In-context word prediction and word correction

• US 9,223,497 B2
• Filed: 03/16/2012
• Issued: 12/29/2015
• Est. Priority Date: 03/16/2012
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Pasquero, Jerome, McKenzie, Donald Somerset, Griffin, Jason Tyler
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Wu, Fuming
• Application Number:
  US13/422,197
• Publication Number:
  US 20130246329A1
• Time in Patent Office: 1,383 Days
• Field of Search: None
• US Class Current: 1/1
• 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
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Methods and systems for predicting user input on a keyboard. Methods include enabling user input on a display comprising at least three fields. The first field displays an input string that is based on input selections such as keyboard entries. The second field displays a candidate prediction generated based on other input selections, consisting at least in part of a proposed completion to the input selection, and partially based on the input string in the first field. The third field displays another candidate prediction generated based on the input string in the first field as well as the candidate prediction in the second field.

Claims

1. A method for accepting text input on an electronic device, comprising:

displaying a first input string based on an input selection in a first field,

displaying a first candidate prediction formed by (1) a set of characters corresponding to input selections and (2) a proposed completion to follow the set of characters in a second field, wherein the proposed completion is generated by a predictive algorithm using at least one of the first input string or the set of characters corresponding to input selections,

subsequent to the first candidate prediction, generating a second candidate prediction using a predictive algorithm that predicts subsequent candidates based on the first candidate prediction, and

displaying the second candidate prediction in a third field.

2. The method of claim 1, further comprising:

generating, by the predictive algorithm, multiple first and second candidate predictions; and

ranking the multiple first and second candidate predictions based on a plurality of ranking criteria;

wherein displaying the first candidate prediction and second candidate prediction is based at least in part on the plurality of ranking criteria.

3. The method of claim 1, further comprising:

receiving input selecting one of the first candidate prediction or the second candidate prediction.

4. The method of claim 3, further comprising:

responsive to input selecting the first candidate prediction,

displaying the first candidate prediction in the first field,

displaying the second candidate prediction in the second field, and

generating, by the predictive algorithm, multiple candidate predictions for the third field; and

responsive to input selecting the second candidate prediction,

displaying the second candidate prediction in the first field,

generating, by the predictive algorithm, multiple candidate predictions for each of the second and third fields.

5. The method of claim 3, wherein the input selecting one of the first candidate prediction or the second candidate prediction comprises one of a tap on the accepted prediction, a swipe across the accepted prediction, or the input of a punctuation key.

6. The method of claim 5, further comprising:

responsive to input selecting the first candidate prediction, performing a spell-check on the first candidate prediction; and

if the spell-check determines that the first candidate prediction is misspelled,

displaying alternate predictions for the first candidate prediction, and

receiving input selecting an alternate prediction in place of the first candidate prediction.

7. The method of claim 1, further comprising:

displaying additional predictions for a prediction or an input string in an area vertically aligned with the prediction or input string, respectively.

8. The method of claim 1, wherein:

the set of fields comprises a horizontal bar; and

the first, second, and third fields respectfully comprise left, center, and, right segments of the horizontal bar.

9. An electronic device comprising:

a display, and

a processor configured to;

display a first input string based on an input selection in a first field,

display a first candidate prediction formed by (1) a set of characters corresponding to input selections and (2) a proposed completion to follow the set of characters in a second field, wherein the proposed completion is generated by a predictive algorithm using at least one of the first input string or the set of characters corresponding to input selections,

subsequent to the first candidate prediction, generat a second candidate prediction using a predictive algorithm that predicts subsequent candidates based on the first candidate prediction, and

display the second candidate prediction in a third field.

10. The device of claim 9, wherein the processor is further configured to:

generate, by the predictive algorithm, multiple first and second candidate predictions;

rank the multiple first and second candidate predictions based on a plurality of ranking criteria; and

display the first candidate prediction and second candidate prediction based at least in part on the plurality of ranking criteria.

11. The device of claim 9, wherein processor is further configured to receive input selecting one of the first candidate prediction or the second candidate prediction.

12. The device of claim 11, wherein the processor is further configured to:

responsive to input selecting the first candidate prediction,

display the first candidate prediction in the first field,

display the second candidate prediction in the second field, and

generate, by the predictive algorithm, multiple candidate predictions for the third field; and

responsive to input selecting the second candidate prediction,

display the second candidate prediction in the first field,

generate, by the predictive algorithm, multiple candidate predictions for each of the second and third fields.

13. The device of claim 11, wherein the input selecting one of the first candidate prediction or the second candidate prediction comprises one of a tap on the accepted prediction, a swipe across the accepted prediction, or the input of a punctuation key.

14. The device of claim 13, wherein the processor is further configured to:

responsive to input selecting the first candidate prediction, perform a spell-check on the first candidate prediction; and

if the spell-check determines that the first candidate prediction is misspelled,

display alternate predictions for the first candidate prediction, and

receive input selecting an alternate prediction in place of the first candidate prediction.

15. The device of claim 9, wherein the processor is further configured to:

display additional predictions for a prediction or an input string in an area vertically aligned with the prediction or input string, respectively.

