Systems and methods for identifying claims associated with electronic text

• US 8,671,341 B1
• Filed: 01/04/2008
• Issued: 03/11/2014
• Est. Priority Date: 01/05/2007
• Status: Expired due to Fees

• Current Assignee: Linguastat, Inc.
• Original Assignee: Linguastat, Inc.
• Inventors: Hellwig, John, Pierre, John M., Butler, Mark H.
• Primary Examiner(s): Hong, Stephen
• Assistant Examiner(s): Ludwig, Matthew
• Application Number:
  US12/006,716
• Time in Patent Office: 2,258 Days
• Field of Search: 715/255, 715/256, 715/259, 715/254, 704/9, 704/251, 704/4
• US Class Current: 715/254
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

A system, method, and computer program for identifying claims associated with electronic text are provided. Electronic text is accessed. Linguistic content associated with the electronic text is identified. A linguistic structure is generated based on the linguistic content identified. The linguistic structure is compared to a claim template. A claim is identified based on the comparison.

Claims

1. A method for identifying claims associated with electronic text comprising:

accessing electronic text;

identifying linguistic content associated with the electronic text wherein the linguistic content includes a plurality of linguistic features;

generating a linguistic structure based on the linguistic content identified, wherein the linguistic structure identifies at least a relationship between a first two or more linguistic features of the plurality of linguistic features;

comparing the linguistic structure to a claim template, wherein the claim template identifies the same relationship between a second two or more linguistic features, each of the second two or more linguistic features corresponding to a linguistic feature of the first two or more linguistic features;

in response to a determination that each of the first two or more linguistic features is a hyponym of the corresponding linguistic feature in the second two or more linguistic features, identifying a claim within the electronic text.

2. The method recited in claim 1, wherein the electronic text comprises electronic media.

3. The method recited in claim 1, further comprising extracting the identified claim.

4. The method recited in claim 1, further comprising storing the identified claim.

5. The method recited in claim 4, further comprising allowing a user to perform a search of the stored claim.

6. The method of claim 1, further comprising storing the linguistic structure.

7. The method of claim 1, further comprising indexing the linguistic structure.

8. The method recited in claim 1, wherein the claim template comprises a structured claim template.

9. The method recited in claim 1, wherein the claim template comprises a statistical claim template.

10. The method recited in claim 1, wherein identifying linguistic content associated with the electronic text comprises identifying at least one entity.

11. The method recited in claim 1, further comprising monitoring an information source for the electronic text.

12. The method recited in claim 1, further comprising determining a likelihood of regulatory compliance of the identified claim.

13. A system for identifying claims associated with electronic text comprising:

one or more processors;

a monitoring module configured to access electronic text;

a linguistic structure module configured to identify linguistic content associated with the electronic text and generate a linguistic structure based on the linguistic content identified, wherein the linguistic content includes a plurality of linguistic features and the linguistic structure identifies at least a relationship between a first two or more linguistic features of the plurality of linguistic features;

a template module configured to compare the linguistic structure to a claim template and to identify a claim within the electronic text based on the comparison,

wherein the claim template identifies the same relationship between a second two or more linguistic features, each of the second two or more linguistic features corresponding to a linguistic feature of the first two or more linguistic features;

wherein the comparison is performed by determining whether each of the first one or more linguistic features is a hyponym of the corresponding linguistic feature in the second one or more linguistic features.

14. The system recited in claim 13, wherein the electronic text comprises electronic media.

15. The system recited in claim 13, wherein the template module is further configured to extract the claim from the electronic text.

16. The system recited in claim 13, further comprising claims storage configured to store the claim.

17. The system recited in claim 16, wherein the claims storage is further configured to allow a user to perform a search of the stored claim.

18. The system of claim 16, wherein the claims storage is further configured to store the linguistic structure.

19. The system of claim 16, wherein the claims storage is further configured to index the linguistic structure.

20. The system recited in claim 13, wherein the claim template comprises a structured claim template.

21. The system recited in claim 13, wherein the at least one claim template comprises a statistical claim template.

22. The system recited in claim 13, wherein the linguistic structure module is further configured to identify at least one entity.

23. The system recited in claim 13, further comprising an analysis module configured to determine a likelihood of regulatory compliance of the identified claim.

24. A computer program embodied on a non-transitory computer readable medium, the computer program being executable by a processor for identifying claims associated with electronic text, the method comprising:

accessing electronic text;

identifying linguistic content associated with the electronic text, wherein the linguistic content includes a plurality of linguistic features;

generating a linguistic structure based on the linguistic content identified, wherein the linguistic structure identifies at least a relationship between a first two or more linguistic features of the plurality of linguistic features;

comparing the linguistic structure to a claim template, wherein the claim template identifies the same relationship between a second two or more linguistic features, each of the second two or more linguistic features corresponding to a linguistic feature of the first two or more linguistic features;

in response to a determination that each of the first two or more linguistic features is a hyponym of the corresponding linguistic feature in the second two or more linguistic features, identifying a claim within the electronic text.

25. The computer program recited in claim 24, wherein the electronic text comprises electronic media.

26. The computer program recited in claim 24, further comprising extracting the identified claims.

27. The computer program recited in claim 24, further comprising storing the identified claim.

28. The computer program recited in claim 27, further comprising allowing a user to perform a search of the stored claim.

29. The computer program of claim 24, further comprising storing the linguistic structure.

30. The computer program of claim 24, further comprising indexing the linguistic structure.

31. The computer program recited in claim 24, wherein the claim template comprises a structured claim template.

32. The computer program recited in claim 24, wherein the at least one claim template comprises a statistical claim template.

33. The computer program recited in claim 24, wherein identifying linguistic content associated with the electronic text comprises identifying at least one entity.

34. The computer program recited in claim 24, further comprising monitoring an information source for the electronic text.

35. The computer program cited in claim 24, further comprising determining a likelihood of regulatory compliance of the identified claim.