公开(公告)号：US20240281060A1

公开(公告)日：2024-08-22

申请号：US18569362

申请日：2022-08-30

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Bingchuan Li

IPC: G06F3/01 ,  G06T7/73

CPC classification number: G06F3/013 ,  G06T7/73 ,  G06T2207/20081 ,  G06T2207/30201

Abstract: The present disclosure discloses a method, apparatus, electronic device, and storage medium for line-of-sight angle adjustment. The line-of-sight angle adjustment method comprises: collecting a facial image to be processed of a target user, processing the facial image to be processed based on a target line-of-sight angle adjustment model to obtain a target facial image corresponding to the facial image to be processed, the target line-of-sight angle adjustment model is used to adjust the line-of-sight angle of a user in the facial image to the target angle; and displaying the target facial image to at least one client.

公开(公告)号：US20240296830A1

公开(公告)日：2024-09-05

申请号：US18573126

申请日：2022-08-24

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Fan Yang ,  Ziqi Sun ,  Yongsen Jiang ,  Bingchuan Li ,  Rongkun Gao

IPC: G10L15/02 ,  G06V40/16 ,  G10L15/08

CPC classification number: G10L15/02 ,  G06V40/161 ,  G10L15/08 ,  G10L2015/088

Abstract: The disclosure discloses a data processing method, apparatus, electronic device, and storage medium. The data processing method includes: collecting audio and video frame data associated with a target user, wherein the audio and video frame data includes voice information to be processed and a face image to be processed; processing the face image to be processed based on a target line-of-sight angle adjustment model to obtain a target face image corresponding to the face image to be processed; performing a following process on the voice information to be processed based on an audio content following method and determining a target sentence in a target text associated with the voice information to be processed; and displaying the target sentence and the target face image separately on clients associated with the target user, or displaying the target sentence and the target face image on a client associated with the target user together.