16. The device of claim 9, wherein

the set of fields comprises a horizontal bar;

and

the first, second, and third fields respectfully comprise left, center, and, right segments of the horizontal bar.

17. A method for accepting text input on an electronic device, comprising:

displaying a preliminary input area on a display, the preliminary input area comprising first, second, and third regions;

displaying a text box on the display;

receiving character entries via a keyboard;

displaying the character entries in the first region and the text box;

generating candidate predictions for a first text unit based on the character entries;

ranking the candidate predictions for the first text unit, based on a first plurality of criteria;

displaying, in the first region, one of the candidate predictions of the first text unit as an initial prediction of the first text unit, based on the rankings of the candidate predictions for the first text unit;

generating first predictions for the second text unit based on the candidate predictions for the first text unit, wherein first predictions for the second text unit are generated by a predictive algorithm that predicts subsequent text units based on preceding text units;

ranking the first predictions for the second text unit based on a second plurality of criteria;

displaying, in the second region, one of the first predictions of the second text unit, based on the rankings of the first predictions for the second text unit;

receiving user input to accept the initial prediction of the first text unit displayed in the first region;

displaying the accepted initial prediction in the third region;

displaying, in the first region, the prediction displayed in the second region, as the current prediction of the first text unit;

generating second predictions for the second text unit based on the current prediction of the first text unit;

ranking the second predictions for the second text unit based on a third plurality of criteria;

displaying, in the second region, one of the second predictions of the second text unit, based on the rankings of the second predictions for the second text unit; and

displaying the accepted initial prediction in the text box.

18. The method of claim 17, wherein the candidate predictions for the first text unit are based on the character entries and candidate predictions that have been previously accepted.

19. The method of claim 17, further comprising:

displaying additional candidate predictions for the first text unit in an area vertically aligned with the displayed one of the candidate predictions for the first text unit.

20. The method of claim 17, wherein the user input to accept the initial prediction of the first text unit displayed in the first region comprises one of a tap on the initial prediction, a swipe across the initial prediction, or a punctuation key being pressed.

21. The method of claim 20, further comprising:

upon receiving the user input to accept the initial prediction of the first text unit displayed in the first region, performing a spell-check on the initial prediction; and

if the spell-check determines that the initial prediction of the first text unit displayed in the first region is misspelled;

displaying alternate predictions for the initial prediction of the first text unit displayed in the first region; and

receiving user input to accept an alternate prediction of the first text unit displayed in the first region.

22. The method of claim 17, wherein:

the remaining input area comprises a horizontal bar; and

the first, second, and third regions respectfully comprise center, right, and left segments of the horizontal bar.

23. An electronic device comprising:

a display, and

a processor configured to;

display a preliminary input area on the display, the preliminary input area comprising first, second, and third regions;

display a text box on the display;

receive character entries via a keyboard;

display the character entries in the first region and the text box;

generate candidate predictions for a first text unit based on the character entries;

rank the candidate predictions for the first text unit, based on a first plurality of criteria;

display, in the first region, one of the candidate predictions of the first text unit as an initial prediction of the first text unit, based on the rankings of the candidate predictions for the first text unit;

generate first predictions for the second text unit based on the candidate predictions for the first text unit, wherein first predictions for the second text unit are generated by a predictive algorithm that predicts subsequent text units based on preceding text units;

rank the first predictions for the second text unit based on a second plurality of criteria;

display, in the second region, one of the first predictions of the second text unit, based on the rankings of the first predictions for the second text unit;

receive user input to accept the initial prediction of the first text unit displayed in the first region;

display the accepted initial prediction in the third region;

display, in the first region, the prediction displayed in the second region, as the current prediction of the first text unit;

generate second predictions for the second text unit based on the current prediction of the first text unit;

rank the second predictions for the second text unit based on a third plurality of criteria;

display, in the second region, one of the second predictions of the second text unit, based on the rankings of the second predictions for the second text unit; and

display the accepted initial prediction in the text box.

24. The device of claim 23, wherein the candidate predictions for the first text unit are based on the character entries and candidate predictions that have been previously accepted.

25. The device of claim 23, wherein the processor is further configured to:

display additional predictions for the first text unit in an area vertically aligned with the displayed one of the candidate predictions for the first text unit.

26. The device of claim 23, wherein the user input to accept the initial prediction of the first text unit displayed in the first region comprises one of a tap on the initial prediction, a swipe across the initial prediction, or a punctuation key being pressed.

27. The device of claim 26, wherein the processor is further configured to:

receive the user input to accept the initial prediction of the first text unit displayed in the first region; and

perform a spell-check on the initial prediction;

if the spell-check determines that the initial prediction of the first text unit displayed in the first region is misspelled;

display alternate predictions for the initial prediction of the first text unit displayed in the first region; and

receive user input to accept an alternate prediction of the first text unit displayed in the first region.

28. The method of claim 23, wherein:

the remaining input area comprises a horizontal bar; and

the first, second, and third regions respectfully comprise center, right, and left segments of the horizontal bar.