Video generation method and device, electronic equipment and storage medium

Through automated steps, new subtitle text and audio are extracted and generated, combined with video special effects, the problem of low video fission efficiency in the existing technology is solved, and efficient personalized video generation is achieved to meet the diverse needs of users.

CN119071559APending Publication Date: 2024-12-03GUANGZHOU XINGYI NETWORK TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411188331.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing video fission method relies on manual editing, is inefficient and lacks personalization, making it difficult to meet the diverse content creation needs of users.

Method used

Obtain target video through automated steps, extract original video frames and subtitle text, generate new subtitle text and commentary audio based on preset models, add it to the original video frame, generate new videos, and add video special effects to achieve different commentary styles and tones video variant.

Benefits of technology

It realizes efficient generation of commentary styles and tone video variants different from the original video, meets users' diverse content creation needs, and improves the efficiency and personalization of video fission.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071559A_ABST
    Figure CN119071559A_ABST
Patent Text Reader

Abstract

The invention relates to a video generation method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a target video, extracting an original video frame and an original subtitle text of the target video, generating a new subtitle text through a preset model based on the original subtitle text, generating a commentary audio according to the new subtitle text, adding the new subtitle text to the original video frame, generating a new video frame, and sending the new video frame to the target video. And generating a new video based on the new caption text, the commentary audio and the new video frame. According to the scheme provided by the invention, through a series of automatic steps, video variants with different explanation styles and different timbre explanation sounds from the original video can be efficiently generated, so that diversified content creation requirements of users are met.
Need to check novelty before this filing date? Find Prior Art