Consistent text suggestion output

• US 9,665,246 B2
• Filed: 12/31/2013
• Issued: 05/30/2017
• Est. Priority Date: 04/16/2013
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhai, Shumin, Quinn, Philip
• Primary Examiner(s): Tran, Tam
• Application Number:
  US14/144,991
• Publication Number:
  US 20140310639A1
• Time in Patent Office: 1,246 Days
• Field of Search: 715773, 715780
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• 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 40/237 Lexical tools
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

In one example, a method includes outputting, by a computing device and for display, a graphical user interface including a plurality of text suggestion regions. The method further includes receiving, by the computing device, an indication of gesture input detected at a presence-sensitive input device, and selecting, based at least in part on the indication of the gesture input, a candidate character string from a plurality of candidate character strings. The method further includes determining that the candidate character string was previously selected while being displayed within a particular text suggestion region from the plurality of text suggestion regions, and outputting, for display and based at least in part on determining that the candidate character string was previously selected while being displayed within the particular text suggestion region, the candidate character string within the particular text suggestion region.

Claims

1. A method comprising:

determining, by a computing device, based on a first input at a graphical keyboard, a plurality of candidate strings and an initial ranked ordering of the plurality of candidate character strings, wherein a first candidate character string from the plurality of candidate character strings is associated with a highest rank of the initial ranked ordering of the plurality of candidate character strings and a second candidate character string from the plurality of candidate character strings is associated with a second-highest rank of the initial ranked ordering of the plurality of candidate character strings;

outputting, by the computing device and for display, based on the initial ranked ordering of the plurality of candidate character strings, the first candidate character string in a first text suggestion region from a plurality of text suggestion regions and the second candidate character string in a second text suggestion region from the plurality of text suggestion regions, the first text suggestion region being associated with a highest rank of a ranked ordering of the plurality of text suggestion regions and the second text suggestion region being associated with a second-highest rank of the ranked ordering of the plurality of text suggestion regions;

receiving, by the computing device, a second input that selects the first candidate character string from the first text suggestion region;

determining, by the computing device, based on a third input at the graphical keyboard, the plurality of candidate strings and a subsequent ranked ordering of the plurality of candidate character strings, the first candidate character string being associated with a second-highest rank of the subsequent ranked ordering of the plurality of candidate character strings and the second candidate character string being associated with a highest rank of the subsequent ranked ordering of the plurality of candidate character strings;

associating, by the computing device, based on the subsequent ranked ordering of the plurality of candidate character strings, the first candidate character string with the second text suggestion region; and

responsive to determining that the first candidate character string was previously selected from the first text suggestion region when the first candidate character string was previously displayed, outputting, by the computing device for display, the first candidate character string in the first text suggestion region.

2. The method of claim 1, wherein determining the initial ranked ordering of the plurality of candidate character strings further comprises comparing, by the computing device, each respective candidate character string from the plurality of candidate character strings with a language model to determine a probability that the respective candidate character string represents a word included in a lexicon.

3. The method of claim 2 wherein the language model comprises an n-gram language model.

4. The method of claim 1, further comprising:

determining, by the computing device, that a context of the third input matches a context associated with the first candidate character string, wherein outputting the first candidate character string for display in the first text suggestion region further comprises outputting, based at least in part on the determining that the context of the third input matches the context associated with the first candidate character string, the first candidate character string for display within the first text suggestion region.

5. The method of claim 1, wherein receiving the second input comprises:

receiving, by the computing device, an indication of a touch input detected at a presence-sensitive input device to select the first text suggestion region.

6. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause at least one processor to:

determine, based on a first input at a graphical keyboard, a plurality of candidate strings and an initial ranked ordering of the plurality of candidate character strings, wherein a first candidate character string from the plurality of candidate character strings is associated with a highest rank of the initial ranked ordering of the plurality of candidate character strings and a second candidate character string from the plurality of candidate character strings is associated with a second-highest rank of the initial ranked ordering of the plurality of candidate character strings;

output, for display, based on the initial ranked ordering of the plurality of candidate character strings, the first candidate character string in a first text suggestion region from a plurality of text suggestion regions and the second candidate character string in a second text suggestion region from the plurality of text suggestion regions, the first text suggestion region being associated with a highest rank of a ranked ordering of the plurality of text suggestion regions and the second text suggestion region being associated with a second-highest rank of the ranked ordering of the plurality of text suggestion regions;

receive a second input that selects the first candidate character string from the first text suggestion region;

determine, based on a third input at the graphical keyboard, the plurality of candidate strings and a subsequent ranked ordering of the plurality of candidate character strings, the first candidate character string being associated with a second-highest rank of the subsequent ranked ordering of the plurality of candidate character strings and the second candidate character string being associated with a highest rank of the subsequent ranked ordering of the plurality of candidate character strings;

associate, based on the subsequent ranked ordering of the plurality of candidate character strings, the first candidate character string with the second text suggestion region; and

responsive to determining that the first candidate character string was previously selected from the first text suggestion region when the first candidate character string was previously displayed, output, for display, the first candidate character string in the first text suggestion region.

7. The non-transitory computer-readable storage medium of claim 6, wherein the instructions, when executed, cause the at least one processor to determine the initial ranked ordering of the plurality of candidate character strings by comparing, by the computing device, each respective candidate character string from the plurality of candidate character strings with a language model to determine a probability that the respective candidate character string represents a word included in a lexicon.

8. The non-transitory computer-readable storage medium of claim 6, wherein the instructions, when executed, cause the at least one processor to output the first candidate character string for display in the first text suggestion region based at least in part on determining that a context of the third input matches a context associated with the first candidate character string.

9. The non-transitory computer-readable storage medium of claim 6, wherein the instructions, when executed, cause the at least one processor to receive the third input by receiving an indication of a touch input detected at a presence-sensitive input device to select the first text suggestion region.

10. A computing device of comprising:

at least one processor; and

a memory comprising instructions that, when executed, cause the at least one processor to;

determine, based on a first input at a graphical keyboard, a first plurality of candidate strings and an initial ranked ordering of the first plurality of candidate character strings, wherein a particular candidate character string from the first plurality of candidate character strings is associated with a highest rank of the initial ranked ordering of the first plurality of candidate character strings;

output, for display, based on the initial ranked ordering of the first plurality of candidate character strings, the particular candidate character string in a first text suggestion region from a plurality of text suggestion regions, the first text suggestion region being associated with a highest rank of a ranked ordering of the plurality of text suggestion regions and the second text suggestion region being associated with a second-highest rank of the ranked ordering of the plurality of text suggestion regions;

receive a second input that selects the particular candidate character string from the first text suggestion region;

determine, based on a third input at the graphical keyboard, a second plurality of candidate strings and a subsequent ranked ordering of the second plurality of candidate character strings, the second plurality of candidate character strings including the particular candidate character string, the particular candidate character string being associated with a second-highest rank of the subsequent ranked ordering of the second plurality of candidate character strings;

associate, based on the subsequent ranked ordering of the second plurality of candidate character strings, the particular candidate character string with the second text suggestion region; and

responsive to determining that the particular candidate character string was previously selected from the first text suggestion region when the particular candidate character string was previously displayed, output, for display, the particular candidate character string in the first text suggestion region.

11. The computing device of claim 10, wherein the instructions, when executed, further cause the at least one processor to determine the initial ranked ordering of the first plurality of candidate character strings by comparing, by the computing device, each respective candidate character string from the first plurality of candidate character strings with a language model to determine a probability that the respective candidate character string represents a word included in a lexicon.

12. The computing device of claim 10, wherein the instructions, when executed, further cause the at least one processor to output the particular candidate character string for display in the first text suggestion region based at least in part on determining that a context of the third input matches a context associated with the particular candidate character string.

13. The computing device of claim 10, wherein the instructions, when executed, further cause the at least one processor to receive the third input by receiving an indication of a touch input detected at a presence-sensitive input device to select the first text suggestion region.