IP Library Granted Patent US 12713107
Granted Patent B2
US 12713107 · App. 18/723,804 · Granted Aug 18, 2026

Music point-based video generation method and apparatus, device, and storage medium

Inventors: Weibo Gong (Beijing, CN); Xiaojie Jin (Los Angeles, CA); Xiaohui Shen (Los Angeles, CA)
Assignee: Lemon Inc.
H04N21/8113G10H1/0008H04N21/439H04N21/44G10H2210/076
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12713107
App. No.
18/723,804
Granted
Aug 18, 2026
Kind
B2
Abstract

The present disclosure provides a video generation method based on music beats, a video generation apparatus based on music beats, an electronic device and a computer-readable storage medium. The method includes: acquiring a plurality of video objects and audio information respectively; determining a plurality of initial music beats in the audio information and characteristic information of each initial music beat, in which the characteristic information at least includes a sound intensity of each initial music beat and time of each initial music beat in the audio information; according to the characteristic information, selecting a target music beat from the plurality of initial music beats; and generating a target video according to the target music beat and the plurality of video objects.

Claims (65)

1 . A video generation method based on music beats, comprising:

acquiring a plurality of video objects and audio information respectively;

determining a plurality of initial music beats in the audio information and characteristic information of each initial music beat, wherein the characteristic information at least comprises a sound intensity of each initial music beat and time of each initial music beat in the audio information;

determining a score of each initial music beat among the plurality of initial music beats based on a duration between two adjacent initial music beats according to the time of each initial music beat in the audio information and a preset weight of each initial music beat;

selecting a music beat from the plurality of initial music beats based on the scores of the plurality of initial music beats; and

generating a video by adding a rendering effect to one of the plurality of video objects corresponding to time where the selected music beat is located, wherein the rendering effect comprises an animation, an effect, or a transition.

2 . The method according to claim 1 , wherein the selecting the music beat from the plurality of initial music beats comprises:

judging whether the sound intensity of each initial music beat is greater than a first preset value;

determining the music beat according to a first music beat whose sound intensity is greater than the first preset value.

3 . The method according to claim 2 , wherein the determining the music beat according to a first music beat whose sound intensity is greater than the first preset value comprises:

for any two adjacent first music beats, acquiring a first duration between the two adjacent first music beats according to time corresponding to the first music beat;

if the first duration is less than a first preset duration, deleting a first music beat with a low priority among the two adjacent first music beats to obtain remaining at least two second music beats; and determining the music beat according to the at least two second music beats.

4 . The method according to claim 1 , wherein the plurality of initial music beats comprise at least two music beats of the following: a downbeat beat, a voice beat, a music phrase beat, a music paragraph beat, a sound effect beat and a chorus beat.

5 . The method according to claim 3 , wherein the deleting a first music beat with a low priority among the two adjacent first music beats comprises:

according to a preset priority order, deleting the first music beat with the low priority among the two adjacent first music beats;

wherein the preset priority order from top to bottom is a chorus beat, a strong sound beat, a music phrase beat, a music paragraph beat, a downbeat beat, a weak sound beat, a voice beat and a preset beat.

6 . The method according to claim 1 , wherein the determining the score of each initial music beat comprises:

determining the score of each initial music beat according to the time of each initial music beat in the audio information.

7 . The method according to claim 1 , wherein the method further comprises:

deleting an initial music beat with the score less than a second preset value to obtain a remaining third music beat; and

according to time of the third music beat in the audio information, redetermining a score of each third music beat, and determining the music beat according to the score of the third music beat.

8 . The method according to claim 6 , wherein the determining the score of each initial music beat according to the time of each initial music beat in the audio information comprises:

determining the duration between the two adjacent initial music beats according to the time of each initial music beat in the audio information, and determining a first score of each initial music beat according to the duration;

determining a second score of each initial music beat according to the preset weight of each initial music beat;

determining a third score of each initial music beat according to the time of each initial music beat in the audio information and starting time and ending time of the audio information;

determining the score of each initial music beat according to the first score, the second score and the third score.

9 . The method according to claim 8 , wherein the determining the first score of each initial music beat according to the second duration comprises:

determining a third duration according to a total duration of the audio information and a number of the plurality of video objects;

determining an absolute value of a difference between the second duration and the third duration as the first score.

