US 11,756,245 B2
Machine learning to generate and evaluate visualizations
Saurabh Abhyankar, McLean, VA (US); Glenn Boysko, Vienna, VA (US); Scott Rigney, Vienna, VA (US); and Timothy Lang, Vienna, VA (US)
Assigned to MicroStrategy Incorporated, Vienna, VA (US)
Filed by MicroStrategy Incorporated, Vienna, VA (US)
Filed on Nov. 23, 2021, as Appl. No. 17/534,053.
Application 17/534,053 is a continuation of application No. 16/731,778, filed on Dec. 31, 2019, granted, now 11,195,050.
Claims priority of provisional application 62/801,320, filed on Feb. 5, 2019.
Prior Publication US 2022/0156512 A1, May 19, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/62 (2022.01); G06N 20/00 (2019.01); G06N 5/04 (2023.01); G06T 11/20 (2006.01); G06T 11/60 (2006.01); G06F 18/40 (2023.01); G06F 18/23 (2023.01); G06F 18/214 (2023.01); G06F 18/2411 (2023.01)
CPC G06T 11/206 (2013.01) [G06F 18/2148 (2023.01); G06F 18/23 (2023.01); G06F 18/2411 (2023.01); G06F 18/40 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06T 11/60 (2013.01); G06T 2200/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by one or more computers, the method comprising:
receiving, by the one or more computers, data indicating a user selection of a portion of a dataset:
determining, by the one or more computers, properties of the selected portion of the dataset;
selecting, by the one or more computers, one or more visualizations for the user-selected portion of the dataset, wherein the one or more visualizations are selected based on evaluation of visualization specifications using a machine learning model trained based on user feedback for visualizations for multiple datasets; and
providing, by the one or more computers, visualization data for display, the visualization data corresponding to the one or more visualizations selected based on output of the machine learning model.