Fuzzy keyboard

• US 6,654,733 B1
• Filed: 01/18/2000
• Issued: 11/25/2003
• Est. Priority Date: 01/18/2000
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Huang, Xuedong, Venolia, Daniel, Goodman, Joshua
• Primary Examiner(s): Gordon, Paul P.
• Assistant Examiner(s): Hirl, Joseph P.
• Application Number:
  US09/484,095
• Time in Patent Office: 1,407 Days
• Field of Search: 706/52, 706/11, 706/46
• US Class Current: 706/52
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus

Abstract

Fuzzy keyboards, to determine a most-likely-to-be-intended keystroke or keystrokes, are disclosed. In one embodiment, a method adds each of one or more keys to each of a current list of key sequence hypotheses, to create a new list of key sequence hypotheses. The method determines a likelihood probability for each hypothesis in the new list, and removes any hypothesis failing to satisfy any of one or more thresholds. The most likely key sequence of the new list may then be displayed. Some embodiments of the invention relate specifically to soft keyboards, while other embodiments relate specifically to real, physical and hard keyboards.

Claims

1. A computer-implemented method comprising:

upon a key press event, adding each of at least one key to each of a current list of key sequence hypotheses to create a new list of key sequence hypotheses;

determining a likelihood probability for each of the new list of key sequence hypotheses;

removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold; and

,

displaying a most likely key sequence hypothesis of the new list.

2. The method of claim 1, further comprising:

setting the new list of key sequence hypotheses as the current list of key sequence hypotheses; and

,

repeating the method.

3. The method of claim 1, wherein determining a likelihood probability for each of the new list comprises utilizing a statistical model.

4. The method of claim 3, wherein utilizing a statistical model comprises utilizing one of a statistical character model and a statistical word model.

5. The method of claim 1, wherein determining a likelihood probability for each of the new list comprises determining the likelihood probability for each of the new list based on at least a location of a key press of the key press event on a soft keyboard.

6. The method of claim 5, wherein determining the likelihood probability for each of the new list is further based on at least a typing speed of a user.

7. The method of claim 5, wherein determining the likelihood probability for each of the new list is further based on at least a context of the key sequence hypothesis.

8. The method of claim 5, wherein determining the likelihood probability for each of the new list is further based on at least timing keypress information and a context of the key sequence hypothesis.

9. The method of claim 1, wherein determining a likelihood probability for each of the new list comprises determining the likelihood probability for each of the new list based on at least a key press of the key press event on a physical keyboard.

10. The method of claim 9, wherein determining the likelihood probability for each of the new list is further based on at least timing keypress information of a user.

11. The method of claim 9, wherein determining the likelihood probability for each of the new list is further based on at least a context of the key sequence hypothesis.

12. The method of claim 9, wherein determining the likelihood probability for each of the new list is further based on at least the timing information of the key presses of a user and a context of the key sequence hypothesis.

13. The method of claim 1, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having a likelihood probability less than a predetermined cut-off threshold.

14. The method of claim 13, wherein the predetermined cut-off threshold comprises a predetermined percentage of the likelihood probability of the most likely key sequence hypothesis.

15. The method of claim 1, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having keys more than a predetermined number of keys back from a most recent key that differ from corresponding keys of the most likely key sequence hypothesis.

16. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:

upon an actuation of a location within a soft keyboard, adding each of at least one key to each of a current list of key sequence hypotheses to create a new list of key sequence hypotheses;

determining a likelihood probability for each of the new list of key sequence hypotheses based on at least the location within the soft keyboard of the actuation;

removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold;

setting the new list of key sequence hypotheses as the current list of key sequence hypotheses; and

,

repeating the method.

17. The medium of claim 16, wherein the method further comprises prior to setting the new list of key sequence hypothesis as the current list of key sequence hypotheses, displaying a most likely key sequence hypothesis of the new list.

18. The medium of claim 16, wherein determining a likelihood probability for each of the new list of key sequence hypotheses is also based on at least one of:

timing keypress information, and a context of the key sequence hypothesis.

