US 11,893,592 B2
Incentivized neural network training and assurance processes
Garry Anthony Smith, Sydney (AU); Zachary Oakes, Kochi (JP); and Steven Dennis Flinn, Sugar Land, TX (US)
Assigned to Revealit Corporation, Seattle, WA (US)
Filed by Revealit Corporation, Seattle, WA (US)
Filed on Jan. 20, 2023, as Appl. No. 18/099,619.
Application 18/099,619 is a continuation of application No. 17/014,115, filed on Sep. 8, 2020, granted, now 11,580,869.
Claims priority of provisional application 62/904,015, filed on Sep. 23, 2019.
Prior Publication US 2023/0153836 A1, May 18, 2023
Int. Cl. G06V 20/40 (2022.01); G06V 10/774 (2022.01); G06V 10/20 (2022.01); G06Q 30/02 (2023.01); G09B 5/06 (2006.01); G06N 3/02 (2006.01); G06T 19/00 (2011.01); G06V 20/20 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 10/422 (2022.01)
CPC G06Q 30/02 (2013.01) [G06N 3/02 (2013.01); G06T 19/006 (2013.01); G06V 10/774 (2022.01); G06V 10/7788 (2022.01); G06V 10/82 (2022.01); G06V 20/20 (2022.01); G06V 20/40 (2022.01); G06V 20/41 (2022.01); G09B 5/065 (2013.01); G06V 10/255 (2022.01); G06V 10/422 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
providing to an object miner within an object mining user interface a first video stream comprising a first sequence of images, wherein the object mining user interface enables the object miner to identify at least one object in the first sequence of images within a region of pixels comprising a plurality of spatial dimensions;
providing to the object miner an incentive in exchange for identifying the at least one object within the first video stream;
receiving from the object miner an identification of the at least one object within the first sequence of images;
training a computer-implemented neural network on a training set that includes the at least one object that is identified;
applying the trained neural network to identify an object representation within a second video stream in response to a user interaction with the object representation, wherein the object representation is a representation of the at least one object that is identified; and
providing to the object miner a compensation in accordance with the user interaction with the representation of the at least one object and the incentive.