Text suggestion output using past interaction data

• US 9,684,446 B2
• Filed: 08/28/2014
• Issued: 06/20/2017
• 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): Han, Qi
• Application Number:
  US14/471,610
• Publication Number:
  US 20140372931A1
• Time in Patent Office: 1,027 Days
• Field of Search: 704 9, 704 10, 704 1, 704 3, 704 4, 704 7
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• 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
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates

Abstract

In one example, a device includes at least one processor and at least one module operable by the at least one processor to output, for display, a graphical user interface including a graphical keyboard and one or more text suggestion regions, and select, based at least in part on an indication of gesture input, at least one key of the graphical keyboard. The at least one module is further operable by the at least one processor to determine a plurality of candidate character strings, determine past interaction data that comprises a representation of a past user input corresponding to at least one candidate character string while the at least one candidate character string was previously displayed in at least one of the one or more text suggestion regions, and output the at least one candidate character string for display in one of the one or more text suggestion regions.

Claims

1. A method comprising:

outputting, by a computing device and for display, a graphical user interface including a graphical keyboard and one or more text suggestion regions, wherein at least one character string is displayed within the one or more text suggestion regions, the at least one character string being associated with a probability;

receiving, by the computing device, an indication of an initial gesture input detected at a presence-sensitive input device operatively coupled to the computing device;

maintaining, by the computing device, based on the initial gesture input, past user interaction data to reflect a past decision corresponding to the at least one candidate character string while the at least one candidate character string was previously displayed within the one or more text suggestion regions;

receiving, by the computing device, an indication of a subsequent gesture input detected at the presence-sensitive input device operatively coupled to the computing device;

determining, by the computing device and based at least in part on the indication of the subsequent gesture input, the at least one candidate character string;

determining, by the computing device and based at least in part on an association between the at least one candidate character string and a context of the subsequent gesture input, a lexical probability for the at least one candidate character string, the lexical probability indicating a probability that the at least one candidate character string represents a word included in a lexicon;

modifying, based at least in part on the past interaction data, the lexical probability;

and

outputting, by the computing device, for display, based on the lexical probability that was modified based at least in part on the past interaction data, the at least one candidate character string.

2. The method of claim 1, wherein the past interaction data indicates whether:

the past decision was to select the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

3. The method of claim 1, further comprising:

determining, by the computing device and based at least in part on the past interaction data, at least one lexical probability weighting factor associated with the at least one candidate character string;

applying, by the computing device, the at least one lexical probability weighting factor to the lexical probability of the at least one candidate character string to determine a weighted lexical probability associated with the at least one candidate character string; and

modifying, by the computing device and based at least in part on the weighted lexical probability associated with the at least one candidate character string, the lexical probability.

4. The method of claim 1, wherein maintaining the past user interaction data comprises:

responsive to determining that the initial gesture input selects the at least one candidate character string while the at least one candidate character string is displayed within the one or more text suggestion regions, maintaining, by the computing device, the past interaction data to reflect that the past decision was to select the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

5. The method of claim 1, wherein maintaining the past user interaction data comprises:

responsive to determining that the initial gesture input selects a key of the graphical keyboard while the at least one candidate character string is displayed within the one or more text suggestion regions, maintaining, by the computing device, the past interaction data to reflect that the past decision was to ignore the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

6. The method of claim 1, wherein maintaining the past user interaction data comprises:

responsive to determining that the initial gesture input selects a different character string within the one or more text suggestion regions while the at least one candidate character string is displayed within the one or more text suggestion regions, maintaining, by the computing device, the past interaction data to reflect that the a past decision was to reject the at least one candidate character string while the at least one candidate character string was displayed in the one or more text suggestion regions.

