US 11,755,676 B2
Systems and methods for generating real-time recommendations
Douglas Sweet, Sunnyvale, CA (US); Paul Davis, Saratoga, CA (US); and Richard Chandler, Santa Cruz, CA (US)
Assigned to Architecture Technology Corporation, Minneapolis, MN (US)
Filed by Architecture Technology Corporation, Minneapolis, MN (US)
Filed on Aug. 11, 2022, as Appl. No. 17/885,794.
Application 17/885,794 is a continuation of application No. 17/113,165, filed on Dec. 7, 2020, granted, now 11,449,553.
Application 17/113,165 is a continuation of application No. 15/947,071, filed on Apr. 6, 2018, granted, now 10,866,989, issued on Dec. 15, 2020.
Prior Publication US 2022/0382814 A1, Dec. 1, 2022
Int. Cl. G06F 7/00 (2006.01); G06F 16/9537 (2019.01); G06F 16/901 (2019.01); G06F 16/31 (2019.01); G06F 18/2113 (2023.01); G06F 18/243 (2023.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01); G06V 20/40 (2022.01)
CPC G06F 16/9537 (2019.01) [G06F 16/313 (2019.01); G06F 16/9027 (2019.01); G06F 18/2113 (2023.01); G06F 18/24323 (2023.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01); G06V 20/40 (2022.01)] 22 Claims
OG exemplary drawing
 
1. A real-time recommendation system, comprising:
a processor; and
a non-transitory, computer-readable storage medium having encoded thereon instructions that when executed by the processor, cause the processor to:
implement a feature detection/selection object, a feature install object, and one or more recommendation objects, a recommendation object comprising one or more recommendation algorithms,
receive detected feature data extracted from a data record by the feature detection/selection object,
accept one or more detected features from the detected feature data,
apply accepted features to one or more feature install algorithms of one or more feature install objects,
determine a class of one or more applied, accepted features,
abstract the one or more applied, accepted features according to a determined class,
modify a recommender algorithm according to one or more abstracted features,
save modified recommender algorithms, and
apply the accepted features to a saved, modified recommender algorithm, the real-time recommendation system adapted to issue one or more item recommendations according to the saved, modified recommender algorithm.