US 12,353,670 B2
Intelligent response using eye gaze
Dmytro Rudchenko, Bellevue, WA (US); Eric N. Badger, Redmond, WA (US); Akhilesh Kaza, Sammamish, WA (US); Jacob Daniel Cohen, Seattle, WA (US); and Harish S. Kulkarni, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jan. 31, 2022, as Appl. No. 17/588,807.
Application 17/588,807 is a continuation of application No. 15/840,562, filed on Dec. 13, 2017, granted, now 11,237,691.
Claims priority of provisional application 62/537,427, filed on Jul. 26, 2017.
Prior Publication US 2022/0155912 A1, May 19, 2022
Int. Cl. G06F 3/048 (2013.01); G06F 3/01 (2006.01); G06F 3/023 (2006.01); G06F 3/0481 (2022.01); G06F 3/04842 (2022.01); G06F 3/04886 (2022.01); G06F 40/274 (2020.01); G06N 20/00 (2019.01)
CPC G06F 3/0481 (2013.01) [G06F 3/013 (2013.01); G06F 3/0237 (2013.01); G06F 3/04842 (2013.01); G06F 3/04886 (2013.01); G06F 40/274 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A processor-implemented method for analyzing eye-gaze input, comprising:
receiving, during a current user session, a current eye-gaze input associated with a first gaze location on an electronic device, the first gaze location being associated with a user interface (UI) element having a function beyond character entry, wherein the UI element corresponds to a button in a web browser, a URL link, or a hyperlink to an application;
determining an intended selection of the UI element based on a first plurality of gaze location points in the current eye-gaze input and historical eye-gaze data received during one or more previous user sessions associated with previous eye-gaze input comprising a second plurality of gaze location points, the historical eye-gaze data comprising at least one of:
one or more historical gaze locations on a certain webpage, wherein the one or more historical gaze locations are based on the second plurality of gaze location points; or
historical click-log data associated with the previous eye-gaze input from one or more users, the historical click-log data indicating one or more previous selections of one or more UI elements; and
causing a selection of the UI element based on the current eye gaze input and the historical eye-gaze data.