公开(公告)号：US20220375172A1

公开(公告)日：2022-11-24

申请号：US17742900

申请日：2022-05-12

Applicant: Snap Inc.

Inventor： David Meisenholder ,  Kameron Sheffield ,  Joseph Timothy Fortier ,  Raymond Zeng ,  Andrei Rybin ,  Jonathan Geddes

IPC: G06T19/00 ,  G06V20/20 ,  G06V10/74 ,  G06V20/60 ,  G06F3/0482 ,  G06F3/04817 ,  G10L15/22 ,  G10L15/08 ,  G06F3/16 ,  G06V10/40 ,  G06V10/70

Abstract: Augmented reality features are selected for presentation to a display of an electronic eyewear device by using a camera of the electronic eyewear device to capture a scan image and processing the scan image to extract contextual signals. Simultaneously, voice data from the user is captured by a microphone of the electronic eyewear device and voice-to-text conversion of the captured voice data is performed to identify keywords in the voice data. The extracted contextual signals and the identified keywords are then used to select at least one augmented reality feature that matches the extracted contextual signals and the identified keywords, and the selected augmented reality feature is presented to the display for user selection. The contextual information thus refines the search results to provide the augmented reality feature best suited for the context of the scan image captured by the electronic eyewear device.