System and method for inputting text into electronic devices

• US 10,445,424 B2
• Filed: 08/06/2014
• Issued: 10/15/2019
• Est. Priority Date: 03/30/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Touchtype Limited (Microsoft Corporation)
• Inventors: Medlock, Benjamin William, Reynolds, Jonathan Paul
• Primary Examiner(s): Repsher, III, John T
• Application Number:
  US14/452,887
• Publication Number:
  US 20140350920A1
• Time in Patent Office: 1,896 Days
• Field of Search: 715816
• CPC Class Codes: G06F 3/023 Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04817 using icons graphical or visual programming using iconic symbols G06F8/34
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• 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

Abstract

The present invention provides a system comprising a user interface configured to receive text input by a user, a text prediction engine comprising a plurality of language models and configured to receive the input text from the user interface and to generate concurrently text predictions using the plurality of language models, and wherein the text prediction engine is further configured to provide text predictions to the user interface for display and user selection. An analogous method and an interface for use with the system and method are also provided.

Claims

1. A non-transitory computer-readable medium containing program instructions for providing a user interface, wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to output for display:

a single or multi-character entry mechanism; and

a word prediction pane;

wherein the word prediction pane is configured to concurrently display currently entered user text input and a plurality of selectable word predictions as the user text input is received by the entry mechanism;

wherein the word prediction pane is configured such that the most likely word prediction of the plurality of selectable word predictions is always displayed in a center of the word prediction pane and display areas on either side of the center are configured to display currently entered user text input and a second most likely word prediction, wherein the most likely word prediction and the second most likely word prediction are a first most probable and a second most probable prediction of a set of overall most probable predictions respectively;

wherein the word prediction pane is part of a touchscreen interface, the user interface being configured such that in response to receiving a touch selection of the currently entered user text input or one selectable word prediction among the plurality of selectable word predictions, the currently entered user text input or the one selectable word prediction is selected and displayed in a typing pane for displaying the user text input; and

wherein, in response to receiving an undo interaction on the touchscreen interface, the word prediction pane is configured to display a prediction comprising at least one of the most likely word prediction in the center of the word prediction pane with the currently entered user text input and the second most likely word prediction displayed on the display areas on either side of the center.

2. The non-transitory computer-readable medium of claim 1, wherein the word prediction pane comprises a fixed number of display areas, each of which displays one of the plurality of selectable word predictions.

3. The non-transitory computer-readable medium of claim 2, wherein the fixed number of display areas are arranged in a row, with the most likely text prediction of the plurality of selectable word predictions being displayed in a central display area.

4. The non-transitory computer-readable medium of claim 2, wherein there are three display areas, each having a fixed size and a fixed location.

5. The non-transitory computer-readable medium of claim 4, wherein the three display areas are arranged in a horizontal row, with a central display area being configured to display the most likely word prediction, and display areas on either side of the central display area being configured to display a sequence of entered characters and a second most likely word prediction, respectively.

6. The non-transitory computer-readable medium of claim 2, wherein the plurality of selectable word predictions comprise at least one phrase prediction.

7. The non-transitory computer-readable medium of claim 1, further comprising a typing pane for displaying user text input.

8. The non-transitory computer-readable medium of claim 7, wherein the user text input includes a current input sequence, and wherein one of the plurality of selectable word predictions corresponds to the current input sequence.

9. The non-transitory computer-readable medium of claim 1, wherein the word prediction pane comprises a plurality of keys, each key displaying a selectable word prediction from among the plurality of selectable word predictions, wherein a number of keys displayed in the word prediction pane is fixed and a size of each key is independent of a length of a selectable word prediction being displayed.

10. A non-transitory computer-readable medium containing program instructions for providing a user interface, wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to output for display:

a single or multi-character entry mechanism; and

a word prediction pane;

wherein the word prediction pane is configured to display only three keys for displaying selectable text, wherein each key displayed has a size and a location that are independent of a length of a selectable text prediction being displayed;

wherein the word prediction pane is configured to always display a most likely text prediction in a center key of the word prediction pane and keys on either side of the center key are configured to display currently entered user text input and a second most likely text prediction, wherein the most likely text prediction and the second most likely text prediction are a first most probable and a second most probable prediction of a set of overall most probable predictions respectively; and

wherein the word prediction pane is part of a touchscreen interface, the user interface being configured such that in response to receiving a touch selection of a key from among the three keys, the text associated with the selected key is selected and displayed in a typing pane of the touchscreen interface; and

wherein, in response to receiving an undo interaction on the touchscreen interface, the word prediction pane is configured to display a prediction comprising at least one of the most likely word prediction in the center key of the word prediction pane with the currently entered user text input and the second most likely word prediction displayed on the display areas on either side of the center.

