Patrick William Jamieson, 10172
Parkshore Dr., Fishers, IN (US) 46038
Subject to any disclaimer, the term of this patent is extended or adjusted under 35 U.S.C. 154(b) by 675 days.
Sep. 20, 2005
G06K 9/68 (2006.01)
G06K 9/64 (2006.01)
U.S. CI 382/217; 382/305; 704/9
Field of Classification Search 382/181,
382/209, 217, 305; 358/403; 704/4, 9; 707/1-10 See application file for complete search history.
U.S. PATENT DOCUMENTS
4,914,590 A * 4/1990 Loatman et al 704/8
5,267,155 A 11/1993 Buchanan et al.
5,523,945 A * 6/1996 Satoh et al 704/9
5,655,130 A 8/1997 Dodge etal.
5,684,999 A * 11/1997 Okamoto 704/9
5,822,743 A 10/1998 Gupta etal.
5,899,989 A * 5/1999 Ikeuchietal 707/3
5,987,446 A * 11/1999 Corey etal 707/3
6,182,095 Bl 6,263,335 Bl4 7,302,383 B24 2003/0101056 Al 2004/0019855 Al
Rebholz-Schuhmann D, Kirsch H, Couto F (2005) Facts from text—Is text mining ready to deliver? PLoS Biol 3(2): e65.
* cited by examiner
Primary Examiner—Daniel G Mariam
Document templates could improve the speed, cost, and quality of documentation if appropriate templates could be located without undue selection burden. Semantic retrieval (IR) can greatly improve the precision of finding relevant document templates. The present invention discloses a process which implements a semantic information retrieval system to locate template documents, using as search vectors the semantic content of sentences from a new partially completed document. The system enables the author to quickly and easily transfer sentences from template documents into the new document. The system provides options for the author to match against specialized template collections and subsets of template documents. A significant advantage of the present invention over other template based methods is ability to retrieve a relevant template document when there are many thousands of exemplar documents without having to construct a formal query.
15 Claims, 6 Drawing Sheets