MULTI-FACTOR PROBABILISTIC MODEL FOR EVALUATING USER INPUT

• US 20110238612A1
• Filed: 03/26/2010
• Published: 09/29/2011
• Est. Priority Date: 03/26/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wilson, Andrew David
• Granted Patent: US 11,429,272 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• 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 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A multi-factor probabilistic model evaluates user input to determine if the user input was intended for an on-screen user interface control. When user input is received, a probability is computed that the user input was intended for each on-screen user interface control. The user input is then associated with the user interface control that has the highest computed probability. The probability that user input was intended for each user interface control may be computed utilizing a multitude of factors including the probability that the user input is near each user interface control, the probability that the motion of the user input is consistent with the user interface control, the probability that the shape of the user input is consistent with the user interface control, and that the size of the user input is consistent with the user interface control.

Claims

1. A computer-implemented method for evaluating user input, the method comprising:

displaying one or more user interface controls;

receiving the user input;

for each user interface control, computing a probability that the user input was intended for the user interface control; and

associating the user input with the user interface control having the highest computed probability.

2. The computer-implemented method of claim 1, wherein computing a probability that the user input was intended for a user interface control comprises computing a probability that the user input was intended for a user interface control based upon a plurality of factors.

3. The computer-implemented method of claim 1, wherein one of the plurality of factors comprises the probability that the user input is near the user interface control.

4. The computer-implemented method of claim 3, wherein one of the plurality of factors comprises the probability that a motion of the user input is consistent with the user interface control.

5. The computer-implemented method of claim 4, wherein one of the plurality of factors comprises the probability that a shape of the user input is consistent with the user interface control.

6. The computer-implemented method of claim 5, wherein one of the plurality of factors comprises the probability that a size of the user input is consistent with the user interface control.

7. The computer-implemented method of claim 6, wherein each of the plurality of factors has an associated weight.

8. The computer-implemented method of claim 7, wherein the user input is associated with the user interface control having the highest probability if the highest probability is greater than a threshold probability.

9. The computer-implemented method of claim 8, wherein the probability that the user input was intended for the user interface control is computed over time.

10. The computer-implemented method of claim 9, further comprising:

determining whether multiple user input controls have a high computed probability; and

in response to determining that multiple user input controls have a high computed probability, providing a user interface through which a user can signify which of the multiple user interface controls the user input was intended for.

11. A computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

receive user input; and

in response to receiving the user input, to identify one of a plurality of user interface controls for which the user input is intended by computing a probability for each of the user interface controls using a probabilistic multi-factor model.

12. The computer-readable storage medium of claim 11, wherein the probabilistic multi-factor model is configured to compute a probability for each user interface control that the user input was intended for the user interface control, and to associate the user input with the user interface control having the highest computed probability.

13. The computer-readable storage medium of claim 12, wherein computing a probability for each user interface control that the user input was intended for the user interface control comprises computing a probability that the user input was intended for the user interface control based upon a plurality of factors.

14. The computer-readable storage medium of claim 13, wherein one of the plurality of factors comprises the probability that the user input is near the user interface control.

15. The computer-readable storage medium of claim 13, wherein one of the plurality of factors comprises the probability that a motion of the user input is consistent with the user interface control.

16. The computer-readable storage medium of claim 13, wherein one of the plurality of factors comprises the probability that a shape of the user input is consistent with the user interface control.

17. The computer-readable storage medium of claim 13, wherein one of the plurality of factors comprises the probability that a size of the user input is consistent with the user interface control.

18. The computer-readable storage medium of claim 13, wherein each of the plurality of factors has an associated weight.

19. The computer-readable storage medium of claim 13, wherein the probability that the user input was intended for the user interface control is computed over time.

20. A computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

display one or more user interface controls;

receive user input;

for each user interface control, compute a probability that the user input was intended for the user interface control utilizing a probabilistic multi-factor model configured to compute the probability for each user interface control based upon a plurality of weighted factors comprising one or more of the probability that the user input is near the user interface control, the probability that a motion of the user input is consistent with the user interface control, the probability that a shape of the user input is consistent with the user interface control, and the probability that a size of the user input is consistent with the user interface control; and

to

associate the user input with the user interface control having the highest computed probability that exceeds a threshold.