Patent · US Active

Utilizing invariant user behavior data for training a machine learning model

US12185129B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 25, 2022
Grant dateDec 31, 2024
Priority date
Expiry dateApr 21, 2043

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L41/12
  • WIPO fieldDigital communication
  • WIPO sectorElectrical engineering

Abstract

A device may receive mobile radio data identifying utilization of a mobile radio network that includes base stations and user devices in a geographical area. The device may process the mobile radio data, with a machine learning feature extraction model, to generate a behavioral representation, that is probabilistic in nature, of invariant aspects of spatiotemporal utilization of the mobile radio network. The device may generate one or more instances of the spatiotemporal utilization of the mobile radio network that reflects the probabilistic nature of a spatiotemporal predictable component of the behavioral representation. The device may utilize the one or more instances of the spatiotemporal utilization of the mobile radio network as a dataset for training or evaluating a system to manage performance of the mobile radio network.

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