Patent · US Active

Apparatus and methods for generating edge ground truth data for a federated system architecture using machine learning processes

US12354327B2 · kind B2 · utility

0Cited by
2References
28Claims
0Family size

Assignee

Inventor

Key dates

Filing dateSep 16, 2022
Grant dateJul 8, 2025
Priority date
Expiry dateDec 2, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/26
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatuses to update or retrain a trained machine learning model/process based on edge ground truth data generated by edge devices. For example, a computing device may obtain, from a database, a first dataset of a first trained machine learning process and a second dataset of a second trained machine learning process. The first dataset may include at least a first value of a parameter of the first trained machine learning process. Additionally, the computing device may transmit, to a first edge device of a plurality of edge devices, a message including the first dataset and the second dataset. Further, the computing device may receive, from the first edge device, a third dataset associated with the message, and update a portion of the first dataset with the third dataset. The updated portion of the first dataset may include an updated value of the parameter.

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