Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/135850
Title: PROCESS-ORIENTED KNOWLEDGE DISCOVERY TO SUPPORT PRODUCT DESIGN USING TEXT MINING
Authors: LAN LIJUN
Keywords: knowledge discovery, product design process, text mining, process mining, event detection, organization mining
Issue Date: 18-Jan-2017
Citation: LAN LIJUN (2017-01-18). PROCESS-ORIENTED KNOWLEDGE DISCOVERY TO SUPPORT PRODUCT DESIGN USING TEXT MINING. ScholarBank@NUS Repository.
Abstract: Design documents accumulated by corporation IT systems have become valuable sources of evidence for design information and knowledge management. Identification and extraction of the embedded information and knowledge into a clear and usable format will accelerate continuous learning from past design efforts for competitive product innovation and efficient design process management. To reuse the embedded design information, most of the existing design information extraction systems focus on either organizing design documents for efficient document retrieval or extracting relevant product information for product optimization. This study seeks to further extract design information deep into the document content, with a focus on process-oriented design knowledge. For this purpose, a process-oriented knowledge discovery system for extracting process relevant knowledge from archival design documents is developed, and three subjects are investigated: process information extraction, process mining, and process knowledge interpretation. The developed knowledge discovery system is tested and illustrated using a real-life design project.
URI: http://scholarbank.nus.edu.sg/handle/10635/135850
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LanLJ.pdf19.45 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

38
checked on Dec 14, 2018

Download(s)

85
checked on Dec 14, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.