11. The non-transitory computer-readable medium of claim 10, wherein the text predictions comprise a phrase prediction.

12. The non-transitory computer-readable medium of claim 11, wherein a key displaying the phrase prediction is configured to display the phrase prediction so each word of the phrase prediction is independently selectable.

13. The non-transitory computer-readable medium of claim 10, wherein the location and the size associated with each key are fixed.

14. The non-transitory computer-readable medium of claim 13, wherein the three keys are arranged in a horizontal row, with a central key being configured to display the most likely text prediction, and keys on either side of the central key being configured to display a sequence of entered characters and a second most likely text prediction, respectively.

15. The non-transitory computer-readable medium of claim 10, further comprising a typing pane for displaying user text input.

16. A non-transitory computer-readable medium containing program instructions for providing a user interface, wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to output for display:

a single or multi-character entry mechanism; and

a word prediction pane;

wherein the word prediction pane is configured to concurrently display currently entered user text input and a plurality of selectable text predictions as the user text input is received by the entry mechanism;

wherein at least one of the plurality of selectable text predictions corresponds to a phrase prediction;

wherein the word prediction pane is configured to display the phrase prediction with parts of the phrase prediction being independently selectable, such that upon selection of an end word of the phrase, the user interface is configured to select for input the selected end word and any word or words of the phrase prediction preceding the selected end word;

wherein upon selection of a single word of the phrase prediction that is not the end word, the single word having one or more words of the phrase prediction preceding the single word and without selection of one or more words of the phrase prediction preceding the selected word, the user interface is configured to select for input the selected word and the one or more words of the phrase prediction preceding the selected word, excluding any word or words of the phrase coming after the selected word;

wherein the user interface is configured to display the selected word and the one or more words of the phrase prediction preceding the selected word; and

wherein, in response to receiving an undo interaction on the user interface, the word prediction pane is configured to display a prediction comprising at least one of the independently selectable parts of the phrase prediction.

17. The non-transitory computer-readable medium of claim 16, wherein the word prediction pane is configured to always display a most likely selectable text prediction from among the plurality of selectable text predictions in a center of the word prediction pane.

18. The non-transitory computer-readable medium of claim 16, wherein display areas available for each selectable text prediction among the plurality of selectable text predictions remain unchanged regardless of a length of the selectable text prediction being displayed.

19. The non-transitory computer-readable medium of claim 18, wherein display areas for displaying the plurality of selectable text predictions have a fixed size and a fixed location on the word prediction pane.

20. The non-transitory computer-readable medium of claim 19, wherein there are three display areas for displaying three selectable text predictions.

21. The non-transitory computer-readable medium of claim 20, wherein the three display areas are arranged in a horizontal row, with a central display area being configured to display a most likely text prediction, and areas on either side of the central area being configured to display a sequence of entered characters and a second most likely text prediction, respectively.

22. The non-transitory computer-readable medium of claim 16, further comprising a typing pane for displaying user text input.

23. The non-transitory computer-readable medium of claim 22, wherein user text input includes a current input sequence, and wherein one selectable text prediction among the plurality of selectable text predictions corresponds to the current input sequence.

24. The non-transitory computer-readable medium of claim 23, wherein the word prediction pane is part of a touchscreen interface, the user interface being configured such that:

in response to receiving a touch selection of one selectable text prediction from among the plurality of selectable text predictions, the selectable text prediction is displayed in the typing pane.

25. The non-transitory computer-readable medium of claim 16, wherein the word prediction pane is configured to display a selectable text prediction on a key, a size of the key corresponding to a display area for displaying the selectable text prediction, wherein a number of keys displayed in the word prediction pane is fixed and a size of each key is independent of a length of a selectable text prediction being displayed.