SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR DETERMINING DOCUMENT VALIDITY

• US 20100202698A1
• Filed: 02/10/2009
• Published: 08/12/2010
• Est. Priority Date: 02/10/2009
• Status: Active Grant

• Current Assignee: Tungsten Automation Corp.
• Original Assignee: Kofax Image Products Incorporated (Kofax Ltd.)
• Inventors: Thompson, Stephen Michael, Amtrup, Jan W., Borrey, Roland G., Schmidtler, Mauritius A.R.
• Granted Patent: US 8,345,981 B2
• Time in Patent Office: Days
• US Class Current: 382/195
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: H04N 1/40 Picture signal circuits H04N1/387 takes precedence

Abstract

A method according to one embodiment includes extracting an identifier from an electronic first document, and identifying a complementary document associated with the first document using the identifier. A validity of the first document is determined by simultaneously considering: textual information from the first document; textual information from the complementary document; and predefined business rules. An indication of the determined validity is output. Systems and computer program products for providing, performing, and/or enabling the methodology presented above are also presented.

Claims

1. A method, comprising:

performing optical character recognition (OCR) on a scanned image of a first document;

extracting an identifier from the first document;

identifying a complementary document associated with the first document using the identifier;

generating a list of hypotheses mapping the first document to the complementary document using;

textual information from the first document;

textual information from the complementary document; and

predefined business rules;

determining a validity of the first document based on the hypotheses; and

outputting an indication of the determined validity.

2. A method as recited in claim 1, wherein the first document is an invoice.

3. A method as recited in claim 2, wherein the complementary document is at least one of a purchase order, a memorandum, and a delivery note having a relationship with the invoice.

4. A method as recited in claim 1, further comprising scanning the first document using a scanner for generating the scanned image.

5. A method as recited in claim 1, further comprising correcting OCR errors in the first document using at least one of the textual information from the complementary document and the predefined business rules.

6. A method as recited in claim 1, further comprising normalizing data from the first document using at least one of the textual information from the complementary document and the predefined business rules.

7. A method as recited in claim 1, further comprising normalizing data from the complementary document using at least one of the textual information from the first document and the predefined business rules.

8. A method as recited in claim 1, further comprising generating an alert upon encountering a potential problem when determining the validity of the first document.

9. A method as recited in claim 8, wherein the alert includes identification of a mismatch in expected similar or identical values in the first and complementary documents.

10. A method as recited in claim 1, further comprising receiving user input indicating at least one of a correction and a validation of a line item or header field item of the first document.

11. A method as recited in claim 1, wherein determining the validity of the first document includes automatically estimating values for expected or actual line items in the first document.

12. A method as recited in claim 1, wherein determining the validity of the first document includes automatically correcting values for expected or actual line items or header field items in the first document based on at least one of the textual information from the complementary document and the business rules.

13. A method as recited in claim 1, wherein the first document is at least one of an explanation of benefits document, a sales order document, and an insurance claim document.

14. A method as recited in claim 1, further comprising correlating a term on the first document and a different term on the complementary document as referring to a same thing.

15. A method as recited in claim 14, further comprising storing the correlation of the terms in a database.

16. A method as recited in claim 1, further comprising reconstructing the first document using the hypotheses and business rules, wherein the determining the validity step analyzes the reconstructed first document.

17. A method as recited in claim 1, further comprising, upon determining that the first document is valid, generating knowledge based on the hypotheses generated.

18. A method as recited in claim 17, wherein the generating the knowledge includes using transduction.

19. A method as recited in claim 1, further comprising outputting a reconciliation screen to a user upon failing to determine the first document is valid or determining that the first document is invalid.

20. A method as recited in claim 19, wherein a notification to access the reconciliation screen is sent to a sender of the first document.

21. A method as recited in claim 19, further comprising receiving a modification to the first document by a user viewing the reconciliation screen.

