公开(公告)号：US20230222605A1

公开(公告)日：2023-07-13

申请号：US18185258

申请日：2023-03-16

Applicant: Meta Platforms, Inc.

Inventor： Vivek Natarajan ,  Shawn C.P. Mei ,  Zhengping Zuo

IPC: G10L15/22 ,  G06V40/16 ,  G02B27/01

CPC classification number: G10L15/22 ,  G06V40/172 ,  G02B27/017 ,  G02B2027/0138 ,  G02B2027/014

Abstract: In one embodiment, a method includes receiving at a head-mounted device a speech input from a user and a visual input captured by cameras of the head-mounted device, wherein the visual input comprises subjects and attributes associated with the subjects, and wherein the speech input comprises a co-reference to one or more of the subjects, resolving entities corresponding to the subjects associated with the co-reference based on the attributes and the co-reference, and presenting a communication content responsive to the speech input and the visual input at the head-mounted device, wherein the communication content comprises information associated with executing results of tasks corresponding to the resolved entities.