7. The method of claim 1, wherein the past interaction data indicates whether the past decision was to ignore the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

8. The method of claim 1, wherein the past interaction data indicates whether the past decision was to reject the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

9. A computing device comprising:

at least one processor; and

at least one module operable by the at least one processor to;

output, for display, a graphical user interface including a graphical keyboard and one or more text suggestion regions, wherein at least one character string is displayed within the one or more text suggestion regions, the at least one character string being associated with a probability;

receive an indication of an initial gesture input detected at a presence-sensitive input device operatively coupled to the computing device;

maintain, based on the initial gesture input, past user interaction data to reflect a past decision corresponding to the at least one candidate character string while the at least one candidate character string was previously displayed within the one or more text suggestion regions;

receive an indication of a subsequent gesture input detected at the presence-sensitive input device operatively coupled to the computing device;

determine, based at least in part on the indication of the subsequent gesture input, the at least one candidate character string;

determine, based at least in part on an association between the at least one candidate character string and a context of the subsequent gesture input, a lexical probability for the at least one candidate character string, the lexical probability indicating a probability that the at least one candidate character string represents a word included in a lexicon;

modify, based at least in part on the past interaction data, the lexical probability;

output, for display, based on the lexical probability that was modified based at least in part on the past interaction data, the at least one candidate character string.

10. The computing device of claim 9, wherein the past interaction data indicates whether:

the past decision was to select the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions

the past decision was to ignore the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions; and

the past decision was to reject the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions.

11. The computing device of claim 9, wherein the at least one module is operable by the at least one processor to:

determine, based at least in part on the past interaction data, at least one lexical probability weighting factor associated with the at least one candidate character string;

apply the at least one lexical probability weighting factor to the lexical probability of the at least one candidate character string to determine a weighted lexical probability associated with the at least one candidate character string; and

modify, based at least in part on the weighted lexical probability associated with the at least one candidate character string, the lexical probability.

12. The computing device of claim 9, wherein the at least one module is operable by the at least one processor to modify the lexical probability by increasing the lexical probability in response to determining, based on the past user interaction data, that the past decision was to select the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions.

13. The computing device of claim 9, wherein the at least one module is operable by the at least one processor to modify the lexical probability by decreasing the lexical probability in response to determining, based on the past user interaction data, that the past decision was to ignore the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions.

14. The computing device of claim 9, wherein the at least one module is operable by the at least one processor to modify the lexical probability by decreasing the lexical probability in response to determining, based on the past user interaction data, that the past decision was to reject the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions.

15. A non-transitory computer-readable storage medium encoded with instructions that, when executed, cause at least one processor of a computing device to:

output, for display, a graphical user interface including a graphical keyboard and one or more text suggestion regions, wherein at least one character string is displayed within the one or more text suggestion regions, the at least one character string being associated with a probability;

receive an indication of an initial gesture input detected at a presence-sensitive input device operatively coupled to the computing device;

maintain, based on the initial gesture input, past user interaction data to reflect a past decision corresponding to the at least one candidate character string while the at least one candidate character string was previously displayed within the one or more text suggestion regions;

receive an indication of a subsequent gesture input detected at the presence-sensitive input device operatively coupled to the computing device;

determine, based at least in part on the indication of the subsequent gesture input, at least one candidate character string;

determine, based at least in part on an association between the at least one candidate character string and a context of the subsequent gesture input, a lexical probability for the at least one candidate character string, the lexical probability indicating a probability that the at least one candidate character string represents a word included in a lexicon;

modify, based at least in part on past interaction data, the lexical probability;

and

output, for display, based on the lexical probability that was modified based at least in part on the past interaction data, the at least one candidate character string.

16. The non-transitory computer-readable storage medium of claim 15, wherein the past interaction data indicates whether the past decision was to ignore the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

17. The non-transitory computer-readable storage medium of claim 15, wherein the past interaction data indicates whether the past decision was to reject the at least one candidate character string while the at least one candidate character string was displayed within the one or more text suggestion regions.

18. The non-transitory computer-readable storage medium of claim 15, wherein the at least one module is operable by the at least one processor to modify the lexical probability by increasing the lexical probability in response to determining, based on the past user interaction data, that the past decision was to select the at least one candidate character string while the at least one candidate character string was displayed at the one or more text suggestion regions.