Juan Jose Pacheco

US Patent:

20220247870, Aug 4, 2022

Filed:

Apr 25, 2022

Appl. No.:

17/727967

Inventors:

- Bellevue WA, US
Huijae Kim - Sammamish WA, US
Juan Murillo Pacheco - Renton WA, US
Arundhati Ghosh - Redmond WA, US
Xiao Zhang - Sammamish WA, US
Prem Kumar Bodiga - Bothell WA, US

International Classification:

H04M 15/00
H04W 4/24
G06N 20/00
H04W 28/24

Abstract:

The disclosed system identifies and resolves telecommunication network problems and/or problems with devices utilizing the network. The system segments the user devices into groups having similar characteristics, by grouping together devices more likely to leave the network, and devices less likely to leave the network. Each group of devices has a trained machine learning model, to predict the NEX score for each device. The system focuses on devices with a low NEX score. The system determines whether the problem is with the network and/or the problem is with the device. The system gathers information from network monitoring software and determine which tower caused, for example, the call to drop. The system determines technological capability of the device from the device TAC number. The system suggests solutions to the network problems by suggesting adding a sector, tuning an antenna, etc., or if the device has problems, adjusting phone settings.