User-centric soft keyboard predictive technologies

• US 10,156,981 B2
• Filed: 04/01/2017
• Issued: 12/18/2018
• Est. Priority Date: 02/12/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Badger, Eric Norman, Linerud, Drew Elliott, Almog, Itai, Paek, Timothy S., Sundararajan, Parthasarathy, Rudchenko, Dmytro, Gunawardana, Asela J.
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US15/477,075
• Publication Number:
  US 20170206002A1
• Time in Patent Office: 626 Days
• Field of Search: 706 15, 706 45
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• 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 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

An apparatus and method are disclosed for providing feedback and guidance to touch screen device users to improve text entry user experience and performance by generating input history data including character probabilities, word probabilities, and touch models. According to one embodiment, a method comprises receiving first input data, automatically learning user tendencies based on the first input data to generate input history data, receiving second input data, and generating auto-corrections or suggestion candidates for one or more words of the second input data based on the input history data. The user can then select one of the suggestion candidates to replace a selected word with the selected suggestion candidate.

Claims

1. A method, comprising:

receiving first input data associated with an input scope of a text input device, wherein the first input data comprises one or more words;

receiving second input data comprising text;

analyzing the second input data and at least a portion of input history data stored in an input history data source; and

based on the analyzing, providing at least one user-specific suggestion candidate for the second input data on a display coupled to the text input device, and resizing one or more target areas associated with one or more, but less than all, respective keys displayed on the display, wherein the resizing is based on one or more characters previously received in the second input data text.

2. The method of claim 1,

wherein the resizing is based on a plurality of characters previously received in the second input data text.

3. The method of claim 1, wherein:

the resizing the one or more target areas comprises using a generic touch model based on previously-collected keyboard typing data for plural users, the generic touch model including one or more child probability scores for one or more input data sequences for the typing data.

4. The method of claim 1, wherein the user-specific suggestion candidates are for a predicted next character for the second input data.

5. The method of claim 1, wherein the user-specific suggestion candidates are displayed in an area adjacent to a most-recently selected character of data in the second input data on the display.

6. The method of claim 1, further comprising generating the input history data by automatically learning user tendencies for the first input data.

7. The method of claim 6, wherein the input history data comprises at least one or more of the following:

user-specific web content, a user-specific dictionary, user-specific word probabilities, or a user-specific touch model.

8. The method of claim 1, wherein the display comprises a touch screen keyboard, and wherein the first input data and the second input data are received with the touch screen keyboard.

9. The method of claim 1, wherein the first input data and the second input data are received with a touch screen mechanically coupled to the text input device, and wherein the touch screen is not mechanically coupled to the display.

10. The method of claim 1, wherein the first input data, the second input data, or the first input data and the second input data are received in a computing cloud via a computer network, and wherein the providing at least one user-specific suggestion candidate comprises sending data for the suggestion candidate to a computing device via the computer network.

11. A text entry device, comprising:

at least one processor; and

a computer-readable storage device or memory storing computer-readable instructions that when executed by the at least one processor, cause the text entry device to perform a method of text entry, the instructions comprising;

instructions that cause the text entry device to receive first input data comprising one or more words, the first input data being associated with an input scope of the text entry device,

instructions that cause the text entry device to receive second input data comprising one or more characters,

instructions that cause the text entry device to analyze the second input data and at least a portion of input history data,

instructions that cause the text entry device to resize one or more target areas associated with one or more, but less than all, respective keys displayed on the display, wherein the resizing is based on one or more characters previously received in the second input data text, and

instructions to provide at least one user-specific suggestion candidate for the second input data on a display coupled to the text entry device.

12. The text entry device of claim 11, wherein

the resizing is based on a plurality of characters previously received in the second input data text.

13. The text entry device of claim 11, wherein the instructions further comprise:

instructions that cause the text entry device to resize the one or more target areas comprises using a generic touch model based on previously-collected keyboard typing data for plural users, the generic touch model including one or more child probability scores for one or more input data sequences for the typing data.

14. The text entry device of claim 11, wherein the instructions further comprise:

instructions that cause the text entry device to display the user-specific suggestion candidates in an area adjacent to a most-recently selected character of data in the second input data on the display.

15. The text entry device of claim 11, wherein the instructions further comprise:

instructions that cause the text entry device to generate the input history data by automatically learning user tendencies for the first input data.

16. The text entry device of claim 11, wherein:

at least a portion of the input history data is stored in a computer-readable storage device or memory mechanically coupled to the text entry device; and

the input history data comprises at least one or more of the following;

user-specific web content, a user-specific dictionary, user-specific word probabilities, or a user-specific touch model.

17. The text entry device of claim 11, wherein:

the display is a touch screen display mechanically coupled to the text entry device.

18. The text entry device of claim 11, wherein:

the text entry device comprises a touch screen display configured to generate the first input data and the second input data.

19. The text entry device of claim 11, wherein:

the text entry device is a smart television; and

the text entry device generates the first input data, the second input data, or the first input data and the second input data based on user input received from an input device in wireless communication with the text entry device.

20. One or more computer-readable storage media storing computer-readable instructions that when executed by a computer, cause the computer to perform a method, the method comprising:

receiving first input data associated with an input scope of a text input device, wherein the first input data comprises one or more words;

receiving second input data comprising text;

analyzing the second input data and at least a portion of input history data stored in an input history data source;

resizing one or more target areas associated with one or more, but less than all, respective keys displayed on a display, the resizing being based on one or more characters previously received in the second input data text; and

based on the analyzing, providing at least one user-specific suggestion candidates for the second input data on the display coupled to the text input device.