Patent · US Active

Method for development and execution of a machine learning model on a field device

US10942754B2 · kind B2 · utility

1Cited by

4References

20Claims

0Family size

Assignee

Siemens Aktiengesellschaft · DE

Inventors

Christian Kern · Rangsdorf, DE
Igor Kogan · Berlin, DE
Josep Soler Garrido · Munich, DE

Key dates

Filing date	Mar 1, 2018
Grant date	Mar 9, 2021
Priority date	—
Expiry date	Mar 1, 2038

Classification

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

Abstract

A method for deployment of a machine learning model (MLM) on a target field device is disclosed herein. The method includes automatically generating a set of source code files based on the machine learning model, wherein the set of source code files is configured to execute the machine learning model according to predetermined capabilities of the target field device; transforming the generated source code files into a model binary using a tool chain specific to the target field device; and deploying the model binary in a memory of the target field device.

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