• The Journal of Society for e-Business Studies
• /
• v.5 no.2
• /
• pp.81-99
• /
• 2000

Nowadays, many commercial ERP products, such as Oracle, SAP, and Baan, etc, are designed based on large-scaled companies. It is difficult for small and medium-size companies with weakness in budgets and resources(e.g., human, organization, technique, and so on) to use them as it was. So, new ERP system need to be provided for small and medium-size companies. In this paper, we model and provide a conceptual ERP model for small and medium-size companies by using "4＋1 View" architecture model of Unified Modeling Language(UML). The conceptual ERP model consists of five subsystems： Manufacturing, Sales, HumanResource and Payroll, Accounting, and Trading. Especially, we describe the conceptual ERP model focusing on "Manufacturing" subsystem by using several diagrams of UML. By using the conceptual ERP model, the ERP system′s developers of small and medium-size companies can obtain many benefits： improving the efficiency of software developing process and helping user requirements gathering and description of ERP system′s nonfunctional aspect as well as functional aspect.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.321-324
• /
• 2024

본 논문에서는 LLM(Large Language Models) 기반의 STT 결합 챗봇 시스템을 제안한다. 제조업 공장에서 안전 교육의 부족과 외국인 근로자의 증가는 안전을 중시하는 작업 환경에서 새로운 도전과제로 부상하고 있다. 이에 본 연구는 언어 모델과 음성 인식(Speech-to-Text, STT) 기술을 활용한 혁신적인 챗봇 시스템을 통해 이러한 문제를 해결하고자 한다. 제안된 시스템은 작업자들이 장비 사용 매뉴얼 및 안전 지침을 쉽게 접근하도록 지원하며, 비상 상황에서 신속하고 정확한 대응을 가능하게 한다. 연구 과정에서 LLM은 작업자의 의도를 파악하고, STT 기술은 음성 명령을 효과적으로 처리한다. 실험 결과, 이 시스템은 작업자의 업무 효율성을 증대시키고 언어 장벽을 해소하는데 효과적임이 확인되었다. 본 연구는 제조업 현장에서 작업자의 안전과 업무 효율성 향상에 기여할 것으로 기대된다.

• The Journal of Korean Medicine
• /
• v.45 no.1
• /
• pp.203-214
• /
• 2024

Objectives: In the context of competency-based education emphasized in Korean Medicine, this study aimed to develop a pilot version of a CPX (Clinical Performance Examination) Practicing Chatbot utilizing large language models with prompt engineering. Methods: A standardized patient scenario was acquired from the National Institute of Korean Medicine and transformed into text format. Prompt engineering was then conducted using role prompting and few-shot prompting techniques. The GPT-4 API was employed, and a web application was created using the gradio package. An internal evaluation criterion was established for the quantitative assessment of the chatbot's performance. Results: The chatbot was implemented and evaluated based on the internal evaluation criterion. It demonstrated relatively high correctness and compliance. However, there is a need for improvement in confidentiality and naturalness. Conclusions: This study successfully piloted the CPX Practicing Chatbot, revealing the potential for developing educational models using AI technology in the field of Korean Medicine. Additionally, it identified limitations and provided insights for future developmental directions.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.106-111
• /
• 2018

감성분석(Sentiment Analysis)은 텍스트에 나타난 감성을 분석하는 기술로 자연어 처리 분야 중 하나이다. 한국어 텍스트를 감성분석하기 위해 다양한 기계학습 기법이 많이 연구되어 왔으며 최근 딥러닝의 발달로 딥러닝 기법을 이용한 감성분석도 활발해지고 있다. 딥러닝을 이용해 감성분석을 수행할 경우 좋은 성능을 얻기 위해서는 충분한 양의 학습데이터가 필요하다. 하지만 감성분석에 적합한 학습데이터를 얻는 것은 쉽지 않다. 본 논문에서는 이와 같은 문제를 해결하기 위해 기존에 구축되어 있는 감성사전을 활용한 대용량 학습데이터 구축 방안을 제안한다.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.634-636
• /
• 1995

This paper presents a new distance relay modeling techniques which avoids unnecessary computational procedure. A general-purpose simulation language, called MODELS, has been added to the software ATP(Alternative Transients Program) providing a new option to perform numerical and logical manipulations of variables of an electrical system. This language has been designed to replace the previous option TACS (Transient Analysis of Control Systems) which permits to simulate a control system in conjunction with a large power network. One purpose of this study is to build a structure for modeling of digital distance relays within EMTP MODELS. Contrary to the traditional methods, the new method using MODELS reduce the number of simulation steps in modeling the distance relay.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.4
• /
• pp.31-37
• /
• 2003

This paper is a review of the large-scale information retrieval system, CONDOR. This system was developed by the consortium that consists of Chonbuk National University, Searchline Co. and Carnegie Mellon University. This system is based on the probabilistic model of information retrieval systems. The multi-language query processing, online document summarization based on query and dynamic hierarchy clustering of this system make difference of other systems. We test this system with 30 million web documents successfully.

• Asia pacific journal of information systems
• /
• v.17 no.1
• /
• pp.33-58
• /
• 2007

Quiet often, an organization tries to grapple with inconsistent and partial information to generate relevant information to support decision making and action. As such, an organization scans the environment interprets scanned data, executes actions, and learns from feedback of actions, which boils down to computational interpretations and learning in terms of machine learning, statistics, and database. The ExOM proposed in this paper is geared to facilitate such knowledge discovery found in large databases in a most flexible manner. It supports a broad range of learning and classification styles and integrates them with traditional database functions. The learning and classification components of the ExOM are tightly integrated so that learning and classification of objects is less burdensome to ordinary users. A brief sketch of a strategy as to the expressiveness of terminological language is followed by a description of prototype implementation of the learning and classification components of the ExOM.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1992.10a
• /
• pp.12-12
• /
• 1992

This paper proposes an analysis method of Petri nets (PNs) using the relational algebra (RA). More specifically, we represent PNs in relations of the relational model. Based on such representation, we first develop an algorithms for analyzing properties of PNs, such as boundedness, conservation, coverability, reachability, and liveness. The advantage of this approach is as follows: First, the algorithms represented by RA can be easily converted to a query language such as SQL of the widely used, commercial relational database management systems (DBMSs). Second, we can alleviate the problem of state space explosion because relational DBMSs can handle large amounts of data efficiency. Finally, we can use the DBMS's query language to interpret the Petri nets and make simulation.

• Journal of the Korea Society for Simulation
• /
• v.1 no.1
• /
• pp.37-47
• /
• 1992

This paper proposes an analysis method of petri nets(PNs) using the relational algebra(RA). More wpecifically, we represent PNs in relations of the relational model. Based on such representation, we first develop an algorithm for generating reachability trees of PNs. we then develop an algorithm for generating reachability trees of PNs. We then develop algorithms for analyzing properties of PNs, such as boundedness, conservation, coverability, reachability, and liveness. The advantage of this approach is as follows: First, the algorithms represented by RA can be easity converted to a query language such as SQL of the widely used, commerical relational database management systems(DBMSs). Second, we can alleviate the problem of state space explosion because relational DBMSs can handle large amounts of data efficiently. Finally, we can use the DBMS's query language to interpret the Petri nets and make simulation.