Soft keyboard interface

• US 9,262,076 B2
• Filed: 09/12/2011
• Issued: 02/16/2016
• Est. Priority Date: 09/12/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Townsend, Reed L., Agrawal, Mudit, Batchvarov, Andrey Borissov, Su, Fei
• Primary Examiner(s): Theriault, Steven B
• Application Number:
  US13/230,723
• Publication Number:
  US 20130067382A1
• Time in Patent Office: 1,618 Days
• Field of Search: 715/773, 715/822, 715/810, 715/812, 345/173, 345/168
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• 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 3/04895 Guidance during keyboard input operation, e.g. prompting

Abstract

User experience of the performance of a computing device is improved through an operating system that processes inputs from a soft keyboard to provide information that can be used to accurately determine keys a user intended to strike while typing. For each detected tap, the operating system provides a probability that one or more keys were the intended target for the user. These probabilities may be computed from probability distribution functions that are dynamically determined based on user and/or system factors, such as typing rate and keyboard style or layout. Other components may use the probabilities to select a key corresponding to a detected keyboard tap as representing the intended user input. The selection may be made based on the probabilities alone or in combination with contextual factors that yield an overall probability that a detected tap arose from a user targeting a specific key.

Claims

1. A method of operating a computing device having a soft keyboard, the method comprising:

determining at least one characteristic of at least one of;

(i) an average time between taps or (ii) a style of the soft keyboard;

determining, for each of a plurality of keys on the soft keyboard, a mean of a probability distribution function and an indication of a spread of the probability distribution function, the mean and the indication of the spread being determined based on the at least one determined characteristic;

with a soft keyboard interface executing on at least one processing circuit;

in response to a first input received through the soft keyboard;

generating a first set of probabilities based on the probability distribution functions, wherein the first set of probabilities includes;

a first indication indicative of a probability that a first key was targeted for the first input; and

a second indication indicative of a probability that a second key was targeted for the first input;

providing the first set of probabilities to a text prediction engine executing on the at least one processing circuit; and

in response to a second input received through the soft keyboard;

generating a second set of probabilities based on the probability distribution functions, wherein the second set of probabilities includes;

a third indication indicative of a probability that a third key was targeted for the second input; and

a fourth indication indicative of a probability that a fourth key was targeted for the second input;

providing the second set of probabilities to the text prediction engine executing on the at least one processing circuit; and

with the text prediction engine, predicting an intended word based on;

the first indication indicative of the probability that the first key was targeted for the first input;

the second indication indicative of the probability that the second key was targeted for the first input;

the third indication indicative of the probability that the third key was targeted for the second input; and

the fourth indication indicative of the probability that the fourth key was targeted for the second input.

2. The method of claim 1, wherein:

the mean and the indication of the spread of the probability distribution function are also based on the average time between taps.

3. The method of claim 1, wherein:

the mean and the indication of the spread of the probability distribution function are also based on the style of the soft keyboard.

4. The method of claim 1, wherein:

the mean and the indication of the spread of the probability distribution function are also based on a position of the key relative to a reference location on the soft keyboard.

5. The method of claim 4, wherein:

the mean and the indication of the spread of the probability distribution function are also based on the size of the key.

6. The method of claim 5, wherein:

the probability distribution function for each of the plurality of keys is a two dimensional spatial probability distribution function with the mean measured relative to a center of the key; and

at least one parameter of the probability distribution function is obtained by function fitting.

7. At least one computer-readable storage medium comprising computer-executable instructions that, when executed, perform a method of operating a soft keyboard interface on a computing device that processes input from a soft keyboard and a text prediction engine on the computing device, the method comprising:

receiving, by the soft keyboard interface, an indication of a first activation of a first location of a soft keyboard;

providing, by the soft keyboard interface, a first probability based at least in part on a mean of a first probability distribution function and on an indication of a spread of the first probability distribution function to the text prediction engine, wherein the first probability represents a likelihood that a first key of the soft keyboard was targeted for the first activation, and wherein the mean of the first probability distribution function and the indication of the spread of the first probability distribution function are based at least in part on a typing speed of input received via the soft keyboard or a style of the soft keyboard;

