公开(公告)号：US20240296871A1

公开(公告)日：2024-09-05

申请号：US18573097

申请日：2023-05-09

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xinwei LI ,  Jiajin CAO

IPC: G11B27/036 ,  G06T11/60 ,  G11B27/10

CPC classification number: G11B27/036 ,  G06T11/60 ,  G11B27/10

Abstract: Embodiments of the present disclosure relates to a method, apparatus, device, storage medium, and program product for video generation. The method comprises: generating initial multimedia data based on received text data; obtaining a target editing template in response to an editing template obtaining request; applying the editing operation indicated by the target editing template to the initial multimedia data to obtain target multimedia data; and generating target video based on the target multimedia data. Embodiments of the present disclosure generates video by directly applying the editing operation in the obtained editing template to the multimedia data, without the need for users to manually clip the video. This can not only reduce the time cost of video production, but also improve the quality of video production.

公开(公告)号：US20250168464A1

公开(公告)日：2025-05-22

申请号：US19033358

申请日：2025-01-21

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Jiajin CAO

IPC: H04N21/81 ,  G10L13/02 ,  H04N21/488

Abstract: Disclosed are a multimedia data generating method, apparatus, electronic device, medium, and program product, applied to the field of multimedia data processing technologies. The method includes: receiving text information inputted by a user; displaying, in response to a recording trigger operation for the text information, the text information and acquiring a first reading speech of the text information; and generating a first multimedia data based on the text information and the first reading speech and displaying the first multimedia data; the first multimedia data includes the first reading speech and a video image matched with the text information; the first multimedia data includes a plurality of first multimedia segments; the plurality of first multimedia segments correspond to a plurality of text segments included in the text information, respectively. The disclose may improve quality of multimedia data generation.

公开(公告)号：US20240121469A1

公开(公告)日：2024-04-11

申请号：US18545819

申请日：2023-12-19

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Jiajin CAO

IPC: H04N21/431 ,  H04N21/234 ,  H04N21/488 ,  H04N21/845

CPC classification number: H04N21/4318 ,  H04N21/23424 ,  H04N21/4884 ,  H04N21/8456

Abstract: Embodiments of the present disclosure provide a video editing method and apparatus, an electronic device, and a storage medium. The method comprises: displaying a material filling interface of a target clip video, the target clip video comprising a plurality of clip segments, and the material filling interface comprising a video preview area, a clip segment switching area, and a multimedia material selection area; in response to a switching operation in the clip segment switching area, switching a selected first clip segment between the plurality of clip segments; in response to a selection operation on a first material in the multimedia material selection area, filling the first material into the first clip segment; and in response to a playback trigger operation on the target clip video, displaying and playing back the target clip video in the video preview area.

公开(公告)号：US20240114215A1

公开(公告)日：2024-04-04

申请号：US18538703

申请日：2023-12-13

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Jiajin CAO

IPC: H04N21/81 ,  G10L13/02 ,  H04N21/488

CPC classification number: H04N21/8106 ,  G10L13/02 ,  H04N21/4884

Abstract: Disclosed are a multimedia data generating method, apparatus, electronic device, medium, and program product, applied to the field of multimedia data processing technologies. The method includes: receiving text information inputted by a user; displaying, in response to a recording trigger operation for the text information, the text information and acquiring a first reading speech of the text information; and generating a first multimedia data based on the text information and the first reading speech and displaying the first multimedia data; the first multimedia data includes the first reading speech and a video image matched with the text information; the first multimedia data includes a plurality of first multimedia segments; the plurality of first multimedia segments correspond to a plurality of text segments included in the text information, respectively. The disclose may improve quality of multimedia data generation.