Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/73569
Title: Knowledge discovery and management for product design through text mining - A case study of online information integration for designers
Authors: Liu, Y.
Lu, W.F. 
Loh, H.T. 
Keywords: Knowledge discovery and management
Online information
Product design
Text classification
Text mining
Issue Date: 2007
Source: Liu, Y.,Lu, W.F.,Loh, H.T. (2007). Knowledge discovery and management for product design through text mining - A case study of online information integration for designers. Proceedings of ICED 2007, the 16th International Conference on Engineering Design DS 42 : -. ScholarBank@NUS Repository.
Abstract: Product innovation and design is often regarded as an information and knowledge intensive activity. While existing tools, i.e. search engines and product data management systems, have provided a certain degree of assistance to design community in information storage, processing and retrieval, many challenges remain, especially if we intend to provide advanced capabilities so that the designers are able to handle the overloaded information. These capabilities include, but are not restricted to, automated classification of design relevant documents based on product architecture, relevance analysis and summarization of design documents, identification of product function from customer feedback\reviews in conceptual design, personal design information subscription and management, market analysis and competitive intelligence report generation and so on. To fulfill these demands, an integrated text mining system for knowledge discovery and management in product design is proposed. In this paper, we report our study on the integration of online information with the internal knowledge base, e.g. product taxonomy, as part of our efforts towards the realization of the proposed system. Several key techniques are explained, i.e. maximal frequent word sequence algorithm in discovering the quality phrases, document profile model based on salient semantic information and finally concept based automated text classification approach. Experimental studies have demonstrated its effectiveness.
Source Title: Proceedings of ICED 2007, the 16th International Conference on Engineering Design
URI: http://scholarbank.nus.edu.sg/handle/10635/73569
ISBN: 1904670024
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

44
checked on Jan 21, 2018

Google ScholarTM

Check


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