Analysis hints

• US 20060210173A1
• Filed: 03/18/2005
• Published: 09/21/2006
• Est. Priority Date: 03/18/2005
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Microsoft Corporation
• Inventors: Gear, Gavin M., Wakeam, Jamie N., Bhattacharyay, Subha, Poulose, Sebastian, Sutanto, Herry, Landstad, Todd M., Wang, Haiyong, Kannapel, Timothy H., Turner, Jerome J., Raghupathy, Sashi, Duncan, Richard J., Snytsar, Roman, Jurion, Benoit Jules, Chudzik, Terri, Race, Amber P., Szilagyi, Zoltan C., Schwarz, Lidia
• Granted Patent: US 7,643,687 B2
• Time in Patent Office: Days
• US Class Current: 382/229
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context
• CPC Class Codes: G06V 30/387 using human interaction, e.g. selection of the best displayed recognition candidate

Abstract

A system and method for assisting with analysis and recognition of ink is described. Analysis hints may be associated with a field. The field may receive electronic ink. Based on the identity of the field and the analysis hint associated with it, at least one of analysis and recognition of ink may be assisted.

Claims

1. A system for recognizing ink comprising:

an input device;

a processor receiving ink from said input device relating to a field, said field having an analysis hint associated with said field, said processor recognizing said ink as text based on said analysis hint.

2. The system according to claim 1, wherein said analysis hint is a factoid.

3. The system according to claim 1, wherein said analysis hint is a link to a database.

4. The system according to claim 1, wherein said ink is parsed into a context tree and said ink resides as a node in said context tree.

5. The system according to claim 4, said context tree including an analysis hint context node.

6. The system according to claim 5, said analysis hint context node including a context link that associates said node relating to said ink and said analysis hint context node.

7. The system according to claim 5, wherein said context tree contains at least one paragraph node and one root node.

8. A method for recognizing ink comprising the steps of:

receiving ink, said ink relating to a field;

determining whether said field is related to an analysis hint; and

recognizing said ink based on said analysis hint.

9. The method according to claim 8, further comprising the step of:

storing a recognition result in a context tree.

10. The method according to claim 9, wherein said analysis hint is stored as a node in said context tree.

11. The method according to claim 10, further comprising the step of:

adding a context link between said analysis hint and said recognition result.

12. The method according to claim 8, further comprising the step of:

storing ink in a context tree.

13. The method according to claim 12, wherein said analysis hint is stored as a node in said context tree.

14. The method according to claim 13, further comprising the step of:

adding a context link between said analysis hint and said ink.

20. The system according to claim 12, wherein said analysis hint is stored as a node in said context tree, said system further comprising:

a context link linking said analysis hint and said ink.

15. A system for recognizing ink comprising:

means for receiving ink, said ink relating to a field;

means for determining whether said field is related to an analysis hint; and

means for recognizing said ink based on said analysis hint.

16. The system according to claim 15, further comprising:

means for storing a recognition result in a context tree.

17. The system according to claim 16, wherein said analysis hint is stored as a node in said context tree.

18. The system according to claim 17, further comprising:

context link linking said analysis hint and said recognition result.

19. The system according to claim 15, further comprising:

means for storing a ink in a context tree.

21. A method for analyzing ink comprising the steps of:

receiving input relating to a field;

analyzing said input based on an analysis hint; and

associating said input with one field among other fields.

22. The method according to claim 21, wherein said analysis hint relates to a factoid.

23. The method according to claim 21, wherein said input is stored in a tree.

24. The method according to claim 21, wherein said hint is an expectation of a type of input to be received with respect to said field.

25. The method according to claim 21, wherein, when said receiving step receives a single line of ink extending over two or more fields, said associating step parses said single line of ink into two or more lines of ink.

26. The method according to claim 21, wherein, when said receiving step receives multiple lines of ink in one field, said associating step combines said multiple lines into a single line of ink.

27. The method according to claim 21, wherein said analyzing step determines expected content for said field based on said analysis hint.

28. A system for analyzing ink comprising:

means for receiving input relating to a field;

means for analyzing said input based on an analysis hint; and

means for associating said input with one field among other fields.

29. The system according to claim 28, wherein said analysis hint relates to a factoid.

30. The system according to claim 28, wherein said input is stored in a tree.

31. The system according to claim 28, wherein said hint is an expectation of a type of input to be received with respect to said field.

32. The system according to claim 28, wherein, when said means for receiving receives a single line of ink extending over two or more fields, said means for associating parses said single line of ink into two or more lines of ink.

33. The system according to claim 28, wherein, when said means for receiving receives multiple lines of ink in one field, said means for associating combines said multiple lines into a single line of ink.

34. The system according to claim 28, wherein said means for analyzing determines expected content for said field based on said analysis hint.