Process and system for the semantic selection of document templates

• US 7,492,949 B1
• Filed: 09/20/2005
• Issued: 02/17/2009
• Est. Priority Date: 09/20/2005
• Status: Active Grant

• Current Assignee: Asapp, Inc.
• Original Assignee: Logical Semantics, Inc.
• Inventors: Jamieson, Patrick William
• Primary Examiner(s): Mariam; Daniel G
• Application Number:
  US11/231,225
• Time in Patent Office: 1,246 Days
• Field of Search: 382/181, 382/209, 382/217, 382/305, 358/403, 704/4, 704/9, 707 1- 10
• US Class Current: 382/217
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires

Abstract

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.

Claims

1. A process for semantically selecting a document template, comprising:

(a) acquiring an input sentence, and

(b) a processor for performing the following steps;

looking up corresponding sentential proposition(s) to said sentence in a mapping table created by domain experts and,

(c) looking up corresponding sentence(s) to said sentential proposition(s) in said mapping table and,

(c) retrieving document templates from a template document collection that contain one or more of said sentences,

Whereby a partial solution set of document templates for each said sentential proposition is returned.

2. The method according to claim 1 where the input sentence is acquired through speech recognition.

3. The method according to claim 1 where the input sentence is acquired through a word processor.

4. The method according to claim 1 where all the sentences in a document under construction are processed and a list of corresponding proposition(s) are displayed.

5. The method according claim 1 wherein sentence(s) from a template document in the partial solution set are displayed as a list which are transferred to a new document under construction in response to user selection.

6. The method according to claim 1 wherein a count of unique documents in the partial solution set for each proposition is displayed.

7. The method according to claim 1 wherein a user restricts the documents from the partial solution set to a subset consisting of either personal templates, departmental templates, or company wide templates, or any combination thereof.

8. The method according to claim 1 wherein a user restricts the sentences for look up to specific sections within the template document collection.

9. A process for semantically selecting a document template, comprising:

(a) acquiring input sentence(s), and

(b) a processor for performing the following steps;

looking up corresponding sentential proposition(s) to said sentence(s) in a mapping table created by domain experts and,

(c) looking up corresponding sentence(s) to said sentential proposition(s) in said mapping table and,

(d) retrieving document templates from a document collection that contain one or more of said sentence(s) into separate partial solution sets and,

(e) performing a Boolean “

AND”

operations on said partial solution sets,

Whereby a solution set of document templates is returned.

10. The method according to claim 9 where the input sentence(s) are acquired through speech recognition.

11. The method according to claim 9 where the input sentence(s) are acquired through a word processor.

12. The method according to claim 9 wherein a count of unique template documents in the solution set is displayed.

13. The method according claim 9 wherein sentence(s) from a template document in the solution set are displayed as a list which are transferred to a document under construction in response to user selection.

14. The method according to claim 9 wherein a user restricts the documents from the solution set to a subset consisting of either personal templates, departmental templates, or company wide templates, or any combination thereof.

15. The method according to claim 9 wherein a user restricts the sentences to specific sections within the template document collection.