19. The medium of claim 16, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having a likelihood probability less than a predetermined cut-off threshold.

20. The medium of claim 16, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having keys more than a predetermined number of keys back from a most recent key that differ from corresponding keys of the most likely key sequence hypothesis.

21. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:

upon an actuation of a key of a keyboard, adding each of at least one key to each of a current list of key sequence hypotheses to create a new list of key sequence hypotheses;

determining a likelihood probability for each of the new list of key sequence hypotheses based on at least the key of the keyboard of the actuation and a context of the key sequence hypothesis;

removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold;

setting the new list of key sequence hypotheses as the current list of key sequence hypotheses; and

,

repeating the method.

22. The medium of claim 21, wherein the method further comprises prior to setting the new list of key sequence hypothesis as the current list of key sequence hypotheses, displaying a most likely key sequence hypothesis of the new list.

23. The medium of claim 21, wherein determining a likelihood probability for each of the new list of key sequence hypotheses is also based on at least timing keypress information of a user.

24. The medium of claim 21, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having a likelihood probability less than a predetermined cut-off threshold.

25. The medium of claim 21, wherein removing from the new list any key sequence hypothesis failing to satisfy any of at least one threshold comprises removing any key sequence hypothesis having keys more than a predetermined number of keys back from a most recent key that differ from corresponding keys of the most likely key sequence hypothesis.

26. A computerized system comprising:

a touch-sensitive display;

a soft keyboard rendered on the display and having a plurality of keys; and

,

a computer program to detect actuation of a location on the soft keyboard and to determine a most likely intended-to-be-typed key of the soft keyboard based on at least the location on the soft keyboard of the actuation.

27. The system of claim 26, wherein the computer program is to determine the most likely intended-to-be-typed key of the soft keyboard also based on at least one of:

timing keypress information of a user;

a key sequence of keys already determined to have been typed; and

, a list of key sequence hypotheses.

28. The system of claim 26, wherein the soft keyboard is rendered on the display such that boundaries between adjacent keys are fuzzy.

29. The system of claim 26, further comprising:

a processor; and

,

a machine-readable medium,

wherein the computer program is executed by the processor from the machine-readable medium.

30. A machine-readable medium having instructions stored thereon to transform a general-purpose computerized device to a specialized-purpose computerized device comprising:

a soft keyboard; and

,

means for detecting actuation of a location on the soft keyboard and for determining a most likely intended-to-be-typed key of the soft keyboard based on at least the location on the soft keyboard of the actuation.

31. The medium of claim 30, wherein the most likely intended-to-be-typed key of the soft keyboard is also based on at least one of:

a typing speed of a user;

a key sequence of keys already determined to have been typed; and

, a list of key sequence hypotheses.

32. A computerized system comprising:

a keyboard having a plurality of keys; and

,

a computer program to detect actuation of a key on the keyboard and to determine a most likely intended-to-be-typed key of the keyboard based on at least the key of the keyboard of the actuation and at least one of a key sequence of keys already determined to have been typed and a list of key sequence hypotheses.

33. The system of claim 32, wherein the computer program is to determine the most likely intended-to-be-typed key of the keyboard also based on at least a typing speed of a user.

34. The system of claim 32, further comprising:

a processor; and

,

a machine-readable medium,

wherein the computer program is executed by the processor from the machine-readable medium.

35. A machine-readable medium having instructions stored thereon to transform a general-purpose computerized device to a specialized-purpose computerized device comprising:

a keyboard having a plurality of keys; and

,

means for detecting actuation of a key on the keyboard and for determining a most likely intended-to-be-typed key of the keyboard based on at least key of the keyboard of the actuation and at least one of a key sequence of keys already determined to have been typed and a list of key sequence hypotheses.

36. The medium of claim 35, wherein the most likely intended-to-be-typed key of the soft keyboard is also based on at least a typing speed of a user.