Systems and methods for routing facsimiles based on content

• US 8,599,419 B2
• Filed: 08/30/2012
• Issued: 12/03/2013
• Est. Priority Date: 05/01/2007
• Status: Active Grant

• Current Assignee: Tungsten Automation Corp.
• Original Assignee: Kofax Incorporated
• Inventors: Couchman, Roy
• Primary Examiner(s): Cato, Miya J
• Application Number:
  US13/600,148
• Publication Number:
  US 20120320422A1
• Time in Patent Office: 460 Days
• Field of Search: None
• US Class Current: 358/1.15
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: H04N 1/00095 Systems or arrangements for the transmission of the picture signal
• CPC Class Codes: H04N 1/00204 with a digital computer or a digital computer system, e.g. an internet server programmed control between transmitter and receiver or between image input and image output device H04N1/32561
• CPC Class Codes: H04N 1/00209 Transmitting or receiving image data, e.g. facsimile data, via a computer, e.g. using e-mail, a computer network, the internet, I-fax
• CPC Class Codes: H04N 1/00355 Mark-sheet input sensing record carriers G06K7/00; character recognition G06V30/10; document-oriented image-based pattern recognition G06V30/40
• CPC Class Codes: H04N 1/0036 Alphanumeric symbols
• CPC Class Codes: H04N 1/00374 on the same page as at least a part of the image
• CPC Class Codes: H04N 1/00968 by scanning marks on a sheet mark-sheet input means H04N1/00355; sensing record carriers G06K7/00
• CPC Class Codes: H04N 2201/0094 Multifunctional device, i.e. a device capable of all of reading, reproducing, copying, facsimile transception, file transception
• CPC Class Codes: H04N 2201/323 for tracing or tracking, e.g. forensic tracing of unauthorized copies

Abstract

A method for routing a facsimile according to one embodiment includes receiving or generating text of a facsimile in a computer-readable format; routing the facsimile or text thereof to an intended recipient identified by recognizing at least one of a name, an email address and contact information of the intended recipient in the facsimile; analyzing the text of the facsimile for at least one of a meaning and a context of the text; and routing the facsimile or text thereof to one or more other destinations based on the analysis. A method according to another embodiment includes analyzing a pattern of light and dark areas of a facsimile in a computer-readable format; correlating the pattern to one or more forms; and routing the facsimile to one or more destinations based on the correlation, with the proviso that the analyzing, correlating and routing are performed without optical character recognition.

Claims

1. A method for routing a facsimile, comprising:

receiving or generating text of a facsimile in a computer-readable format;

ascertaining one or more of a significance and a relevance of one or more words of the text by ascertaining a position of one or more keywords in the text, wherein at least two of the keywords are not adjacent in the text;

routing the facsimile or text thereof to an intended recipient identified by recognizing at least one of a name, an email address and contact information of the intended recipient in the facsimile;

analyzing the text of the facsimile for at least one of a meaning and a context of the text; and

routing the facsimile or text thereof to one or more other destinations based on the analysis.

2. A method as recited in claim 1, wherein more than one keyword is determined by the analysis, wherein at least two of the keywords are not adjacent in the facsimile text.

3. A method as recited in claim 1, wherein the portions of the text used to determine the one or more other destinations does not include a name, a physical address, an email address, and a fax number of the intended recipient.

4. A method as recited in claim 1, wherein the facsimile text that is analyzed does not contain destination information.

5. A method as recited in claim 4, wherein the destination information that is not contained in the facsimile text includes a name of an intended facsimile recipient, a physical address, an email address, and a fax number.

6. A method as recited in claim 1, wherein the analysis further includes comparing one or more keywords in the text to at least one other element in the text.

7. A method as recited in claim 6, wherein the element includes one or more of a word, a symbol, a keyword, and a graphic element.

8. A method as recited in claim 1, wherein the analysis further includes matching one or more keywords in the text to data stored in memory.

9. A method as recited in claim 1, wherein the analysis further includes classifying the text as a specific document type, wherein the classifying utilizes one or more of:

a naï

ve Bayes classifier, tf-idf weighting, latent semantic analysis, support vector machines, an artificial neural network, a k-nearest neighbor algorithm, decision trees, and concept mining.

10. A method as recited in claim 1, wherein the analysis further includes classifying at least one of the keywords in the text as a specific word type.

11. A method as recited in claim 1, wherein the text is generated by converting the facsimile to a computer-readable format.

12. A method as recited in claim 1, wherein the text is generated by converting a source to text in a different human language other than a human language of the source.

13. The method as recited in claim 1, wherein the portions of the text used to determine the one or more other destinations does not include a name, a physical address, an email address, and a fax number of the intended recipient,

wherein the analysis includes at least two of:

determining two or more non-adjacent keywords in the text, comparing one or more keywords in the text to at least one other element in the text;

matching one or more keywords in the text to data stored in memory;

classifying at least one of the keywords in the text as a specific word type; and

classifying the text as a specific document type,

wherein the element includes one or more of a word, a symbol, a keyword, and a graphic element,

wherein the text is produced by converting a source to text in a different human language other than a human language of the source,

wherein the classifying utilizes one or more of;

a na{dot over (i)}ve Bayes classifier, tf-idf weighting, latent semantic analysis, support vector machines, an artificial neural network, a k-nearest neighbor algorithm, decision trees, and concept mining, and

wherein multiple facsimile destinations are determined,

wherein at least one of the analyzing and the routing comprises at least one parallel processing operation.

14. A computer program product comprising a non-transitory computer readable medium having computer code stored thereon, which when executed by a processor causes the processor to perform the method of claim 1.

