US 11,751,087 B2
Predicting whether a user of a wireless telecommunication network will report a problem
Aditi Saluja, Bellevue, WA (US); Ting Zhang, Bellevue, WA (US); and Vikas Ranjan, Bellevue, WA (US)
Assigned to T-Mobile USA, Inc., Bellevue, WA (US)
Filed by T-Mobile USA, Inc., Bellevue, WA (US)
Filed on Apr. 18, 2022, as Appl. No. 17/723,180.
Application 17/723,180 is a continuation of application No. 16/932,618, filed on Jul. 17, 2020, granted, now 11,337,096.
Prior Publication US 2022/0248250 A1, Aug. 4, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. H04W 24/10 (2009.01); H04L 41/5009 (2022.01); G06N 20/00 (2019.01); H04B 17/318 (2015.01); H04W 4/24 (2018.01)
CPC H04W 24/10 (2013.01) [G06N 20/00 (2019.01); H04B 17/318 (2015.01); H04L 41/5009 (2013.01); H04W 4/24 (2013.01)] 19 Claims
OG exemplary drawing
 
1. At least one non-transient, computer-readable medium, carrying instructions that, when executed by at least one data processor, implement a process comprising:
receiving a value of each of multiple key performance indicators (KPIs) according to a rule for the KPIs,
wherein each KPI relates to a user experience with a wireless telecommunication network;
creating a particular image representing a value of a KPI among the multiple KPIs,
wherein a first axis of the particular image represents the KPI among at least one of the multiple KPIs, and
wherein a second axis of the particular image represents the value of the KPI among the at least one of the multiple KPIs; and
predicting whether a user of the wireless telecommunication network will report a problem associated with the wireless telecommunication network by:
providing the particular image to a machine learning model configured to make a prediction based on an image, and
receiving a particular prediction from the machine learning model indicating whether the user of the wireless telecommunication network will report the problem.