At&t Intellectual Property I, L.p.

New Jersey Institute of Technology

Anwar Syed Aftab

Manoop Talasila

Rittwik Jana

Guy Jacobson

Wen-Ling Hsu

Yu Zhou

Cristian Borcea

Xiaopeng Jiang

Mukesh Mantan

Shuai Zhao

Lorraine Welch

Jun Hu

Yi Chen

The described technology is generally directed towards an adapting radio access network coverage for location-based alerts. A group of cells and/or cell sectors can be selected for sending an alert, according to selection techniques described herein. The selection techniques can provide a target level of cellular coverage for a geographic area, while avoiding over-inclusion of cells and consequent dissemination of alerts to subscribers outside the geographic area. The target level of coverage can comprise a desired amount of service overlap, to achieve a corresponding level of confidence that subscribers within the geographic area will receive an alert. The selection techniques can furthermore close identified coverage gaps within the geographic area.

Adapting radio access network coverage for location-based alerts

The described technology is generally directed towards public service answering point (PSAP) call routing issue detection and resolution. A PSAP call routing issue detection tool is disclosed. The PSAP call routing issue detection tool can be configured to identify PSAP call routing problems in a cellular network. The PSAP call routing issue detection tool can present the PSAP call routing problems for further analysis and correction by cellular network engineers. The PSAP call routing issue detection tool can furthermore identify and suggest call routing corrections to address identified PSAP call routing problems. The PSAP call routing issue detection tool can optionally also automatically correct identified PSAP call routing problems according to suggested call routing corrections.

Public service answering point call routing issue detection and resolution

The described technology is generally directed towards reducing unwanted cellular network activities, such as phantom 911 calls or other unwanted cellular network activities. Machine learning models described herein can be trained, using device level data and network level data, to identify devices that are likely to engage in an unwanted cellular network activity. A trained machine learning model can be deployed to identify devices, and devices identified by the trained machine learning model can be re-configured to prevent them from engaging in the unwanted cellular network activity. Devices likely to engage in the unwanted cellular network activity are thus identified and reconfigured to prevent future unwanted cellular network activity before it occurs.

Phantom call reduction for cellular networks

An artificial intelligence (AI) automation to improve network quality based on predicted locations is provided. A method can include training, by a first device comprising a processor and according to model configuration parameters received from a second device that is not the first device, a local machine learning model with training data derived from first location data collected by the first device; transmitting, by the first device to the second device, anonymized model features associated with the local machine learning model; in response to the transmitting of the anonymized model features, receiving, by the first device from the second device, an aggregated machine learning model; and estimating, by the first device, a future position of the first device by applying the aggregated machine learning model to second location data collected by the first device.

Artificial intelligence automation to improve network quality based on predicted locations

Aspects of the subject disclosure may include, for example, a device including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of receiving signal to noise and interference ratio (SINR) measurements from a cell for two or more uplink carriers associated with a mobile device; determining an optimal uplink carrier from the two or more uplink carriers based on plural parameters, wherein the plural parameters include the SINR measurements; selecting the optimal uplink carrier from the two or more uplink carriers; and sending the optimal uplink carrier selected to the cell, wherein the mobile device uses the optimal uplink carrier for uplink transmissions. Other embodiments are disclosed.

Supplementary uplink carrier selection by radio access network intelligent controller

Growing community of inventors

Budd Lake, NJ, United States of America

Anwar Syed Aftab