• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.209-213
• /
• 2023

최근 자연어 이해 분야에서 대규모 언어모델 기반으로 프롬프트를 활용하여 모델과 상호작용하는 방법이 널리 연구되고 있으며, 특히 상담 분야에서 언어모델을 활용한다면 내담자와의 자연스러운 대화를 주도할 수 있는 대화생성 모델로 확장이 가능하다. 내담자의 상황에 따라 개인화된 상담대화를 진행하는 모델을 학습시키려면 동일한 내담자에 대한 과거 및 차기 상담대화가 필요하지만, 기존의 데이터셋은 대체로 단일 대화세션으로 구축되어 있다. 본 논문에서는 언어모델을 활용하여 단일 대화세션으로 구축된 기존 상담대화 데이터셋을 확장하여 연속된 대화세션 구성의 학습데이터를 확보할 수 있는 프롬프트 기반 데이터 증강 기법을 제안한다. 제안 기법은 기존 대화내용을 반영한 요약질문 생성단계와 대화맥락을 유지한 차기 상담대화 생성 단계로 구성되며, 프롬프트 엔지니어링을 통해 상담 분야의 데이터셋을 확장하고 사용자 평가를 통해 제안 기법의 데이터 증강이 품질에 미치는 영향을 확인한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• Journal of the Korea Society for Simulation
• /
• v.18 no.1
• /
• pp.27-34
• /
• 2009

Currently network users, especially the number of internet users, increase rapidly. Also, high quality of service is required and this requirement results a sudden network traffic increment. As a result, an efficient management system for huge network traffic becomes an important issue. Ontology/data engineering based context awareness using the System Entity Structure (SES) concepts enables network administrators to access traffic data easily and efficiently. The network traffic analysis system, which is studied in this paper, is designed and implemented based on a model and simulation using data engineering methodology to be avaiable in evaluating large network traffic data. Extensible Markup Language (XML) is used for metadata language in this system. The information which is extracted from the network traffic analysis system could be modeled and simulated in Discrete Event Simulation (DEVS) methodology for further works such as post simulation evaluation, web services, and etc.

• Journal of Advanced Marine Engineering and Technology
• /
• v.41 no.1
• /
• pp.56-61
• /
• 2017

This paper presents a data prediction method and its application to haptic-based teleoperation systems. In general, time delays inevitably occur during data transmission in a network environment, which degrades the overall performance of haptic-based teleoperation systems. To address this situation, this paper proposes an autoregressive moving average (ARMA) model-based data prediction algorithm for estimating model parameters and predicting future data recursively in real time. The proposed method was applied to haptic data captured every 5 ms while bilateral haptic interaction was carried out by two users with an object in a virtual space. The results showed that the prediction performance of the proposed method had an error of less than 1 ms when predicting position-level data 100 ms ahead.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2316-2322
• /
• 2012

The present study investigates a standardized framework for support system of ship design engineering. The purpose of this research is to improve the efficiency of information gathering and its use in tasks of the ship design engineering support system. Due to their variety and complexity, the existing engineering methods tend to waste time in searching for the standardized method and knowledge or to cause errors on tasks. Generally, these kinds of system have serious problems. The most serious one among them is that the existing system consists of both useful and useless data. This finally leads engineers to a failure in finding out useful information from the system. We have designed a standardized framework, which enables users to properly recompose the menu form depending on the task process, simplifies the methods at several process levels, and provides a more intuitive method in user interface environment in order to resolve the existing problems, minimize the system-operating costs, and improve the efficiency of engineering tasks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2987-2992
• /
• 2015

In this paper, we propose the framework under a standardized task configuration to improve data accuracy and to provide unified system for the outfitting production design in shipyards. Due to the mismatching engineering data, the wrong designs or drawings were produced. With these wrong information, the production process can be broken and faced a big problem during production stage. In this study, we propose novel framework and its components which can offer better supporting for the design task and its process to improve productivity and efficiency with knowledge based engineering support system.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.51-66
• /
• 2023

