US 12,142,161 B2
Systems and methods for providing information incorporating reinforcement-based learning and feedback
Jugoslav Bilic, Richmond (CA); Ivana Bilic, Richmond (CA); Justin Callison, Vancouver (CA); Manuj Aggarwal, Vancouver (CA); Stephen Michaud, Vancouver (CA); Ryan Ogg, Vancouver (CA); Juan Camilo Ramirez, Port Moody (CA); Sarbjit Sarkaria, Richmond (CA); and Jian Zhou, Burnaby (CA)
Assigned to D2L Corporation, Kitchener (CA)
Filed by D2L Corporation, Kitchener (CA)
Filed on Nov. 11, 2021, as Appl. No. 17/524,575.
Application 17/524,575 is a continuation of application No. 16/101,934, filed on Aug. 13, 2018, granted, now 11,195,428.
Application 16/101,934 is a continuation of application No. 14/740,733, filed on Jun. 16, 2015, granted, now 10,249,206, issued on Apr. 2, 2019.
Application 14/740,733 is a continuation of application No. 13/486,923, filed on Jun. 1, 2012, granted, now 9,064,017, issued on Jun. 23, 2015.
Claims priority of provisional application 61/492,246, filed on Jun. 1, 2011.
Prior Publication US 2022/0180763 A1, Jun. 9, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/30 (2019.01); G06F 16/22 (2019.01); G06F 16/23 (2019.01); G06F 16/907 (2019.01); G06F 16/9535 (2019.01); G09B 7/00 (2006.01)
CPC G09B 7/00 (2013.01) [G06F 16/2282 (2019.01); G06F 16/2379 (2019.01); G06F 16/907 (2019.01); G06F 16/9535 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method, implemented by a computer, for feedback-driven provision of information in relation to a plurality of information resources, the method comprising:
obtaining a feedback metric related to interaction of a first user with the at least one information resource; and providing output information comprising one or more recommended actions related to the at least one information resource based at least in part on the feedback metric and a mapping of the at least one information resource, wherein providing one or more recommended actions comprises: filtering a state-table records to obtain a subset of the state-table records whose state-actions pairs include states comprising historical actions which match a current state of particular user, the current state of the particular user comprising historical actions of the particular user in relation to the information resources; and selecting at least one of the one or more recommended actions to be an action corresponding to one of the subset of the state-table records having the highest value.