Document semantic analysis/selection with knowledge creativity capability

• US 20010014852A1
• Filed: 02/07/2001
• Published: 08/16/2001
• Est. Priority Date: 09/09/1998
• Status: Abandoned Application

• Current Assignee: Igor V. Sovpel, Leonid S. Batchilo, Valery M. Tsourikov
• Original Assignee: Igor V. Sovpel, Leonid S. Batchilo, Valery M. Tsourikov
• Inventors: Tsourikov, Valery M., Batchilo, Leonid S., Sovpel, Igor V.
• Application Number:
  US09/745,261
• Publication Number:
  US 20010014852A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/221 Parsing markup language streams streaming G06F40/149
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation

Abstract

A computer based software system and method for semantically processing a user entered natural language request to identify and store linguistic subject-action-object (SAO) structures, using such structures as key words/phrases to search local and web-based databases for downloading candidate natural language documents, semantically processing candidate document texts into candidate document SAO structures, and selecting and storing only relevant documents whose SAO structures include a match with a stored request SAO structure. Further features include analyzing relationships among relevant document SAO structures and creating new SAO structures based on such relationships that may yield new knowledge concepts and ideas for display to the user and generating and displaying natural language summaries based on the relevant document SAO structures.

Claims

1. A natural language document analysis and selection system comprising,

a general purpose computer having a monitor, a central processing unit (CPU), a user input device for generating request data representing a natural language request, and a communications device for communication with local and remote natural language document databases,

said CPU comprising

(i) first storage means for storing the request data,

(ii) a semantic processor for generating request subject-action-object (SAO) extractions in response to receiving request data, and

(iii) SAO storage means for storing representations of the request SAO extractions.

2. A system as set forth in

claim 1

, wherein said communication device conveys candidate document data to said CPU for storage in said first storage means, the candidate document data representing natural language document text,

said semantic processor generating candidate document SAO extractions in response to receiving candidate document data, and

said SAO storage means also storing representations of candidate document SAO extractions.

3. A system as set forth in

claim 2

, wherein said semantic processor identifies matches between said representations of said request SAO extractions and said candidate document SAO extractions.

4. A system as set forth in

claim 3

, wherein said semantic processor comprises means for marking as relevant candidate document data that includes at least one representation of candidate document SAO extraction that matches at least one representation of request SAO extraction.

5. A system as set forth in

claim 4

, wherein said semantic processor comprises means for deleting stored candidate document data and stored representations of candidate document SAO extractions for those documents that have no representation of candidate document SAO extraction that matches a representation of request SAO extraction.

6. A system as set forth in

claim 3

, wherein said semantic processor includes an SAO text analyzer having a plurality of stored text formatting rules, coding rules, word tagging rules, SAO recognizing rules, parsing rules, SAO extraction rules, and normalizing rules for applying such rules to the request data and candidate document data such that said representations of candidate document SAO extractions and of request SAO extractions comprise candidate document and request SAO structures, respectively.

7. A system as set forth in

claim 6

further comprising second storage means for storing request SAO structures and for applying SAO structures as key words/phrases to said communication device for application to document search engines on the WEB or local databases to cause downloading of candidate document data to the system.

8. A system as set forth in

claim 6

further comprising an SAO synthesizer for generating and storing for display on said monitor natural language summaries of marked documents in response to receipt of document SAO structures.

9. A system as set forth in

claim 6

further comprising an SAO synthesizer for analyzing relationships among subjects, actions, and objects among relevant and stored SAO structures and processing those SAO structures that have a relationship with at least one other SAO structure to generate a different SAO structure and storing the different SAO structure for display to the user.

10. A system as set forth in

claim 9

wherein said relationship comprises:

S₁-A₁-O₁ S₂-A₂-O₂

where S₁ synonym O₂

Then S₂-A₂-S₁-A₁-O₁.

11. In a digital data processing system including the World Wide Web and a general purpose computer having a monitor, a central processing unit (CPU), a user input device, and a communications device for communication with local and remote natural language document databases, the method of analyzing and selecting natural language documents comprising,

generating request data representing a natural language request,

storing the request data,

semantically processing the request data to generate request subject-action-object (SAO) extractions, and

storing representations of the request SAO extractions.

12. The method as set forth in

claim 11

, wherein said communication device conveys candidate document data to said CPU, the candidate document data representing natural language document text,

storing the candidate document data,

said semantically processing including generating candidate document SAO extractions in relation to the candidate document data, and

storing representations of candidate document SAO extractions.

13. A method as set forth in

claim 12

, wherein said semantically processing includes identifying matches between said representations of said request SAO extractions and said candidate document SAO extractions.

14. A method as set forth in

claim 13

, wherein said semantically processing comprises marking as relevant candidate document data that includes at least one representation of candidate document SAO extraction that matches at least one representation of request SAO extraction.

15. A method as set forth in

claim 14

, wherein said semantically processing comprises deleting access to stored candidate document data and stored representations of candidate document SAO extractions for those documents that have no representation of candidate document SAO extraction that matches a representation of request SAO extraction.

16. A method as set forth in

claim 13

, wherein said semantically processing includes applying a plurality of stored text formatting rules, noun and verb recognition rules, coding rules, word tagging rules, SAO recognizing rules, parsing rules, SAO extraction rules, and normalizing rules to the request data and candidate document data such that said representations of candidate document SAO extractions and representations of request SAO extractions comprise candidate document and request SAO structures, respectively.

17. A method as set forth in

claim 16

further comprising storing request SAO structures and applying SAO structures as key words/phrases to document search engines on the WEB or local databases to cause downloading of candidate document data to the CPU.

18. A method as set forth in

claim 16

further comprising generating and storing and displaying on said monitor natural language summaries of marked relevant documents in relation to relevant document SAO structures.

19. A method as set forth in

claim 16

further comprising analyzing relationships among subjects, actions, and objects among relevant and stored SAO structures, further processing those SAO structures that have a relationship with at least one other relevant and stored SAO structure, and generating a different SAO structure based on the said relationship, and

storing the different SAO structure and displaying the different SAO structure to the user.

20. A method as set forth in

claim 19

wherein said relationship comprises:

S₁-A₁-O₁ comprises one relevant and stored SAO structure

S₂-A₂-O₂ comprises a second relevant and stored SAO structure

where said relationship comprises S₁ synonym O₂ and the different SAO structure is

S₂-A₂-S₁-A₁-O₁.

21. A method as set forth in

claim 19

wherein said relationship comprises:

S₁-A₁-O₁ comprises one relevant and stored SAO structure

S₂-A₂-O₂ comprises a second relevant and stored SAO structure

where said relationship exists between S₁ and A₂ and the different SAO structure is

S₁-A₁/A₂-O₁

where / means alternate.