Nonstandard locality-based text entry

• US 10,534,802 B2
• Filed: 08/08/2017
• Issued: 01/14/2020
• Est. Priority Date: 06/25/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Baluja, Shumeet, Kamvar, Maryam, Gil, Elad
• Primary Examiner(s): Pulliam, Christyann R
• Assistant Examiner(s): Hoffler, Raheem
• Application Number:
  US15/671,994
• Publication Number:
  US 20180032604A1
• Time in Patent Office: 889 Days
• Field of Search: 707 3
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04M 1/72445 for supporting Internet browser applications
• CPC Class Codes: H04M 1/72457 according to geographic location
• CPC Class Codes: H04M 2250/10 including a GPS signal receiver
• CPC Class Codes: H04M 2250/70 methods for entering alphabetical characters, e.g. multi-tap or dictionary disambiguation

Abstract

A computer-implemented method of providing text entry assistance data includes receiving at a system location information associated with a user, receiving at the system information indicative of predictive textual outcomes, generating dictionary data using the location information, and providing the dictionary data to a remote device.

Claims

1. A device comprising:

a memory comprising a data entry dictionary that maintains concurrence probabilities for words in the data entry dictionary; and

at least one processor configured to;

receive a plurality of user inputs that each correspond to a respective location of a keyboard;

determine, based on the plurality of user inputs, at least one first word from the data entry dictionary;

automatically receive updated dictionary information for a particular geographic location that is associated with the at least one first word;

add, to the data entry dictionary and from the updated dictionary information, at least one second word that is associated with the particular geographic location;

update, based on the updated dictionary information, the concurrence probabilities for words in the data entry dictionary;

output, for display, the at least one first word;

and

output, for display and based at least in part on a respective concurrence probability of the at least one second word relative to the at least one first word, the at least one second word as a likely candidate for a follow-up word.

2. The device of claim 1, wherein the at least one processor is configured to update the concurrence probabilities for words in the data entry dictionary by increasing a respective concurrence probability of the at least one first word relative to the at least one second word.

3. The device of claim 1, wherein the at least one processor is further configured to output the at least one second word as the likely candidate term further in response to determining that the respective concurrence probability of the at least one second word relative to the at least one first word exceeds a respective concurrence probability of other words from the data entry dictionary relative to the at least one first word.

4. The device of claim 1, wherein the at least one processor is further configured to update the concurrence probabilities for words in the data entry dictionary by decreasing respective probabilities, relative to the at least one first word, of other words from the data entry dictionary that are not associated with the particular geographic location.

5. The device of claim 1, wherein the at least one first word is different than the at least one second word.

6. The device of claim 1, wherein the at least one processor is further configured to automatically receive updated dictionary information for a particular geographic location that is associated with the at least one first word in response to outputting location information indicative of the particular geographic location associated with the at least one first word, the location information being obtained from a positioning system that indicates the device is at the particular geographic location.

7. The device of claim 1, wherein the device is a client device and the at least one processor is configured to automatically receive the updated dictionary information from a server device.

8. The device of claim 7, wherein the at least one processor is configured to automatically receive the updated dictionary information from the server device in response to outputting, to the server device, location information indicative of the particular geographic location associated with the at least one first word, the location information being obtained from a positioning system that indicates the device is at the particular geographic location.

9. The device of claim 7, wherein the at least one processor is configured to automatically receive the updated dictionary information from the server device while the at least one processor receives additional user inputs that each correspond to a respective location of the keyboard.

10. The device of claim 7, wherein the at least one processor is configured to automatically receive the updated dictionary information from the server device periodically and apart from receiving additional user inputs that each correspond to a respective location of the keyboard.

11. A method comprising:

receiving, by a computing device, a plurality of user inputs that each correspond to a respective location of a keyboard;

determining, by the computing device, based on the plurality of user inputs, at least one first word from a data entry dictionary maintained in a memory of the computing device;

automatically receiving updated dictionary information for a particular geographic location that is associated with the at least one first word;

adding, to the data entry dictionary and based on the updated dictionary information, at least one second word that is associated with the particular geographic location;

updating, based on the updated dictionary information, concurrence probabilities for words maintained in the data entry dictionary;

outputting, by the computing device, for display, the at least one first word;

and

outputting, by the computing device, for display and based at least in part on a respective concurrence probability of the at least one second word relative to the at least one first word, the at least one second word as a likely candidate for a follow-up word.

12. The method of claim 11, wherein updating the concurrence probabilities for words in the data entry dictionary comprises:

increasing, by the computing device, a respective concurrence probability of the at least one first word relative to the at least one second word.

13. The method of claim 11, wherein outputting the at least one second word as the likely candidate term further comprises outputting the at least one second word as the likely candidate term in response to determining that the respective concurrence probability of the at least one second word relative to the at least one first word exceeds a respective concurrence probability of other words from the data entry dictionary relative to the at least one first word.

14. The method of claim 11, wherein updating the concurrence probabilities for words in the data entry dictionary comprises:

decreasing, by the computing device, respective probabilities, relative to the at least one first word, of other words from the data entry dictionary that are not associated with the particular geographic location.

15. The method of claim 11, wherein the at least one first word is different than the at least one second word.

16. The method of claim 11, wherein automatically receiving updated dictionary information for a particular geographic location that is associated with the at least one first word comprises:

obtaining, from a positioning system, location information that indicates the computing device is at the particular geographic location; and

automatically receiving the updated dictionary information for the particular geographic location that is associated with the at least one first word in response to outputting the location information obtained from the positioning system.

17. The method of claim 11, further comprising:

decreasing the respective concurrence probability of the at least one second word relative to the at least one first word based on a distance traveled from the particular geographic location that is associated with the at least one first word.

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

receive a plurality of user inputs that each correspond to a respective location of a keyboard;

determine, based on the plurality of user inputs, at least one first word from a data entry dictionary maintained in a memory of the computing device;

automatically receive updated dictionary information for a particular geographic location that is associated with the at least one first word;

adding, to the data entry dictionary and based on the updated dictionary information, at least one second word that is associated with the particular geographic location;

updating, based on the updated dictionary information, concurrence probabilities for words maintained in the data entry dictionary;

output, for display, the at least one first word;

output, for display and based at least in part on a respective concurrence probability of the at least one second word relative to the at least one first word, the at least one second word as a likely candidate for a follow-up word.

19. The non-transitory, machine-readable medium of claim 18, wherein the non-transitory, machine-readable medium of claim is further encoded with instructions that, when executed, cause the at least one processor of the computing device to update the concurrence probabilities for words in the data entry dictionary by:

increasing a respective concurrence probability of the at least one first word relative to the at least one second word.

20. The non-transitory, machine-readable medium of claim 18, wherein the instructions, when executed, cause the at least one processor to output the at least one second word as the likely candidate term further in response to determining that the respective concurrence probability of the at least one second word relative to the at least one first word exceeds a respective concurrence probability of other words from the data entry dictionary relative to the at least one first word.

21. The non-transitory, machine-readable medium of claim 18, wherein the non-transitory, machine-readable medium of claim is further encoded with instructions that, when executed, cause the at least one processor of the computing device to update the concurrence probabilities for words in the data entry dictionary by decreasing respective probabilities, relative to the at least one first word, of other words from the data entry dictionary that are not associated with the particular geographic location.