| CPC G06T 11/00 (2013.01) [G06F 3/0481 (2013.01); G06F 3/04842 (2013.01); G06T 2200/24 (2013.01)] | 20 Claims |

|
1. A method, comprising:
obtaining a document including a digital canvas;
identifying a plurality of layers associated with the digital canvas, wherein each layer of the plurality of layers organizes content in the digital canvas based on a semantic knowledge of the content and a semantic knowledge of content of one or more other layers of the digital canvas;
determining a plurality of semantic labels associated with the plurality of layers;
determining a semantic layer hierarchy of the plurality of layers;
generating, using one or more machine learning models, content of the digital canvas, wherein the content is a digital object depicted in the digital canvas and associated with a content type and a location in the digital canvas;
adding the generated content to a new layer of the digital canvas;
updating the semantic layer hierarchy by adding the new layer to the semantic layer hierarchy; and
organizing the plurality of layers based at least on the semantic layer hierarchy.
|