Digital library of construction informatics
and information technology in civil engineering and construction


Paper w78-2005-d6-5-scherer:
Constructing Building Information Networks from Proprietary Documents and Product Model Data

Facilitated by the SciX project

RJ Scherer & S-E Schapke

Constructing Building Information Networks from Proprietary Documents and Product Model Data

Abstract: The paper presents a novel Building Information Mining Framework (BIMF) that allows utilising building information captured in product model data as a valuable source of background knowledge in information retrieval and mining. Central to the framework is a four layered Bayesian Network adapted from probabilistic Information Retrieval models developed in the 90s. Capturing, combining and visualising the results of various text and model analyses as well as representing aspects of the current mining context, the network allows for explicitly representing content of the repository in personalisable information networks. These networks enable not only the retrieval of information from the text documents but also the explicit interlinking of the document and the product model domain to also support the understanding of the available interrelations and the exploration of new mining and integration strategies. The paper introduces the principal approach, explains the components of the basic network and suggests several further extensions that are currently still under development.



Full text: content.pdf (458,088 bytes) (available to registered users only)

Series: w78:2005 (browse)
Similar papers:
Sound: N/A.

Permission to reproduce these papers has been graciously provided by the Technische Universitšt Dresden.


hosted by University of Ljubljana



© itc.scix.net 2003
FIRST PREVIOUS NEXT LAST Home page of this database login Powered by SciX Open Publishing Services 1.002 February 16, 2003