Anomaliedetektion für Digitale Zwillinge unter Verwendung von Einbettungsgesteuertem Personalisiertem Föderiertem Lernen

Details

Veröffentlichungs-Nr.

EP4779526

Anmeldetag

30. Dezember 2025

Veröffentlichung

22. Juli 2026

Rechtsraum

EP

IPC

G06N3/098, G06N20/00

Abstract

Described herein is a client device, configured to provide a user service and to establish communication with a server device for providing a Digital Twin Machine Learning, ML, Model training service for said client device, comprising: at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the client device at least to: receive, from the server device, a plurality of models for providing estimation for at least one parameter associated with the user service; apply, for each of the received plurality of models, data at the client device associated with the user service to a model evaluation function, and determine, for the each model, a corresponding model evaluation value for indicating performance of the each model in providing estimation for said at least one parameter associated with the user service; obtain, from the server device, an indicator for indicating a model selected by the server device for the client device among the received plurality of models based on all of the determined model evaluation values for the received plurality of models; train and/or update the selected model based on said data at the client device associated with the user service; and send, to the server device, information relating to the trained and/or updated selected model for the server device to further update the selected model.

Anmelder

Firma

Nokia Solutions and Networks Oy

Land

🇫🇮 Finnland

Fachgebiete