US 12,423,721 B2
Machine-learned database interaction model
Kirill Klimuk, San Mateo, CA (US); Roman E. Zubenko, San Francisco, CA (US); and Sara A. Berry, San Francisco, CA (US)
Assigned to ZenPayroll, Inc., San Francisco, CA (US)
Filed by ZenPayroll, Inc., San Francisco, CA (US)
Filed on Apr. 20, 2024, as Appl. No. 18/641,330.
Application 18/641,330 is a continuation of application No. 17/315,988, filed on May 10, 2021, granted, now 11,995,668.
Prior Publication US 2024/0273560 A1, Aug. 15, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0202 (2023.01); G06F 16/28 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/0202 (2013.01) [G06F 16/288 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
8. A method comprising:
training a machine-learned model using entity characteristics and interactions associated with a content item, the machine-learned model configured to identify additional account holder entities that, if presented with the content item, are most likely to interact with the content item;
causing display of the content item to a subset of account holder entities identified using the trained machine-learned model within an interface displayed by devices associated with the subset of account holder entities, the content item including an interface element that, when selected or interacted with, enables an account holder entity to interact with the content item;
receiving one or more interactions from an account holder entity with the displayed content item;
updating the training set of information to additionally include the received one or more interactions and associated labels indicating for each of the received interactions that the interaction is a positive interaction or a negative interaction; and
updating the machine-learned model by retraining the machine-learned model using the updated training set of information.