Predictive virtual keyboard

• US 9,317,201 B2
• Filed: 07/08/2013
• Issued: 04/19/2016
• Est. Priority Date: 05/23/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhai, Shumin, Diao, Lawrence
• Primary Examiner(s): Sax, Steven
• Assistant Examiner(s): CHOI, DAVID E
• Application Number:
  US13/936,913
• Publication Number:
  US 20130314352A1
• Time in Patent Office: 1,016 Days
• 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

Abstract

In general, aspects of this disclosure are directed to techniques for predictive text correction and completion for text entry using virtual keyboards on touch-sensitive displays. A user may be able to type on a representation of a virtual keyboard displayed on touch-sensitive displays by contacting representations of virtual keys included in the virtual keyboard, and the word the user intended to type on the virtual keyboard may be predicted and displayed in place of characters associated with the virtual keys actually contacted by the user. In some examples of the present disclosure, a virtual spacebar key included in the virtual keyboard may be treated in a probabilistic fashion to determine whether a contact received by the touch-sensitive display is intended to select the virtual spacebar key to perform an autocorrect or autocomplete function.

Claims

1. A computer-implemented method comprising:

receiving, by a computing device, an indication of at least two contacts at a region of a presence-sensitive screen that outputs a virtual keyboard, the at least two contacts constituting a sequence of contacts and being associated with a predicted word and a probability for the predicted word;

receiving, by the computing device, an indication of a third contact at the region of the presence-sensitive screen;

applying, by the computing device, a probabilistic model based on a spatial location of the third contact and the predicted word, wherein the spatial location is based on a distance of the third contact from a location within a virtual spacebar key, the probabilistic model configured to interpret the third contact as at least one of (i) a selection of the predicted word, wherein the predicted word has a same number of characters as a number of contacts in the sequence of contacts, (ii) a selection of the predicted word, wherein the predicted word has a greater number of characters than the number of contacts in the sequence of contacts, and (iii) a user input of a non-space character; and

updating an input buffer based on an interpretation of the third contact, the interpretation being based on the probabilistic model.

2. The method of claim 1, further comprising:

outputting at least a portion of the updated input buffer for display at the presence-sensitive screen.

3. The method of claim 1, wherein the probabilistic model comprises a language model that predicts words based on at least the sequence of contacts and a spatial model that predicts a character for the third contact based on the information about the spatial location of the third contact.

4. The method of claim 3, wherein the probabilistic model estimates a probability of selection of the predicted word having a same number of characters as the number of contacts in the sequence of contacts separately from estimating the probability of selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

5. The method of claim 4, wherein the probabilistic model comprises a first probability threshold for determining selection of the predicted word having the same number of characters as the number of contacts in the sequence of contacts, and a second probability threshold for determining selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

6. The method of claim 5, wherein triggering the first probability threshold is more likely than triggering the second probability threshold.

7. The method of claim 1, wherein the probabilistic model interfaces with a spatial model that determines a probability that an input key is selected based on the spatial location of the third contact.

8. The method of claim 1, wherein the probabilistic model interfaces with a language model that determines a probability that an input key is selected based on previous contacts in the sequence of contacts.

9. The method of claim 1, wherein the sequence of contacts comprises contacts received subsequent to completion of at least one of a prior word and contacts initially received in response to a prompt for input.

10. A non-transitory computer-readable storage device comprising instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

receiving an indication of at least two contacts at a region of a presence-sensitive screen that outputs virtual keyboard, the at least two contacts constituting a sequence of contacts and being associated with a predicted word and a probability for the predicted word;

receiving an indication of a third contact at the region of the presence-sensitive screen;

applying a probabilistic model based on a spatial location of the third contact and the predicted word, wherein the spatial location is based on a distance of the third contact from a location within the virtual spacebar key, the probabilistic model configured to interpret the third contact as at least (i) a selection of the predicted word, wherein the predicted word has a same number of characters as a number of contacts in the sequence of contacts, (ii) a selection of the predicted word, wherein the predicted word has a greater number of characters than the number of contacts in the sequence of contacts, and (iii) a user input of a non-space character; and

updating an input buffer based on an interpretation of the third contact, the interpretation being based on the probabilistic model.

