U.S. Department of Energy Office of Scientific and Technical Information
Title: PIRANHA: A Knowledge Discovery Engine Software
Software·
OSTI ID:1231328
Clustering textual information provides a number of useful capabilities for a PIRANHA user. Finding Similar Documents : A user can select a document of interest, and then quickly find other documents that are a close match. For example, a user may have an e-mail of interest found on a captured computer. Clustering allows for similar e-mail on other computers to be quickly found, thus potentially establishing a link. Document Sampling: A set of documents will usually contain common themes or topic. Representative documents from these themes can be quickly found, and presented to a user. For example, a captured hard drive may have thousands of documents representing many different topics, i.e., form finances to methods to favorite restaurants. Ten or twenty representative documents from these themes can be found, and used by a user to quickly determine what areas need further attention. Classifying Documents: A set of representative documents can be used by a user to define a topic of interest, and then related documents can be added to that set. This allows a user to pick specific documents that are of interest, perhaps nuclear materials, then allows the software agents to automatically put related document into the same nuclear materials folder.
To order this software or receive further information, please fill out the following request: Request Software
@misc{osti_1231328,
title = {PIRANHA: A Knowledge Discovery Engine Software, Version 00},
author = {},
abstractNote = {Clustering textual information provides a number of useful capabilities for a PIRANHA user. Finding Similar Documents : A user can select a document of interest, and then quickly find other documents that are a close match. For example, a user may have an e-mail of interest found on a captured computer. Clustering allows for similar e-mail on other computers to be quickly found, thus potentially establishing a link. Document Sampling: A set of documents will usually contain common themes or topic. Representative documents from these themes can be quickly found, and presented to a user. For example, a captured hard drive may have thousands of documents representing many different topics, i.e., form finances to methods to favorite restaurants. Ten or twenty representative documents from these themes can be found, and used by a user to quickly determine what areas need further attention. Classifying Documents: A set of representative documents can be used by a user to define a topic of interest, and then related documents can be added to that set. This allows a user to pick specific documents that are of interest, perhaps nuclear materials, then allows the software agents to automatically put related document into the same nuclear materials folder.},
doi = {},
url = {https://www.osti.gov/biblio/1231328},
year = {Thu Dec 18 00:00:00 EST 2008},
month = {Thu Dec 18 00:00:00 EST 2008},
note =
}