Intended Input to a User Interface from Detected Gesture Positions

Patent metadata

Field	Value
Publication number	US-2020348836-A1
Application number	US-201916400857-A
Country	US
Kind code	A1
Filing date	May 1, 2019
Priority date	May 1, 2019
Publication date	Nov 5, 2020
Grant date	—

Abstract

The present disclosure describes techniques and systems directed to determining an intended input to a user interface from detected gesture positions. The described techniques and systems include detecting positions associated with a gesture made relative the user interface, associating a timing profile to the detected positions, and determining, from the detected positions and the associated timing profile, the intended input to the user interface.

First claim

What is claimed is:

1 . A computing device comprising:
a user interface having a display; a position-detection mechanism; a processor; and a computer-readable media having executable instructions of a position-detection manager that, when executed by the processor, direct the computing device to:
detect, through the position-detection mechanism, positions associated with a gesture, the gesture made by a user of the computing device relative to the user interface;
associate, to the detected positions, a timing profile and a context;
determine, using the associated timing profile and the associated context, an intended input by the user; and
performing an operation corresponding to the determined, intended input.

2 . The computing device of claim 1 , wherein the timing profile identifies a static position associated with the gesture and determining the intended input is based, in part, on the identified, static position.

3 . The computing device of claim 1 , wherein the computing device detects the context using a sensor of the computing device that is a GPS sensor, a proximity sensor, an accelerometer, a radar sensor, a radio-frequency identification (RFID) sensor, or a near-field communication (NFC) sensor.

4 . The computing device of claim 1 , wherein the position-detection mechanism includes:
an input mechanism that is a mouse, a mouse-scrolling wheel, a touchpad, a touchpad button, or a touchpad joystick; and determining the intended input includes using a gauge capability of the mouse, the mouse-scrolling wheel, the touchpad, the touchpad button, or the touchpad joystick.

5 . The computing device of claim 1 , wherein the position-detection mechanism includes an input mechanism that is a radar sensor and determining the intended input includes using a gauge capability of the radar sensor.

6 . The computing device of claim 1 , wherein the position-detection mechanism includes an input mechanism that is an image sensor and determining the intended input includes using a gauge capability of the image sensor.

7 . The computing device of claim 1 , wherein the user interface including the display combines with the position-detection mechanism to form a touchscreen.

8 . The computing device of claim 7 , wherein the position-detection mechanism uses a capacitive, resistive, reflective, or grid-interruption technology and determining the intended input includes using a gauge capability of the position-detection mechanism for the capacitive, reflective, or grid interruption technology.

9 . The computing device of claim 1 , wherein:
the computing device includes a sensor that detects a condition surrounding the computing device; and the computing device uses the detected condition surrounding the computing device to determine the context that is associated to the detected positions.

10 . The computing device of claim 9 , wherein the detected condition is a location of the computing device.

11 . The computing device of claim 9 , wherein the detected condition is an identity of a user of the computing device.

12 . A method performed by a computing device comprising:
detecting positions associated with a gesture, the gesture made by a user of the computing device and the gesture made relative to a touchscreen of the computing device; associating, to the detected positions, a timing profile; determining, based on the detected positions and the timing profile, an intended input by the user; and performing an operation corresponding to the determined, intended input, wherein performing the operation that corresponds to the determined, intended input includes providing the input to an application that launches the application, selects a variable presented by the application, or terminates the application.

13 . The method of claim 12 , wherein associating the timing profile to the positions detected relative to the touchscreen identifies a static position associated with a portion of the gesture.

14 . The method of claim 13 , wherein the determined, intended input corresponds to the identified, static position.

15 . The method of claim 12 , wherein associating the timing profile to the positions detected relative to the touchscreen identifies a motion vector associated with the gesture.

16 . The method of claim 15 , wherein the determined, intended input corresponds to a weighted average of detected positions associated with a low relative-velocity portion of the motion vector.

17 . A method performed by a computing device comprising:
detecting positions associated with a gesture, the gesture made by a user of the computing device and the positions detected relative to a touchscreen of the computing device; associating, to the detected positions, a context; determining, based on the detected positions and the associated context, an intended input by the user; and performing an operation corresponding to the determined, intended input, wherein performing the operation that corresponds to the determined, intended input includes providing the input to an application that launches the application, selects a variable presented by the application, or terminates the application.

18 . The method of claim 17 , wherein determining the intended input uses a machine-learning algorithm executed by a processor of the computing device, wherein the machine-learning algorithm accounts for variables that include a past behavior of the user, a location of the computing device, or a time of day.

19 . The method of claim 18 , wherein the machine-learning algorithm adheres to a neural network model.

20 . The method of claim 17 , wherein the application is accessed through a cloud-based service provider.

Assignees

• Google Llc

Inventors

• Adem Richard Hasim

Classifications

• G06F3/011

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06F3/0416

  Control or interface arrangements specially adapted for digitisers · CPC title

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06F3/04883 Primary

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06F3/044

  by capacitive means · CPC title