Classification of User Input

• US 20140368436A1
• Filed: 06/13/2013
• Published: 12/18/2014
• Est. Priority Date: 06/13/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Abzarian, David, Su, Fei, Agrawal, Mudit, Nichols, Ross W.
• Granted Patent: US 9,405,379 B2
• Time in Patent Office: Days
• US Class Current: 345/168
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• 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 3/038 Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry
• CPC Class Codes: G06F 3/04186 Touch location disambiguation
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures

Abstract

Techniques for identifying inadvertent user input, such as inadvertent touch contact or air input, are described. The techniques may include classifying a touch contact or air input as intentional or unintentional based on contextual information related to the touch contact, the air input, or a device via which the touch contact or air input was received. In some examples, the contextual information may indicate how a user is interacting with the device, such as a position of the user'"'"'s hand, a location of the touch contact on a touch surface, a path of user'"'"'s touch trajectory, an application with which the user may be interacting, keyboard input history of the user, and so on. When the user input is classified as unintentional, the techniques may refrain from performing an action that is generally triggered by the user input.

Claims

1. A system comprising:

a touch device to receive a touch contact;

one or more processors communicatively coupled to the touch device;

memory communicatively coupled to the one or more processors;

a first classification module stored in the memory and executable by the one or more processors to determine a classification of the touch contact based at least in part on contextual information related to at least one of the touch contact or the system, the classification indicating that the touch contact is intentional or unintentional; and

a second classification module stored in the memory and executable by the one or more processors to determine whether the classification of the touch contact is accurate based, at least in part, on a history of the touch contact.

2. The system of claim 1, wherein the touch device comprises at least one of a touch pad or a touch screen.

3. The system of claim 1, wherein the contextual information comprises at least one of location information of the touch contact that indicates a location of the touch contact relative to a predetermined portion of the touch device, a confidence value of the touch contact that is determined by the touch device, geometry information of the touch contact that indicates a size or shape of the touch contact, or hand position information that indicates a position of a hand of a user relative to the system.

4. The system of claim 1, wherein the contextual information comprises at least one of application information related to an application that is running on the system, keyboard input history of a keyboard associated with the system, or information that indicates a number of substantially simultaneous touch contacts on the touch device.

5. The system of claim 1, wherein the classification of the touch contact is determined based at least in part on whether the touch contact is within a predetermined portion of the touch device.

6. The system of claim 5, wherein:

the predetermined portion of the touch device includes first and second portions; and

the classification of the touch contact indicates a degree of unintentional contact of the touch contact, the degree of unintentional contact being based, at least in part, on whether the touch contact is within the first portion or the second portion.

7. A method comprising:

receiving information that indicates a touch contact on a touch surface;

identifying a location of the touch contact on the touch surface from the information;

determining, by a device, that the location of the touch contact is within a predetermined portion of the touch surface that is defined based, at least in part, on an offset of the touch surface to an input device; and

upon determining that the location of the touch contact is within the predetermined portion of the touch surface, identifying the touch contact as inadvertent input.

8. The method of claim 7, wherein the predetermined portion of the touch surface includes an outer portion of the touch surface.

9. The method of claim 7, wherein the input device comprises a keyboard that is associated with the touch surface.

10. The method of claim 7, further comprising:

determining that an amount of time between receiving the touch contact via the touch surface and receiving input via a keyboard is less than a threshold amount of time,

wherein the touch contact is identified as inadvertent input based, at least in part, on determining that the amount of time is less than the threshold amount of time.

11. The method of claim 7, wherein the offset comprises at least one of:

a first offset between the touch surface and a keyboard that is associated with the touch surface, or

a second offset between the touch surface and the keyboard,

the first offset extending along a line that is substantially perpendicular to a line along which the second offset extends.

12. One or more computer storage media storing computer-readable instructions that, when executed, instruct one or more processors to perform operations comprising:

identifying information that indicates user input received via an input device, the user input comprising at least one of a touch contact or air input;

classifying the user input an intentional or unintentional based on at least one of a shape of the user input, a position of a hand of a user, application information related to an application that is currently running, keyboard input history, or a number of substantially simultaneous user inputs; and

upon classifying the user input as intentional, causing an action to be performed.

13. The one or more computer storage media of claim 12, wherein the operations further comprise:

reclassifying the user input based at least in part on user input history of the user input that indicates at least one of;

a duration of time that the user input was on a touch surface, a velocity of the user input, or a path of the user input.

14. The one or more computer storage media of claim 13, wherein the operations further comprise:

determining a probability that the user input was incorrectly classified based at least in part on the reclassifying; and

causing the action that was caused to be performed to be recalled when the probability exceeds a threshold.

15. The one or more computer storage media of claim 12, wherein the user input is classified with a statistical classifier that uses weighted variables for two or more of the shape of the user input, the position of the hand of the user, the application information related to the application that is currently running, the keyboard input history, or the number of substantially simultaneous user inputs.

16. The one or more computer storage media of claim 12, wherein the user input is classified with a rule classifier that uses threshold-based rules for at least one of the shape of the user input, the position of the hand of the user, the application information related to the application that is currently running, the keyboard input history, or the number of substantially simultaneous user inputs.

17. The one or more computer storage media of claim 12, wherein the classifying the user input includes classifying the user input as intentional when the keyboard input history indicates that input has not been received via a keyboard over a period of time.

18. The one or more computer storage media of claim 12, wherein the operations further comprise:

determining that an amount of time between receiving the user input via a touch surface and receiving input via a keyboard is more than a threshold amount of time,

wherein the classifying the user input comprises classifying the user input as intentional based at least in part on determining that the amount of time is more than a threshold amount of time.

19. The one or more computer storage media of claim 12, wherein the operations further comprise:

learning information related to a user'"'"'s interaction with at least one of a touch surface or a keyboard associated with the touch surface.

20. The one or more computer storage media of claim 19, wherein the information about the user'"'"'s interaction with the touch surface or the keyboard comprises at least one of an average typing rate of the user, how soon after typing the user uses the touch surface, or a characteristic about a hand of the user.