Method and apparatus for word prediction using the position of a non-typing digit

• US 9,348,429 B2
• Filed: 03/15/2013
• Issued: 05/24/2016
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Pasquero, Jerome, McKenzie, Donald Somerset McCulloch
• Primary Examiner(s): Pappas, Claire X
• Assistant Examiner(s): CASAREZ, BENJAMIN X.
• Application Number:
  US13/833,303
• Publication Number:
  US 20140267056A1
• Time in Patent Office: 1,166 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0227 Cooperation and interconnection of the input arrangement with other functional units of a computer G06F3/023 - G06F3/037 take precedence
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

Methods and apparatuses are provided for improving word prediction in an electronic device. User input of one or more characters is received via a capacitive physical keyboard having a plurality of input members. Concurrently, the device determines the location of a non-typing digit, such as the user'"'"'s finger or a stylus. Word prediction candidates are generated and weighted, and candidates that have subsequent characters associated with the input member proximal to the location of the non-typing digit are given more weight. The word prediction candidates are displayed, a second user input is then received comprising a selection of one of the candidates, and the device displays the selected word prediction candidate on the display.

Claims

1. A method for operating an electronic device having a display and a keyboard having a plurality of input members for receiving inputs, comprising:

receiving an input of one or more characters by a first typing digit;

detecting a first position of a non-typing digit while receiving the input by the first typing digit, wherein the non-typing digit is a digit other than the typing digit;

determining a plurality of reference motion vectors that represent respective possible movements of the non-typing digit from the first position of the non-typing digit to a plurality of possible input members of the keyboard;

detecting a second position of the non-typing digit at the end of multiple time points;

generating an actual motion vector for the non-typing digit based on the first position and the second position of the non-typing digit;

comparing the actual motion vector with the plurality of reference motion vectors;

generating a set of word prediction candidates based on the input and the second position of the non-typing digit;

weighting the word prediction candidates in the set;

adjusting weights for word prediction candidates based on respective closeness between the actual motion vector with the plurality of reference motion vectors; and

displaying select ones of the word prediction candidates based on the adjusted weights.

2. The method of claim 1, further comprising:

receiving selection of a word prediction candidate; and

responsive to detection of an input reflecting selection of one of the word prediction candidates, displaying in an input field on the display the selected candidate.

3. The method of claim 1, further comprising:

displaying visual indicia of the character within each displayed word prediction candidate corresponding to the input member proximal to the detected position of the non-typing digit.

4. The method of claim 1, wherein weighting the word prediction candidates in the set includes weighting the word prediction candidates based on a geographical location of a user.

5. The method of claim 1, wherein adjusting weights for word prediction candidates includes:

weighting word prediction candidates in which a next character corresponds to an input member located under the non-typing digit greater than word prediction candidates in which a character following the next character corresponds to the input member located under the non-typing digit.

6. The method of claim 1, wherein detecting the first position of the non-typing digit comprises:

detecting one or more X-Y coordinate pairs associated with the non-typing digit;

selecting one of the coordinate pairs; and

selecting an input member associated with the selected coordinate pair.

7. The method of claim 1, wherein the non-typing digit is hovering above the keyboard and its position is sensed by capacitive sensors integrated with, situated above, or situated under the input members.

8. The method of claim 1, wherein:

the input of one or more characters by the first typing digit corresponds to input members located to a first side of a space bar input member on the keyboard; and

the position of the non-typing digit corresponds to an input member located to a second side of the space bar input member, the first side and the second side being on opposite sides of the space bar input member.

9. The method of claim 1, wherein:

determining a plurality of reference motion vectors that represent respective possible movements of the non-typing digit from the first position of the non-typing digit to a plurality of possible input members of the keyboard the plurality of possible input members of the keyboard comprises determining a plurality of reference motion vectors that represent respective possible movements of the non-typing digit from the first position of the non-typing digit to a plurality of input members that are within a distance of the first position of the non-typing digit in all directions of the keyboard.

10. An electronic device having a display and a keyboard having a plurality of input members for receiving inputs, comprising:

a memory containing instructions; and

one or more processors configured to execute the instructions to;

receive an input of one or more characters by a first typing digit;

detect a first position of a non-typing digit while receiving the input by the first typing digit, wherein the non-typing digit is a digit other than the first digit;

determine a plurality of reference motion vectors that represent respective possible movements of the non-typing digit from the first position of the non-typing digit to a plurality of possible input members of the keyboard;

detect a second position of the non-typing digit at the end of multiple time points;

generate an actual motion vector for the non-typing digit based on the first position and the second position of the non-typing digit;

compare the actual motion vector with the plurality of reference motion vectors;

generate a set of word prediction candidates based on the input and the second position of the non-typing digit;

weight the word prediction candidates in the set;

adjust weights for word prediction candidates based on respective closeness between the actual motion vector with the plurality of reference motion vectors; and

display select ones of the word prediction candidates based on the adjusted weights.

11. The electronic device of claim 10, wherein the one or more processors are further configured to execute the instructions to:

receive selection of a word prediction candidate; and

responsive to detection of an input reflecting selection of one of the word prediction candidates, display in an input field on the display the selected candidate.

12. The electronic device of claim 10, wherein the one or more processors are further configured to execute the instructions to:

display visual indicia of the character within each displayed word prediction candidate corresponding to the input member proximal to the detected position of the non-typing digit.

13. The electronic device of claim 10, wherein the one or more processors are further configured to execute the instructions to:

weight the word prediction candidates based on a geographical location of a user.

14. The electronic device of claim 10, wherein the one or more processors are further configured to execute the instructions to:

adjust weights for word prediction candidates by weighting word prediction candidates in which a next character corresponds to an input member located under the non-typing digit greater than word prediction candidates in which a character following the next character corresponds to the input member located under the non-typing digit.

15. The electronic device of claim 10, wherein the one or more processors are further configured to execute the instructions to:

detect the position of the non-typing digit by;

detecting one or more X-Y coordinate pairs associated with the non-typing digit;

selecting one of the coordinate pairs; and

selecting an input member associated with the selected coordinate pair.

16. The electronic device of claim 10, wherein the non-typing digit is hovering above the keyboard and its position is sensed by capacitive sensors integrated with, situated above, or situated under the input members.

17. The electronic device of claim 10:

wherein;

the input of one or more characters by the first typing digit corresponds to input members located to a first side of a space bar input member on the keyboard; and

the position of the non-typing digit corresponds to an input member located to a second side of the space bar input member, the first side and the second side being on opposite sides of the space bar input member.

18. The electronic device of claim 10, wherein the one or more processors are configured to execute the instructions to:

determine a plurality of reference motion vectors that represent respective possible movements of the non-typing digit from the first position of the non-typing digit to a plurality of input members that are within a distance of the first position of the non-typing digit in all directions of the keyboard.