US 11,917,268 B2
Prediction model training via live stream concept association
Matthew D. Zeiler, Fort Lee, NJ (US); and Daniel Kantor, New York, NY (US)
Assigned to CLARIFAI, INC., New Yory, NY (US)
Filed by Clarifai, Inc., Wilmington, DE (US)
Filed on Jan. 10, 2022, as Appl. No. 17/571,602.
Application 17/571,602 is a continuation of application No. 17/016,457, filed on Sep. 10, 2020, granted, now 11,245,968.
Application 17/016,457 is a continuation of application No. 15/986,239, filed on May 22, 2018, granted, now 10,779,060, issued on Sep. 15, 2020.
Application 15/986,239 is a continuation of application No. 15/717,114, filed on Sep. 27, 2017, granted, now 10,051,344, issued on Aug. 14, 2018.
Claims priority of provisional application 62/400,538, filed on Sep. 27, 2016.
Prior Publication US 2022/0132222 A1, Apr. 28, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/84 (2011.01); H04N 21/2187 (2011.01); H04N 21/482 (2011.01); H04N 21/431 (2011.01); H04N 21/4223 (2011.01); H04N 21/466 (2011.01); H04N 21/278 (2011.01); H04N 21/266 (2011.01); H04N 21/44 (2011.01); H04N 21/80 (2011.01); H04N 21/422 (2011.01); H04N 21/81 (2011.01); H04N 21/231 (2011.01); H04N 21/234 (2011.01); G06F 18/40 (2023.01); G06F 18/2411 (2023.01); G06V 10/764 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)
CPC H04N 21/84 (2013.01) [G06F 18/2411 (2023.01); G06F 18/41 (2023.01); G06V 10/764 (2022.01); G06V 10/7788 (2022.01); G06V 10/82 (2022.01); H04N 21/2187 (2013.01); H04N 21/23109 (2013.01); H04N 21/23418 (2013.01); H04N 21/26603 (2013.01); H04N 21/278 (2013.01); H04N 21/4223 (2013.01); H04N 21/42202 (2013.01); H04N 21/4312 (2013.01); H04N 21/44008 (2013.01); H04N 21/466 (2013.01); H04N 21/4666 (2013.01); H04N 21/482 (2013.01); H04N 21/80 (2013.01); H04N 21/8133 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system that comprises one or more processors programmed with computer program instructions that, when executed, cause the system to:
display, on a user interface, a video stream and a plurality of predicted concepts associated with the video stream, the plurality of predicted concepts generated by a prediction model based on the video stream, and the plurality of predicted concepts include a first set of predicted concepts and a second set of predicted concepts, the first set of predicted concepts being associated with first confidence values equal to or higher than a confidence threshold and the second set of predicted concepts being associated with second confidence values less than the confidence threshold, and the first and second confidence values indicate a confidence level that a particular predicted concept is present in a particular frame of the video stream;
receive, from an input device, a user selection of a concept related to a frame of the video stream, the selected concept being from among the plurality of predicted concepts;
receive, from the input device, a selection of a portion of the frame of the video stream;
determine an association between the selected portion of the frame and the selected concept; and
cause the prediction model to be trained based on the association.