Visual Attention-Based Surfacing Using Inferred Head Pose With Product Locations
AssigneeGoogle Inc.
InventorDongeek Shin
Life of this patent
Estimating the term…
Abstract
Systems (312) and methods (400) are provided for passively collecting context data associated with in-store shopping by a user. In this regard, one or more processors (202, 204) may receive, from each earbud in a pair of earbuds (238) worn by a user, sensor data corresponding to an orientation of each respective earbud (240, 242). Based on the received sensor data, the one or more processors (202, 204) may determine the gaze directions of the user as the user travels within a store and one or more products viewed by the user while traveling within the store by comparing, using a content map (128) of the store, the gaze directions of the user to product locations storing products, wherein the one or more products are the context data.
Claims21
A method for passively collecting context data, the method comprising:
- receiving, by one or more processors, from each earbud in a pair of earbuds worn by a user, sensor data corresponding to an orientation of each respective earbud;
- determining, by the one or more processors, based on the received sensor data, gaze directions of the user as the user travels within a facility;
- and
- determining, by the one or more processors, one or more products viewed by the user while traveling within the facility by comparing, using a content map of the facility, the gaze directions of the user to product locations storing products, wherein the one or more products are the context data.
A system comprising:
- one or more processors;
- and
- a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
- receive, from each earbud in a pair of earbuds worn by a user, sensor data corresponding to an orientation of each respective earbud;
- determine, based on the received sensor data, gaze directions of the user as the user travels within a facility;
- and
- determine, one or more products viewed by the user while traveling within the facility by comparing, using a content map of the facility, the gaze directions of the user to product locations storing products, wherein the one or more products are the context data.
(canceled)
Dependencies are inferred from the claim text.