Patent · US Active

Artificial intelligence automation to improve network quality based on predicted locations

US11848828B1 · kind B1 · utility

1Cited by
1References
20Claims
0Family size

Assignees

Inventors

Key dates

Filing dateAug 23, 2022
Grant dateDec 19, 2023
Priority date
Expiry dateAug 23, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.