| CPC G06F 16/9024 (2019.01) [G06F 16/24578 (2019.01); G06F 16/435 (2019.01); G06F 16/958 (2019.01); G06F 18/23 (2023.01); G06Q 30/0201 (2013.01); G06F 16/487 (2019.01)] | 20 Claims |
|
1. A computer-implemented method, comprising:
determining, for each collection of a plurality of collections, a respective plurality of media objects that are associated with the collection;
determining a diversity score for each collection based at least in part on the respective plurality of media objects;
determining, based at least in part on the diversity scores, a first sub-plurality of collections from the plurality of collections;
forming a graph that includes a plurality of nodes representing the first sub-plurality of collections and media objects associated with the first sub-plurality of collections;
determining a target node in the plurality of nodes;
determining a cluster that includes a first sub-plurality of nodes of the plurality of nodes and the target node;
initiating a first plurality of random walks through the graph, wherein at least one node in the cluster is visited by at least one random walk of the first plurality of random walks;
determining, for the target node, a target node visit count based at least in part on a number of times the target node or a node of the first sub-plurality of nodes is visited by a random walk of the first plurality of random walks; and
determining, based at least in part on the target node visit count, a recommendation that indicates at least one node of the plurality of nodes.
|