In this paper, we propose a new type of process discovery framework, which is named as control-path-driven process group discovery framework, to be used for process mining and process reengineering in supporting life-cycle management of business process models. In addition, we develop a process mining system based on the proposed framework and perform experimental verification through it. The process execution event logs applied to the experimental effectiveness and verification are specially defined as Process BIG-Logs, and we use it as the input datasets for the proposed discovery framework. As an eventual goal of this paper, we design and implement a control path-driven process group discovery algorithm and framework that is improved from the ρ-algorithm, and we try to verify the functional correctness of the proposed algorithm and framework by using the implemented system with a BIG-Log dataset. Note that all the process mining algorithm, framework, and system developed in this paper are based on the structural information control net process modeling methodology.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.245-250
• /
• 2023

Digital twin technology, which copies information from real space into virtual space, is being used in a variety of fields.Interest in digital twins is increasing, especially in advanced manufacturing fields such as Industry 4.0-based smart manufacturing. Operating a digital twin system generates a large amount of data, and the data generated has different characteristics depending on the technology field, so it is necessary to efficiently manage resources and use an optimized digital twin platform technology. Research on digital twin pipelines has continued, mainly in the advanced manufacturing field, but research on high-speed pipelines suitable for data in the plant field is still lacking. Therefore, in this paper, we propose a pipeline design method that is specialized for digital twin data in the plant field that is rapidly poured through Apache Kafka. The proposed model applies plant information on a Revit basis. and collect plant-specific data through Apache Kafka. Equipped with a lightweight CFD engine, it is possible to create a digital twin model that is more suitable for the plant field than existing digital twin technology for the manufacturing field.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.209-227
• /
• 2023

The government continues to announce measures to revitalize smart construction technology based on BIM for productivity innovation in the construction industry. In the design phase, the goal is design automation and optimization by converging BIM Data and other advanced technologies. Accordingly, in the basic design of the Namhae Seomyeon-Yeosu Sindeok National Road Construction Project, a domestic undersea tunnel project, BIM-based design was carried out by developing tunnel design automation technology using 3D spatial information according to the tunnel design process. In order to derive the optimal alignment, more than 10,000 alignment cases were generated in 36hr using the generative design technique and a quantitative evaluation of the objective functions defined by the designer was performed. AI-based ground classification and 3D Geo Model were established to evaluate the economic feasibility and stability of the optimal alignment. AI-based ground classification has improved its precision by performing about 30 types of ground classification per borehole, and in the case of the 3D Geo Model, its utilization can be expected in that it can accumulate ground data added during construction. In the case of 3D blasting design, the optimal charge weight was derived in 5 minutes by reviewing all security objects on the project range on Dynamo, and the design result was visualized in 3D space for intuitive and convenient construction management so that it could be used directly during construction.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2010.04a
• /
• pp.369-374
• /
• 2010

최근 건설 산업에서 BIM이 각광 받으면서, BIM 기반의 다양한 엔지니어링 기술 도입 및 프로세스 적용이 시도 되고 있다. 이중 BIM 기반의 프로젝트 운영을 위해서는 BIM의 데이터의 저장, 수정, 배포뿐만 아니라, 관련 주체간의 협업이 가능한 환경이 요구되고 있으며, 이러한 환경 구축을 위해 제조업에서 활용되고 있는 PDM(Project Data Management) 또는 PLM (Product Life-cycle Management) 시스템을 벤치마킹한 CPLM (Construction Project Life-cycle Management)과 같은 BIM 기반 협업 시스템이 등장하고 있다. 하지만 기존의 이러한 협업 시스템의 경우, 건설 프로젝트가 가지는 다양한 계약 방식, 관리 단계, 관련 정보의 체계 등에 대한 종합적 계획 없이 프로젝트의 각 참여 주체들의 기존 관리 방식을 도입함으로써, 당초 BIM 기술을 도입하여 달성하고자 하는 원활한 협업 환경을 구축하는데 한계를 가지고 있다. 따라서 본 연구에서는 최근 BIM 가이드라인의 도입 등에서 시도되고 있는 BIM Planning이라는 개념을 활용하여, BIM 기반 협업 시스템의 구축 이전에 BIM을 관리하기 위한 관리 구조, 방식, 데이터 체계 등을 효과적으로 계획하고, 이를 시스템에 반영시킴으로써 보다 효과적인 BIM 기반 협업 환경이 구축될 수 있는 체계를 제안하였다.