US 11,769,006 B2Granted

Parsing and reflowing infographics using structured lists and groups

AssigneeAdobe Inc.

InventorsSumit Shekhar, Zoya Bylinskii, Tushar Gurjar, Ritwick Chaudhry, Ayush Goyal

Life of this patent

Estimating the term…

Loading patent…

Abstract

This disclosure describes methods, systems, and non-transitory computer readable media for automatically parsing infographics into segments corresponding to structured groups or lists and displaying the identified segments or reflowing the segments into various computing tasks. For example, the disclosed systems may utilize a novel infographic grouping taxonomy and annotation system to group elements within infographics. The disclosed systems can train and apply a machine-learning-detection model to generate infographic segments according to the infographic grouping taxonomy. By generating infographic segments, the disclosed systems can facilitate computing tasks, such as converting infographics into digital presentation graphics (e.g., slide carousels), reflow the infographic into query-and-response models, perform search functions, or other computational tasks.

Claims20

Dependent claims

A non-transitory computer readable medium storing executable instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

receiving an infographic comprising text elements and graphic elements;
accessing a machine-learning-detection model trained with annotation labels according to an infographic grouping taxonomy;
generating, from the infographic utilizing the machine-learning-detection model, candidate infographic segments;
generating, utilizing the machine-learning-detection model, segment-confidence values indicating a probability that particular candidate infographic segments comprise discrete components from the infographic corresponding to a list or a group, the discrete components each comprising one or more of related text elements and graphic elements according to the infographic grouping taxonomy;
based on the segment-confidence values, selecting, from the candidate infographic segments utilizing the machine-learning-detection model, infographic segments comprising one or more of related text elements and graphic elements together as a discrete component, the infographic segments corresponding to particular lists or particular groups within the infographic;
and
providing the infographic segments for display by the processing device.

4 more elements

A system comprising:

a memory component comprising a machine-learning-detection model trained with annotation labels according to an infographic grouping taxonomy, and an infographic including text elements and graphic elements;
and
one or more processing devices coupled to the memory component, the one or more processing devices to perform operations comprising:
partitioning the infographic into overlapping infographic frames;
generating, from the overlapping infographic frames utilizing the machine-learning-detection model, candidate infographic segments;
generating, utilizing the machine-learning-detection model, segment-confidence values indicating probabilities that particular candidate infographic segments from the candidate infographic segments comprise discrete components from the infographic corresponding to a list or a group, the discrete components each comprising one or more of related text elements and graphic elements according to the infographic grouping taxonomy;
based on the segment-confidence values, selecting, from the candidate infographic segments utilizing the machine-learning-detection model, infographic segments comprising one or more of related text elements and graphic elements together as a discrete component, the infographic segments corresponding to particular lists or particular groups within the infographic;
and
converting, for display on a graphical user interface of a client device, the infographic segments into digital presentation graphics.

6 more elements

Dependencies are inferred from the claim text.