing information. The use of ontology repository and inference engine is required for consistent retrieval and reasoning of logically expressed knowledge. Our work presents an experiment for storing and retrieving the designed knowledge by using the Minerva ontology repository, which demonstrates satisfied techniques and efficient requirements. At last, the efficient indexing possibility with related research is also considered.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.379-384
• /
• 2002

개발적인 측면에서 온라인 게임 환경에서의 NPC(Non Playable Character)들은 환경인식능력, 이동능력, 특수 능력 및 아이템의 소유 배분 등을 원활히 하기 위한 능력들을 소유해야 하며, 게임 환경을 인식, 저장하기 위한 데이터구조와 자신만의 독특한 임무(mission)를 달성하기 위한 계획을 갖고 행위를 해야 한다. 이런 의미에서 NPC는 자신만의 고유한 규칙과 행동 패턴, 그리고 목표(Goal)와 이를 실행하기 위한 계획(plan)을 소유하는 에이전트로 인식되어야 할 것이다. 그러나, 기존 게임의 NPC 제어 구조나 구현 방법은 이러한 요구조건에 부합되지 못한 부분이 많았다. C/C++ 같은 컴퓨터 언어들을 이용한 구현은 NPC의 유연성이나, 행위에 많은 문제점이 있었다. 이들 언어의 switch 문법은 NPC의 몇몇 특정 상태를 묘사하고, 그에 대한 행위를 지정하는 방법으로 사용되었으나, 게임 환경이 복잡해지면서, 더욱더 방대한 코드를 만들어야 했고, 해석하는데 많은 어려움을 주었으며, 동일한 NPC에 다른 행동패턴을 적용시키기도 어려웠다. 또한, 대부분의 제어권을 게임 서버 폭에서 도맡아 함으로써, 서버측에 많은 과부하 요인이 되기도 하였다. 이러한 어려움을 제거하기 위해서 게임 스크립트를 사용하기도 하였지만, 그 또한 단순 반복적인 패턴에 사용되거나, 캐릭터의 속성적인 측면만을 기술 할 수 있을 뿐이었다 이러한 어려움을 해소하기 위해서는 NPC들의 작업에 필요한 지식의 계층적 분화를 해야 하고, 현재 상황과 목표 변화에 적합한 반응을 표현할 수 있는 스크립트의 개발이 필수 적이라 할 수 있다 또한 스크립트의 실행도 게임 서버 측이 아닌 클라이언트 측에서 수행됨으로써, 서버에 걸리는 많은 부하를 줄일 수 있어야 할 것이다. 본 논문에서는, 대표적인 반응형 에이전트 시스템인 UMPRS/JAM을 이용하여, 에이전트 기반의 게임 캐릭터 구현 방법론에 대해 알아본다.퓨터 부품조립을 사용해서 Template-based reasoning 예를 보인다 본 방법론은 검색노력을 줄이고, 검색에 있어 Feasibility와 Admissibility를 보장한다.매김할 수 있는 중요한 계기가 될 것이다.재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer algorithm could efficiently reject ISI of channel and increase speed of convergence in avoidance burden of computational complexity in reality when it was experimented having

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• The Journal of the Korea Contents Association
• /
• v.12 no.11
• /
• pp.502-510
• /
• 2012

As defense science and technology are developing, smart weapons are being developed continually. The collection and analysis of the future strategic weapon information from all over the world have become a greater priority because information sharing became active. So, a system to manage and analyze heterogeneous defense intelligence is required. Semantic Web is the next generation knowledge information management technology for integrating, searching and navigating heterogeneous knowledge resource. Recently, Semantic Web is wildly being used in intelligent information management system. Semantic Web supports the analysis with the high reliability because it supports the simple keyword search as well as the semantic based information retrieval. In this paper, we propose the semantic web based multi-dimensional information analysis system on the national defense weapons that constructs ontology for various weapons information such as weapon specifications, nations, manufacturers and technologies and searches and analyses the specific weapon based on ontology. The proposed system supports the semantic search and multi-dimensional information analysis based on the relations between weapon specifications. Also, our system improves the efficiency on acquiring smart weapon information because it is developed with ontology based on military experts' knowledge and various web documents related with various weapons and intelligent search service.

• Journal of Korean Society of Archives and Records Management
• /
• v.20 no.4
• /
• pp.1-17
• /
• 2020

Along with the development of information technology, the digitalization of archives has also been accelerating. However, digital archives have limitations in effectively searching, interlinking, and understanding records. In response to these issues, this study proposes a knowledge graph that represents comprehensive relationships among heterogeneous entities in digital archives. In this case, the knowledge graph organizes resources in the archives on the Korean financial crisis of 1997 by transforming them into named entities that can be discovered by machines. In particular, the study investigates and creates an overview of the characteristics of the archives on the Korean financial crisis as a digital archive. All resources on the archives are described as entities that have relationships with other entities using semantic vocabularies, such as Records in Contexts-Ontology (RiC-O). Moreover, the knowledge graph of the Korean Financial Crisis of 1997 is represented by resource description framework (RDF) vocabularies, a machine-readable format. Compared to conventional digital archives, the knowledge graph enables users to retrieve a specific entity with its semantic information and discover its relationships with other entities. As a result, the knowledge graph can be used for semantic search and various intelligent services.

• Journal of KIISE:Software and Applications
• /
• v.37 no.7
• /
• pp.548-557
• /
• 2010

In this paper, we propose a semi-automatic modeling approach of ontology to annotate VOD to realize the IPTV's intelligent searching. The ontology is made by combining partial tree that extracts hypernym, hyponym, and synonym of keywords related to a service domain from WordNet. Further, we add to the partial tree new keywords that are undefined in WordNet, such as foreign words and words written in Chinese characters. The ontology consists of two parts: generic hierarchy and specific hierarchy. The former is the semantic model of vocabularies such as keywords and contents of keywords. They are defined as classes including property restrictions in the ontology. The latter is generated using the reasoning technique by inferring contents of keywords based on the generic hierarchy. An annotation generates metadata (i.e., contents and genre) of VOD based on the specific hierarchy. The generic hierarchy can be applied to other domains, and the specific hierarchy helps modeling the ontology to fit the service domain. This approach is proved as good to generate metadata independent of any specific domain. As a result, the proposed method produced around 82% precision with 2,400 VOD annotation test data.