10 . The method according to claim 8 , wherein the determining the third score of each initial music beat according to the time of each initial music beat in the audio information and starting time and ending time of the audio information comprises:

determining a fourth score according to the time of each initial music beat in the audio information, the starting time of the audio information and a second preset duration;

determining a fifth score according to the time of each initial music beat in the audio information, the ending time of the audio information and the second preset duration;

determining the third score according to the fourth score and the fifth score.

11 . The method according to claim 8 , further comprising:

according to a preset priority order, setting a corresponding weight for each initial music beat, wherein the weight is at least partially related to a priority of the music beat.

12 . The method according to claim 1 , wherein generating the video comprises:

adding the audio information to an audio track of the plurality of video objects to obtain a video to be processed;

in the video to be processed, adding the rendering effect to the video object corresponding to the time where the selected music beat is located to obtain the video.

13 . The method according to claim 1 , wherein the determining a plurality of initial music beats in the audio information and characteristic information of each initial music beat comprises:

inputting the audio information into an audio characteristic analysis model to obtain the plurality of initial music beats in the audio information and the characteristic information of each initial music beat.

14 . An electronic device, comprising: a processor and a memory communicatively connected to the processor;

wherein computer-executable instructions are stored on the memory;

the computer-executable instructions stored in the memory are executed by the processor, to perform operations, the operations comprising:

acquiring a plurality of video objects and audio information respectively;

determining a score of each initial music beat among the plurality of initial music beats based on a duration between two adjacent initial music beats according to the time of each initial music beat in the audio information and a preset weight of each initial music beat;

selecting a music beat from the plurality of initial music beats based on the scores of the plurality of initial music beats; and

generating a video by adding a rendering effect to one of the plurality of video objects corresponding to time where the selected music beat is located, wherein the rendering effect comprises an animation, an effect, or a transition.

15 . A non-transient computer-readable storage medium, storing computer-executable instructions thereon, wherein the computer-executable instructions, when executed by a processor, perform operations, the operations comprising:

acquiring a plurality of video objects and audio information respectively;

determining a plurality of initial music beats in the audio information and characteristic information of each initial music beat, wherein the characteristic information at least comprises a sound intensity of each initial music beat and time of each initial music beat in the audio information;

determining a score of each initial music beat among the plurality of initial music beats based on a duration between two adjacent initial music beats according to the time of each initial music beat in the audio information and a preset weight of each initial music beat;

selecting a music beat from the plurality of initial music beats based on the scores of the plurality of initial music beats; and

generating a video by adding a rendering effect to one of the plurality of video objects corresponding to time where the selected music beat is located, wherein the rendering effect comprises an animation, an effect, or a transition.

16 . The electronic device according to claim 14 , wherein the selecting the music beat from the plurality of initial music beats comprises:

judging whether the sound intensity of each initial music beat is greater than a first preset value;

determining the music beat according to a first music beat whose sound intensity is greater than the first preset value.

17 . The electronic device according to claim 16 , wherein the determining the music beat according to a first music beat whose sound intensity is greater than the first preset value comprises:

for any two adjacent first music beats, acquiring a first duration between the two adjacent first music beats according to time corresponding to the first music beat;

if the first duration is less than a first preset duration, deleting a first music beat with a low priority among the two adjacent first music beats to obtain remaining at least two second music beats; and determining the music beat according to the at least two second music beats.

18 . The electronic device according to claim 14 , wherein the plurality of initial music beats comprise at least two music beats of the following: a downbeat beat, a voice beat, a music phrase beat, a music paragraph beat, a sound effect beat and a chorus beat.

19 . The electronic device according to claim 17 , wherein the deleting a first music beat with a low priority among the two adjacent first music beats comprises:

according to a preset priority order, deleting the first music beat with the low priority among the two adjacent first music beats;

wherein the preset priority order from top to bottom is a chorus beat, a strong sound beat, a music phrase beat, a music paragraph beat, a downbeat beat, a weak sound beat, a voice beat and a preset beat.

20 . The electronic device according to claim 14 , wherein the determining the score of each initial music beat comprises:

determining the score of each initial music beat according to the time of each initial music beat in the audio information.