US 12,316,891 B2
Video generating method and apparatus, electronic device, and readable storage medium
Yufan Xue, Beijing (CN); Jie He, Beijing (CN); Ye Yuan, Los Angeles, CA (US); Xiaojie Li, Los Angeles, CA (US); and Yue Gao, Beijing (CN)
Assigned to Lemon Inc., Grand Cayman (KY)
Filed by Lemon Inc., Grand Cayman (KY)
Filed on Jun. 27, 2024, as Appl. No. 18/757,292.
Application 18/757,292 is a continuation of application No. PCT/SG2022/050946, filed on Dec. 29, 2022.
Claims priority of application No. 202111672927.6 (CN), filed on Dec. 31, 2021.
Prior Publication US 2024/0348846 A1, Oct. 17, 2024
Int. Cl. H04N 21/23 (2011.01); H04N 21/234 (2011.01); H04N 21/2368 (2011.01); H04N 21/439 (2011.01); H04N 21/81 (2011.01)
CPC H04N 21/2368 (2013.01) [H04N 21/23418 (2013.01); H04N 21/23424 (2013.01); H04N 21/4394 (2013.01); H04N 21/8113 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A video generating method, comprising:
acquiring a plurality of video materials from an initial video material collection which comprises user-related videos;
acquiring a target audio material serving as background music;
for each of the video materials, performing image feature extraction on video frames of the video material respectively, and performing segmentation processing according to image feature information corresponding to the video frames of the video material respectively to acquire a target video segment corresponding to the video material;
merging the target video segment corresponding to each of the video materials respectively and the target audio material to generate a target video; the target video comprises a plurality of video segments which are obtained based on the plurality of target video segments respectively; the plurality of video segments in the target video are played in order of post time, and time lengths of the plurality of video segments are matched with time lengths of corresponding musical phrases in the target audio material,
wherein, the acquiring a target audio material serving as background music comprises:
determining the target audio material according to an audio material, in which time length of each musical phrase comprised in a particular audio segment of the audio material meets a preset time length condition, in a second candidate audio material collection; and
if there is no audio material, in which the time length of the musical phrase in the particular audio segment meets a preset time length condition, in the second candidate audio material collection, matching with an audio feature corresponding to each of the audio materials in a pre-assigned audio material collection respectively according to preference of a user, and if the matching is successful, determining the target audio material according to the successfully matched audio material.