US 12,136,442 B1
System, method, and computer program for providing an interactive platform for video generation in which users are able to interact with machine-learning asset enhancement modules via proxy elements in a video production workspace
Matthew Harney, Bangkok (TH); and Gary Alan Lipkowitz, Brisbane, CA (US)
Assigned to GoAnimate, Inc., San Mateo, CA (US)
Filed by GoAnimate, Inc., San Mateo, CA (US)
Filed on Feb. 10, 2023, as Appl. No. 18/108,393.
Claims priority of provisional application 63/433,403, filed on Dec. 16, 2022.
Int. Cl. G11B 27/036 (2006.01)
CPC G11B 27/036 (2013.01) 18 Claims
OG exemplary drawing
 
1. A method, performed by a computer system, for providing an interactive video-generation platform through which a user is able to guide the output of machine-learning modules to produce assets for a video, the method comprising:
providing a multimedia video production workspace for creating videos;
enabling a user to add a plurality of multimedia assets for a video to the multimedia workspace;
providing an asset enhancement platform comprising a plurality of machine-learning modules trained to generate assets for a video in response to receiving an input asset, system-defined attributes of the input asset, and user-defined attributes for an output asset; and
enabling a user to trigger and guide the output of the asset enhancement platform by performing the following:
enabling a user to select an asset in the video production workspace and to enter an asset enhancement request for the selected asset, wherein the selected asset can be enhanced independent of other assets in the video and wherein any asset in the multimedia workspace may serve as a proxy for a machine-generated asset;
receiving an asset enhancement request for a selected asset;
identifying a location and a time window in the video associated with the selected asset;
identifying one or more user-defined attributes for the asset enhancement request;
identifying one or more system-defined attributes of the selected asset;
identifying one or more machine learning modules in the asset enhancement platform to use to process the asset enhancement request;
using the identified machine-learning module(s) to obtain a machine-generated asset having the user-defined attributes, wherein the selected asset, the user-defined attributes, and the system-defined attributes are inputted into the identified asset enhancement module(s);
linking the machine-generated asset to the selected asset in the visual production workspace;
determining whether to visually replace the selected asset with the machine-generated asset in the workspace;
in response to determining to visually replace the proxy asset with machine-generated asset, visually replacing the selected asset with the machine-generated asset, wherein the machine-generated asset is displayed in the same location as the selected asset within the video production workspace and during the same time window as the selected asset; and
in response to determining to add the machine-generated asset to the video production workspace without visually replacing the selected asset, making the machine-generated asset perceptible to a user in the video production workspace in conjunction with the selected asset and during the same time window as the selected asset.