CPC G06N 20/00 (2019.01) [H04L 67/306 (2013.01); H04L 67/535 (2022.05)] | 17 Claims |
1. A method comprising:
receiving, by at least one processor, a user selection by a user of a link to at least one content part of a network resource;
receiving, by the at least one processor, the at least one content part of the network resource returned by a network based on the link;
monitoring, by the at least one processor, user interactions with the at least one content part of the network resource to produce user interaction data associated with the user;
determining, by the at least one processor, at least one user usage parameter based at least in part on the user interaction data;
automatically determining, by the at least one processor, when a value of the at least one user usage parameter exceeds a threshold value, at least one network resource content classification associated with the at least one content part, the network resource, or both, based at least in part on a content classification machine learning model;
wherein the content classification machine learning model classifies the at least one content part, the network resource, or both, into the at least one network resource content classification associated with the user based at least in part on a content similarity to at least one additional content part of at least one existing stored network resource identifier;
automatically generating, by the at least one processor, for the link, at least one stored network resource identifier in a network resource group of a user profile;
wherein the at least one stored network resource identifier comprises a profile link to the at least one content part or the network resource;
wherein the network resource group is associated with the at least one network resource content classification associated with the user;
determining, by the at least one processor, at least one updated user usage parameter based at least in part on at least one record deletion event comprising a deleting of the at least one stored network resource identifier;
training, by the at least one processor, a usage threshold model based on a difference between the at least one updated user usage parameter and the threshold value; and
generating, by the at least one processor, a new threshold value based at least in part on the usage threshold model.
|