Automatic generation of transformations of formatted templates using deep learning modeling

A system comprising:

• at least one processor;
• and
• a memory, operatively connected with the at least one processor;
• storing computer-executable instructions that, when executed by the at least one processor, causes the at least one processor to execute a method that comprises:
• extracting feature data for objects of a first slide-based template and feature data for visual style attributes of the first slide-based template, wherein the feature data for the objects comprises shape information for the objects, and wherein the first slide-based template is associated with a first presentation theme providing a first set of visual style attributes for the objects of the first slide-based template;
• applying trained artificial intelligence (AI) processing, configured for generation of transformations of slide-based templates, to generate a transformation of the first slide-based template, wherein the applying of the trained AI processing executes processing operations that comprise:
• encoding the feature data for the objects of the first slide-based template as a latent vector providing a distributed representation of the feature data,
• propagating the latent vector to a first decoder network selected from a plurality of decoder networks, wherein each of the plurality of decoder networks is trained based on training data comprising data for slide-based templates having one of a plurality of different presentation themes, wherein the first decoder network is trained based on training data comprising data for slide-based templates having a second presentation theme of the plurality of different presentation themes, wherein the second presentation theme is different from the first presentation theme and provides a second set of visual style attributes for objects thereof, and
• automatically generating a transformed template for the first slide-based template based on analysis of the latent vector using the first decoder network, wherein the transformed template comprises:
• one or more transformations of the objects of the first slide-based template and a style transformation modifying one or more visual style attributes of the first set of visual style attributes;
• and
• storing the transformed template for subsequent presentation through a productivity service.

A method comprising:

• extracting first feature data for a first set of formatted templates associated with a slide-based presentation, wherein the first set of formatted templates are part of a first presentation theme of a plurality of different presentation themes providing a first set of visual style attributes for objects of the first set of formatted templates;
• extracting second feature data for a second set of formatted templates associated with a slide-based presentation, wherein the second set of formatted templates are part of a second presentation theme of the plurality of different presentation themes providing a second set of visual style attributes for objects of the second set of formatted templates;
• applying trained artificial intelligence (AI) processing, configured for generation of transformations of slide-based templates, to generate a transformation of the first set of formatted templates and a transformation of the second set of formatted templates, wherein the applying of the trained AI processing executes processing operations that comprise:
• encoding the first feature data of the first set of formatted templates as a first latent vector providing a distributed representation of the first feature data,
• encoding the second feature data of the second set of formatted templates as a second latent vector providing a distributed representation of the second feature data,
• propagating the first latent vector to a first decoder network selected from a plurality of decoder networks, wherein each of the plurality of decoder networks is trained based on training data comprising data for slide-based templates having one of the plurality of different presentation themes, wherein the first decoder network is trained based on training data comprising data for slide-based templates having the second presentation theme,
• propagating the second latent vector to a second decoder network selected from the plurality of decoder networks, wherein the second decoder network is trained based on training data comprising data for slide-based templates having the first presentation theme,
• automatically generating a transformed set of formatted templates for the first set of formatted templates based on analysis of the first latent vector using the first decoder network, wherein the transformed set of formatted templates comprises:
• one or more transformations of the objects within a slide-based template of the first set of formatted templates and a style transformation modifying one or more visual style attributes of the first set of visual style attributes, and
• automatically generating a transformed set of formatted templates for the second set of formatted templates based on analysis of the second latent vector using the second decoder network, wherein the transformed set of formatted templates for the second set of formatted templates comprises:
• one or more transformations of the objects within a slide-based template of the first set of formatted templates and a style transformation modifying one or more visual style attributes of the first set of visual style attributes;
• and
• storing the transformed set of formatted templates for the first set of formatted templates and the transformed set of formatted templates for the second set of formatted templates.