15. A method for routing a facsimile, comprising:

analyzing a pattern of light and dark areas of a facsimile in a computer-readable format;

correlating the pattern to one or more forms using one or more support vector machines (SVMs); and

routing the facsimile to one or more destinations based on the correlation, with the proviso that the analyzing, correlating and routing are performed without optical character recognition.

16. A method as recited in claim 15,

wherein the form relates to a certain document type.

17. A method as recited in claim 15, wherein the analyzing determines one or more document features of the pattern.

18. A method as recited in claim 17, wherein the correlating includes comparing at least one of the document features to features of the one or more forms.

19. A method as recited in claim 17, wherein the correlating includes determining the position of one or more of the document features within the pattern.

20. A method as recited in claim 17, wherein the correlating includes comparing at least one of the document features to other features of the pattern.

21. A method for routing a facsimile, comprising:

converting a facsimile to a computer-readable document;

identifying one or more keywords in the document;

analyzing the document by determining at least one of;

a relation of one or more symbols in the document to the one or more keywords,

a relation of one or more keywords in the document to the one or more other keywords,

a relation of graphic elements to the one or more keywords,

a classification of the text of the document as a specific document type,

a significance of text of the one or more keywords;

determining a facsimile destination based on the analysis; and

routing the facsimile to the facsimile destination based on the determination;

routing the facsimile to a default destination when no facsimile destination determined based on the analyzing is a viable destination.

22. A method as recited in claim 21, wherein multiple facsimile destinations are determined;

wherein the facsimile is routed to the multiple destinations, wherein at least one destination is determined using text that does not contain a name, a physical address, an email address, and a fax number associated with the one destination.

23. A method as recited in claim 21, wherein the computer-readable document is also routed to the facsimile destination based on the determination.

24. A method as recited in claim 21, wherein the document does not contain destination information, wherein the destination information that is not contained in the document includes a name of, a physical address, an email address, and a fax number an intended facsimile recipient.

25. A computer program product comprising a non-transitory computer readable medium having computer code stored thereon, which when executed by a processor causes the processor to perform the method of claim 21.

26. A method for routing a facsimile, comprising:

obtaining a pattern of light and dark areas of a computer-readable version of a facsimile;

determining one or more document features from the pattern;

determining a facsimile destination based on at least two of the following operations;

comparing the one or more document features to features of one or more forms, said forms relating to one or more of a certain document type;

determining the position of one or more of the document features within the pattern; and

comparing at least one of the document features to other features of the pattern; and

routing the facsimile to the facsimile destination based on the determination of the destination, with the proviso that the routing is performed without results of optical character recognition.

27. A computer program product comprising a non-transitory computer readable medium having computer code stored thereon, which when executed by a processor causes the processor to perform the method of claim 26.

28. A system for routing a facsimile, comprising:

a processor; and

logic in or executable by the processor for converting the facsimile to a computer-readable document;

logic in or executable by the processor for identifying one or more keywords in the document;

logic in or executable by the processor for analyzing the document by determining at least three of;

a relation of one or more words in the document to the one or more keywords,

a relation of one or more symbols in the document to the one or more keywords,

a relation of the one or more keywords in the document to the one or more other keywords,

a relation of graphic elements to the one or more keywords,

a position of one or more keywords in the document,

a classification of the text of the document as a specific document type,

a classification of one or more keywords in the document as a specific word type, and

a significance of text of the one or more keywords;

logic in or executable by the processor for determining a facsimile destination based on the analysis; and

logic in or executable by the processor for routing the facsimile to the facsimile destination based on the determination,

wherein the facsimile destination is determined using text that does not contain a name, a physical address, an email address, and a fax number associated with the facsimile destination.

29. A system as recited in claim 28, wherein multiple facsimile destinations are determined;

wherein the facsimile is routed to the multiple destinations, wherein a second of the multiple destinations is associated with an intended recipient, wherein the intended recipient is identified by recognizing at least one of a name, an email address and contact information of the intended recipient in the computer-readable document.

30. A system as recited in claim 28, wherein the computer-readable document is also routed to the facsimile destination based on the determination.

31. A system as recited in claim 30, wherein multiple facsimile destinations are determined, wherein the facsimile is routed to the multiple destinations, and wherein at least one of the destinations is a default destination.

32. A system for routing a facsimile, comprising:

a processor;

logic in or executable by the processor for obtaining a pattern of light and dark areas of the facsimile;

logic in or executable by the processor for determining one or more document features from the pattern;

logic in or executable by the processor for determining a facsimile destination based on at least one of the following, with the proviso that the determining a facsimile destination is performed without results of optical character recognition;

logic for comparing the one or more document features to features of one or more forms, said forms relating to one or more of a certain document type;

logic for determining the position of one or more of the document features within the pattern; and

logic for comparing at least one of the document features to other features of the pattern; and

logic for generating a text file from the facsimile; and

logic for routing the facsimile and the text file to the facsimile destination based on the determination of the destination,

logic for determining from the generated text file any information needed to electronically log or track a transmission of the facsimile.

33. A system for initiating a business process, comprising:

a processor;

logic in or executable by the processor for analyzing a facsimile in a computer-readable format for at least one of a meaning and a context of the facsimile;

logic in or executable by the processor for selecting a business process based on the at least one of the context and meaning of the facsimile; and

logic in or executable by the processor for initiating the business process based on the analysis;

logic in or executable by the processor for notifying a sender of a problem with the business process.

34. A system as recited in claim 33, further comprising logic for sending a confirmation back to an original sender of the facsimile when at least one of the business process is initiated and the business process is completed.