Generating visual data stories

Patent metadata

Field	Value
Publication number	US-2022237228-A1
Application number	US-202117161406-A
Country	US
Kind code	A1
Filing date	Jan 28, 2021
Priority date	Jan 28, 2021
Publication date	Jul 28, 2022
Grant date	—

Abstract

This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that intelligently and automatically analyze input data and generate visual data stories depicting graphical visualizations from data insights determined from the input data. For example, the disclosed systems automatically extract data insights utilizing an in-depth statistical analysis of dataset groups from data-attribute categories within the input data. Based on the data insights, the disclosed systems can automatically generate exportable visual data stories to visualize the data insights, provide textual or audio-based natural language summaries of the data insights, and animate such data insights in videos. In some embodiments, the disclosed systems generate a visual-data-story graph comprising nodes representing visual data stories and edges representing similarities between the visual data stories. Based on the visual-data-story graph, the disclosed systems can select a relevant visual data story to display on a graphical user interface.

First claim

1 . A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:
receive, from a client device, a dataset organized according to data-attribute categories comprising dataset groups; determine data insights across different dataset groups utilizing a statistical analysis that compares data-attribute values corresponding to the dataset groups; generate visual data stories comprising graphical visualizations and natural language summaries of the data insights; determine aggregate pairwise distances between data-story properties of visual-data-story pairs from the visual data stories by determining a combination of at least two or more of data-attribute distances, grouping-attribute distances, group-name distances, or group-insight distances between the visual-data-story pairs; generate a visual-data-story graph comprising nodes for the visual data stories and edges representing the aggregate pairwise distances between the data-story properties of the visual-data-story pairs; provide, for display within a graphical user interface of the client device, a set of visual data stories selected from among the visual data stories utilizing the visual-data-story graph; and generate a stitched-visual-data story for an exportable file based on receiving, from the client device, a selection of a combination of visual data stories from the set of visual data stories.

2 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to determine the data insights by:
determining energy ratios from portions of particular data-attribute values organized in a time series for a particular dataset group; or determining a linear data trend for the time series utilizing a linear regression on the time series for the particular dataset group.

3 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine the data insights by determining a first data trend between a first dataset group and a second dataset group and a second data trend between the first dataset group and a third dataset group; determine that the first data trend and the second data trend follow a similar pattern; and based on determining the similar pattern, provide, for display within the graphical user interface of the client device, a visual data story from the set of visual data stories to visually indicate the similar pattern between the first data trend and the second data trend.

4 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to determine the data insights across the different dataset groups by comparing the data-attribute values corresponding to the dataset groups to determine one or more of derived data values, data distributions, data extremums, or data minimums from the data-attribute values corresponding to the dataset groups.

5 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine the data-attribute distances by determining distances between particular data-attribute values for the particular dataset groups in pairs of visual data stories; determine the grouping-attribute distances by determining distances between particular data-attribute categories for the particular dataset groups in the pairs of visual data stories; determine the group-name distances by determining distances among group names for the particular dataset groups in the pairs of visual data stories; or determining the group-insight distances by determining distances between particular data insights for the particular dataset groups in the pairs of visual data stories.

6 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to combine the combination of visual-data stories utilizing a minimum spanning tree algorithm.

7 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to provide the stitched-visual-data story as a video file.

8 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to provide, for display within the graphical user interface of the client device, a visual data story, from the set of visual data stories, comprising a highlighted portion associated with a time segment of the visual data story, the highlighted portion indicating a specific data insight corresponding to the time segment.

9 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
select the set of visual data stories to display within the graphical user interface by utilizing the aggregate pairwise distances between the data-story properties of the visual-data-story pairs data: receive a user selection to bookmark one or more visual data stories from the set of visual data stories to determine the combination of visual data stories; and generate the stitched-visual-data story from the combination of visual data stories based on receiving the user selection to bookmark the one or more visual data stories.

10 . The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computing device to provide, for display within the graphical user interface of the client device, the set of visual data stories by:
identifying a visual data story utilizing the visual-data-story graph; identifying a similar visual data story to the visual data story utilizing the visual-data-story graph; and providing, for display within the graphical user interface of the client device, a selectable option for the similar visual data story.

11 . A system comprising:
one or more memory devices comprising tabular data recorded over a time period and organized according to data-attribute categories comprising dataset groups and one or more additional data-attribute values that correspond to the dataset groups; and one or more processors configured to cause the system to: determine data insights across different dataset groups utilizing a statistical analysis that compares data-attribute values corresponding to the dataset groups; based on the data insights, generate visual data stories that compare particular dataset groups and comprise graphical visualizations and natural language summaries of particular data insights across the particular dataset groups; determine aggregate pairwise distances between data-story properties of visual-data-story pairs from the visual data stories by determining a combination of at least two or more of data-attribute distances, grouping-attribute distances, group-name distances, or group-insight distances between the visual-data-story pairs; generate a visual-data-story graph comprising nodes for the visual data stories and edges representing the aggregate pairwise distances between data-story properties of the visual-data-story pairs; provide, for display within a graphical user interface of a client device, a set of visual data stories selected from among the visual data storie

Assignees

• Adobe Inc

Inventors

• Xu Shenyu
• Koh Eunyee
• Du Fan
• Lee Tak Yeon
• Lee Sana Malik
• Rossi Ryan

Classifications

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F16/2474 Primary

  Sequence data queries, e.g. querying versioned data · CPC title

• G06F40/216

  using statistical methods · CPC title