US 12,356,220 B2
Telecommunications network predictions based on machine learning using aggregated network key performance indicators
Hui-Lin Chang, Brambleton, VA (US); Lance Paul Lukens, Templeton, CA (US); Shawn Derek Wallace, Charles Town, WV (US); Farhana Sharmin Munnee, Herndon, VA (US); and Daqi Li, Overland Park, KS (US)
Assigned to T-MOBILE INNOVATIONS LLC, Overland Park, KS (US)
Filed by T-Mobile Innovations LLC, Overland Park, KS (US)
Filed on Dec. 29, 2021, as Appl. No. 17/565,126.
Prior Publication US 2023/0209367 A1, Jun. 29, 2023
Int. Cl. H04W 24/02 (2009.01); G06N 20/00 (2019.01)
CPC H04W 24/02 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving network key performance indicators (KPIs) associated with a plurality of user equipment (UEs);
parsing the network KPIs into a plurality of geographic area-based categories, wherein each one of the plurality of geographic area-based categories corresponds to network KPIs obtained by cell towers or UEs located within a given geographic area;
combining the geographic area-based categories into clusters determined based on one or more similarities in the network KPIs of each of the geographic area-based categories;
predicting a most-influential one of the network KPIs within at least one of the clusters by applying a machine learning (ML) model to the network KPIs of the at least one of the clusters; and
in response to the predicting of the most-influential one of the network KPIs, causing an indicator to be generated at a user interface, the indicator indicating the most-influential one of the network KPIs within the at least one of the clusters.