providing, by the soft keyboard interface, a second probability based at least in part on a mean of a second probability distribution function and on an indication of a spread of the second probability distribution function to the text prediction engine, wherein the second probability represents a likelihood that a second key of the soft keyboard was targeted for the first activation, and wherein the mean of the second probability distribution function and the indication of the spread of the second probability distribution function are based at least in part on the typing speed of input received via the soft keyboard or the style of the soft keyboard;

receiving, by the soft keyboard interface, an indication of a second activation of a second location of the soft keyboard;

providing, by the soft keyboard interface, a third probability and a fourth probability to the text prediction engine, wherein the third probability represents a likelihood that a third key of the soft keyboard was targeted for the second activation, and wherein the fourth probability represents a likelihood that a fourth key of the soft keyboard was targeted for the second activation;

receiving, by the text prediction engine, the first, second, third, and fourth probabilities from the soft keyboard interface; and

predicting, by the text prediction engine, a word according to the first, second, third, and fourth probabilities received from the soft keyboard interface.

8. The at least one computer-readable storage medium of claim 7, wherein the method further comprises:

receiving, by the soft keyboard interface, an indication of a third activation of a third location of the soft keyboard;

determining, by the soft keyboard interface, that a location of the third activation is within a central region of a fifth key of the soft keyboard; and

providing, by the soft keyboard interface, an indication that the fifth key was activated.

9. The at least one computer-readable storage medium of claim 7, wherein:

the computer readable storage medium further stores instructions for computing the first and second probability distribution functions; and

the method further comprises;

computing the first and second probability distribution functions using the stored instructions for computing the first and second probability distribution functions and an indication of the layout of the soft keyboard on a display of the computing device.

10. The at least one computer-readable storage medium of claim 9, wherein:

the typing speed of input received via the soft keyboard is based on a measured average time between user activations of the keyboard.

11. The at least one computer-readable storage medium of claim 10, wherein:

the instructions for computing the first and second probability distribution function comprise instructions that increase the indication of the spread of the first probability distribution function in response to an increase in the typing speed of the input received via the soft keyboard.

12. The at least one computer-readable storage medium of claim 10, wherein:

the plurality of keyboard layouts comprise;

a QWERTY keyboard;

a reduced QWERTY keyboard; and

a split keyboard.

13. The at least one computer-readable storage medium of claim 12, wherein:

the instructions for computing the first and second probability distribution functions comprise instructions that determine an offset for each of the first and second probability distribution functions, the offset being;

increased based on the increase in the typing speed of the input received via the soft keyboard; and

decreased in a direction towards a central portion of the soft keyboard for a QWERTY and a reduced QWERTY keyboard; and

/or

increased in a direction away from an edge of the soft keyboard for a split keyboard.

14. A computing device comprising:

a display adapted to visually present a soft keyboard;

a touchscreen controller configured to provide indications of activations of the soft keyboard;

a keyboard interface configured to monitor a typing rate associated with the soft keyboard; and

a processor configured to, for each of multiple activations in the region, provide probabilities for each of a set of keys proximate the location of that activation based at least in part on respective means of probability distribution functions for each of the set of keys proximate the location of that activation and on respective indications of spreads of the probability distribution functions, the individual probabilities representing likelihoods that an associated key was targeted for that particular activation, and the probability distribution functions being based at least in part on at least one of the typing rate or a style of the soft keyboard; and

the processor further configured to predict a word based on;

a first likelihood that a first key was targeted for a first activation of the multiple activations;

a second likelihood that a second key was targeted for the first activation of the multiple activations;

a third likelihood that a third key was targeted for a second activation of the multiple activations; and

a fourth likelihood that a fourth key was targeted for the second activation of the multiple activations.

15. The computing device of claim 14, wherein:

the individual probabilities are based on a layout of the soft keyboard.

16. The computing device of claim 14, wherein:

the processor is further configured to;

compute, for each of the set of keys, the probability distribution function to represent a probability that a given activation at a location proximate that key represents intent to actuate that key; and

determine the provided probabilities based on the probability distribution functions.

17. The computing device of claim 16, wherein:

the processor is further configured to;

compute the probability distribution functions via selection of parameters of a Gaussian distribution based on the typing rate.

18. The computing device of claim 14, wherein:

the individual probabilities are further based on a size of a gutter between adjacent keys on the soft keyboard.

19. The computing device of claim 14, wherein:

the computing device has a tablet form factor.