US 12,294,861 B2
Phantom call reduction for cellular networks
Manoop Talasila, Branchburg, NJ (US); Mukesh Mantan, Irving, TX (US); and Anwar Syed Aftab, Budd Lake, NJ (US)
Assigned to AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed by AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed on Aug. 11, 2022, as Appl. No. 17/819,011.
Prior Publication US 2024/0056817 A1, Feb. 15, 2024
Int. Cl. H04W 12/08 (2021.01); H04W 12/12 (2021.01); H04W 12/72 (2021.01); H04W 24/02 (2009.01)
CPC H04W 12/12 (2013.01) [H04W 12/08 (2013.01); H04W 12/72 (2021.01); H04W 24/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, by network equipment comprising a processor, first data associated with first devices, wherein the first devices are associated with a cellular network activity;
obtaining, by the network equipment, second data associated with second devices, wherein the second devices are not associated with the cellular network activity;
using, by the network equipment, the first data and the second data to generate model data for a machine learning model, wherein the machine learning model is usable to predict whether other devices, other than the first devices and the second devices, present a probability of engaging in the cellular network activity;
using, by the network equipment, the machine learning model to analyze third data associated with a third device, in order to generate a prediction of whether the third device presents the probability of engaging in the cellular network activity; and
in response to the prediction indicating that the third device presents the probability of engaging in the cellular network activity, facilitating, by the network equipment, a reconfiguration of the third device in order to prevent the third device from engaging in the cellular network activity.