23. A method as recited in claim 1, wherein the determined validity is used to validate a business transaction.

24. A method as recited in claim 1, further comprising:

performing OCR on a scanned image of a second document;

extracting an identifier from the second document;

identifying a second complementary document associated with the second document;

generating a list of hypotheses mapping the second document to the second complementary document using;

textual information from the second document;

textual information from the second complementary document; and

predefined business rules;

determining a validity of the second document based on the hypotheses; and

outputting an indication of the determined validity of the second document.

25. A method as recited in claim 24, wherein the validated first document is used as the second complementary document.

26. A method as recited in claim 1, further comprising repeating the method using a second complementary document for again determining a validity of the first document.

22. A method as recited in claim 22, further comprising attempting to re-validate the modified first document.

27. A method, comprising:

extracting an identifier from an electronic first document;

identifying a complementary document associated with the first document using the identifier;

determining a validity of the first document by simultaneously considering;

textual information from the first document;

textual information from the complementary document; and

predefined business rules; and

outputting an indication of the determined validity.

28. A method as recited in claim 27, further comprising correcting OCR errors in the first document using at least one of the textual information from the complementary document and the predefined business rules.

29. A method as recited in claim 27, further comprising normalizing data from the first document using at least one of the textual information from the complementary document and the predefined business rules.

30. A method as recited in claim 27, further comprising normalizing data from the complementary document using at least one of the textual information from the first document and the predefined business rules.

31. A method as recited in claim 27, further comprising generating an alert upon encountering a potential problem when determining the validity of the first document.

32. A method as recited in claim 31, wherein the alert includes identification of a mismatch in expected similar or identical values in the first and complementary documents.

33. A method as recited in claim 27, further comprising receiving user input indicating at least one of a correction and a validation of a line item or header field item of the first document.

34. A method as recited in claim 27, wherein determining the validity of the first document includes automatically estimating values for expected or actual line items in the first document.

35. A method as recited in claim 27, wherein determining the validity of the first document includes automatically correcting values for expected or actual line items or header field items in the first document based on at least one of the textual information from the complementary document and the business rules.

36. A method as recited in claim 27, wherein the determined validity is used to validate a business transaction.

37. A method as recited in claim 27, further comprising:

acquiring an electronic second document;

identifying a second complementary document associated with the second document;

generating a list of hypotheses mapping the second document to the second complementary document using;

textual information from the second document;

textual information from the second complementary document; and

predefined business rules;

determining a validity of the second document based on the hypotheses; and

outputting an indication of the determined validity of the second document.

38. A method as recited in claim 37, wherein the validated first document is used as the second complementary document.

39. A method as recited in claim 27, further comprising repeating the method using a second complementary document for again determining a validity of the first document.

40. A computer program product embodied on a computer readable medium, comprising:

code for performing optical character recognition (OCR) on a scanned image of a first document;

code for extracting an identifier from the first document;

code for identifying a complementary document associated with the first document using the identifier;

code for generating a list of hypotheses mapping the first document to the complementary document using;

textual information from the first document;

textual information from the complementary document; and

predefined business rules;

code for determining a validity of the first document based on the hypotheses; and

code for outputting an indication of the determined validity.

41. A system, comprising:

a device for performing optical character recognition (OCR) on a scanned image of a first document, extracting an identifier from the first document, identifying a complementary document associated with the first document using the identifier, generating a list of hypotheses mapping the first document to the complementary document using textual information from the first document, textual information from the complementary document, and predefined business rules, determining a validity of the first document based on the hypotheses, and outputting an indication of the determined validity

42. A computer program product embodied on a computer readable medium, comprising:

code for extracting an identifier from an electronic first document;

code for identifying a complementary document associated with the first document using the identifier;

code for determining a validity of the first document by simultaneously considering;

textual information from the first document;

textual information from the complementary document; and

predefined business rules; and

code for outputting an indication of the determined validity.

43. A system, comprising:

a device for extracting an identifier from an electronic first document, identifying a complementary document associated with the first document using the identifier, determining a validity of the first document by simultaneously considering textual information from the first document, textual information from the complementary document, and predefined business rules, and

outputting an indication of the determined validity.