US 2021/0200942 A1Published application

Automatic generation of alternative content layouts

AssigneeMicrosoft Technology Licensing, LLC

InventorsKatarina JOVANOVIC, Andreja ILIC, Umachandra CHIKKAREDDY, Dragan SLAVESKI, Igor ILIC, Marko Zoran DJOKIC, Sladjan KANTAR, Vladimir ILIC, Damjan DAKIC

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A system is configured to automatically enhance user content by dynamically generating alternative layouts given an original layout of the user content. The alternative layouts are generated based on determined roles for a number of different content elements on a canvas and/or detected semantic relationships between content elements. Once the alternative layouts are generated, the system can evaluate the alternative layouts and assign a score to each of the alternative layouts. The system can then identify recommended alternative layouts that are suitable for a particular purpose (e.g., a professional presentation, a teaching lesson, etc.), and provide the recommended alternative layouts for display on a device of a user.

Claims20

Dependent claims

A computer-implemented method comprising:

analyzing, by a machine learning classifier, original positions of a plurality of content elements in an original layout of a slide to determine a creator intended role for each of the plurality of content elements;
detecting, based at least in part on the creator intended role for each of the plurality of content elements, a semantic relationship between a first content element of the plurality of content elements and a second content element of the plurality of elements;
generating a plurality of alternative layouts for the plurality of content elements on the slide, wherein each of the plurality of alternative layouts:
preserves the semantic relationship between the first content element and the second content element;
and
re-arranges the plurality of content elements by changing a position of at least one content element;
creating a ranking of the plurality of alternative layouts based on a score for each of the plurality of alternative layouts;
using the ranking to select one or more recommended alternative layouts from the plurality of alternative layouts;
and
providing the one or more recommended alternative layouts for display on a device.

7 more elements

A system comprising:

one or more processors;
and
computer-readable media storing instructions, that when executed by the one or more processors, cause the system to:
analyze, by a machine learning classifier, original positions of a plurality of content elements in an original layout to determine a creator intended role for each of the plurality of content elements;
detect, based at least in part on the creator intended role for each of the plurality of content elements, a semantic relationship between a first content element of the plurality of content elements and a second content element of the plurality of elements;
generate a plurality of alternative layouts for the plurality of content elements, wherein each of the plurality of alternative layouts:
preserves the semantic relationship between the first content element and the second content element;
and
re-arranges the plurality of content elements by changing a position of at least one content element;
and
provide the plurality of alternative layouts for display on a device.

8 more elements

Dependencies are inferred from the claim text.