公开(公告)号：US20240112702A1

公开(公告)日：2024-04-04

申请号：US18537529

申请日：2023-12-12

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Gen LI ,  Wozhou HE ,  Xinglong WU

IPC: G11B27/031 ,  H04L67/306

CPC classification number: G11B27/031 ,  H04L67/306

Abstract: The present disclosure provides a template recommendation method and apparatus, a device, and a storage medium. The method comprises: first, obtaining a feature of a multimedia material to be processed; then, determining a similarity between the feature corresponding to said multimedia material and a feature corresponding to a candidate editing template; and in response to determining that the similarity satisfies a preset matching condition, determining the candidate editing template as a target editing template corresponding to said multimedia material.

公开(公告)号：US20240249752A1

公开(公告)日：2024-07-25

申请号：US18566180

申请日：2022-06-01

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Wozhou HE ,  Gen LI ,  Xinglong WU

IPC: G11B27/031 ,  G06T5/60 ,  G06T5/70 ,  G06T7/20 ,  G11B27/00

CPC classification number: G11B27/031 ,  G06T5/60 ,  G06T5/70 ,  G06T7/20 ,  G11B27/005 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method, device, storage medium, and computer program product of video processing are provided in embodiments of the disclosure, by obtaining an initial video segment; inputting the initial video segment into a machine learning model and determining a speed variation rate of the initial video segment based on an output result of the machine learning model; wherein the machine learning model has been trained based on a sample video segment labeled with the speed variation rate; and varying a speed of the initial video segment based on the speed variation rate to obtain a target video segment. Embodiments of the present disclosure apply artificial intelligence to determine the speed variation rate of an initial video segment by a machine learning model to reduce the dependence on the user's editing experience, increase the density of the video information, and increase the number of overall playing of the released video.