US 11,960,553 B1
Unsupervised user segment discovery system
Mohammad Reza Loghmani, Paris (FR); and Mouad Antari, Paris (FR)
Assigned to Content Square SAS, Paris (FR)
Filed by Content Square SAS, Paris (FR)
Filed on Oct. 25, 2023, as Appl. No. 18/383,534.
Application 18/383,534 is a continuation in part of application No. 18/210,206, filed on Jun. 15, 2023.
Application 18/210,206 is a continuation of application No. 18/131,173, filed on Apr. 5, 2023, abandoned.
Application 18/131,173 is a continuation of application No. 17/977,392, filed on Oct. 31, 2022, granted, now 11,625,442.
Int. Cl. G06F 16/951 (2019.01); G06F 16/904 (2019.01); G06F 16/906 (2019.01); G06F 40/30 (2020.01)
CPC G06F 16/951 (2019.01) [G06F 16/904 (2019.01); G06F 16/906 (2019.01); G06F 40/30 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
generating, for each of a first plurality of sessions, a session representation indicating an order through which a user navigated through a plurality of webpages during the session;
generating a plurality of clusters by clustering the session representations based on similarity between session representations, the plurality of clusters comprising an optimal number of clusters based on key performance indicators corresponding to each cluster of the plurality of clusters;
generating, for each of a second plurality of sessions, a session representation indicating an order through which a user navigated through a plurality of webpages during the session;
determining a medoid of each of the plurality of clusters; and
for each session representation generated for each of the second plurality of sessions, performing operations comprising:
computing a distance between the session representation and each medoid to determine a nearest medoid; and
assigning the session representation to a cluster associated with the nearest medoid.