11. The non-transitory computer-readable storage device of claim 10, further comprising:

outputting at least a portion of the updated input buffer for display at the presence-sensitive screen.

12. The non-transitory computer-readable storage device of claim 10, wherein the probabilistic model comprises a language model that predicts words based on at least the sequence of contacts and a spatial model that predicts a character for the additional contact based on the information about the spatial location of the third contact.

13. The computer-readable storage device of claim 12, wherein the probabilistic model estimates a probability of selection of the predicted word having a same number of characters as the number of contacts in the sequence of contacts separately from estimating the probability of selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

14. The non-transitory computer-readable storage device of claim 13, wherein the probabilistic model comprises a first probability threshold for determining selection of the predicted word having the same number of characters as the number of contacts in the sequence of contacts, and a second probability threshold for determining selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

15. The non-transitory computer-readable storage device of claim 14, wherein triggering the first probability threshold is more likely than triggering the second probability threshold.

16. The non-transitory computer-readable storage device of claim 10, wherein the probabilistic model interfaces with a spatial model that determines a probability that an input key is selected based on the spatial location of the third contact.

17. The non-transitory computer-readable storage device of claim 10, wherein the probabilistic model interfaces with a language model that determines a probability that an input key is selected based on previous contacts in the sequence of contacts.

18. The non-transitory computer-readable storage device of claim 10, wherein the sequence of contacts comprises contacts received subsequent to completion of at least one of a prior word and contacts initially received in response to a prompt for input.

19. A computing device comprising:

one or more processors; and

at least one module operable by the one or more processors to;

receive an indication of at least two contacts at a region of a presence-sensitive screen that outputs a virtual keyboard, the at least two contacts constituting a sequence of contacts and being associated with a predicted word and a probability for the predicted word;

receive an indication of a third contact at the region of the presence-sensitive screen;

apply a probabilistic model based on a spatial location of the third contact and the predicted word, wherein the spatial location is based on a distance of the third contact from a location within the virtual spacebar key, the probabilistic model configured to interpret the third contact as at least one of (i) a selection of the predicted word, wherein the predicted word has a same number of characters as a number of contacts in the sequence of contacts, (ii) a selection of the predicted word, wherein the predicted word has a greater number of characters than the number of contacts in the sequence of contacts, and (iii) a user input of a non-space character; and

update an input buffer based on an interpretation of the third contact, the interpretation being based on the probabilistic model.

20. The computing device of claim 19, wherein the at least one module is operable by the one or more processors to:

output at least a portion of the updated input buffer for display at the presence-sensitive screen.

21. The computing device of claim 19, wherein the probabilistic model comprises a language model that predicts words based on at least the sequence of contacts and a spatial model that predicts a character for the third contact based on the information about the spatial location of the third contact.

22. The computing device of claim 21, wherein the probabilistic model estimates a probability of selection of the predicted word having a same number of characters as the number of contacts in the sequence of contacts separately from estimating the probability of selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

23. The computing device of claim 22, wherein the probabilistic model comprises a first probability threshold for determining selection of the predicted word having the same number of characters as the number of contacts in the sequence of contacts, and a second probability threshold for determining selection of the predicted word having a greater number of characters than the number of contacts in the sequence of contacts.

24. The computing device of claim 23, wherein triggering the first probability threshold is more likely than triggering the second probability threshold.

25. The computing device of claim 19, wherein the probabilistic model interfaces with a spatial model that determines a probability that an input key is selected based on the spatial location of the third contact.

26. The computing device of claim 19, wherein the probabilistic model interfaces with a language model that determines a probability that an input key is selected based on previous contacts in the sequence of contacts.

27. The computing device of claim 19, wherein the sequence of contacts comprises contacts received subsequent to completion of at least one of a prior word and contacts initially received in response to a prompt for input.