US Patent Application 18141628. MACHINE LEARNING SYSTEMS CONFIGURED TO GENERATE LABELED TIME SERIES DATASETS FOR MANUFACTURING OPERATIONS simplified abstract

From WikiPatents
Jump to navigation Jump to search

MACHINE LEARNING SYSTEMS CONFIGURED TO GENERATE LABELED TIME SERIES DATASETS FOR MANUFACTURING OPERATIONS

Organization Name

3M INNOVATIVE PROPERTIES COMPANY

Inventor(s)

Karthik Subramanian of St. Paul MN (US)

Anish R. Kunduru of South St. Paul MN (US)

Nicholas John Blum of Woodbury MN (US)

MACHINE LEARNING SYSTEMS CONFIGURED TO GENERATE LABELED TIME SERIES DATASETS FOR MANUFACTURING OPERATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18141628 titled 'MACHINE LEARNING SYSTEMS CONFIGURED TO GENERATE LABELED TIME SERIES DATASETS FOR MANUFACTURING OPERATIONS

Simplified Explanation

The patent application describes a method for training a semi-supervised learning algorithm (SSLA) using annotated seed data and unlabeled time series process data.

  • The method involves obtaining annotated seed data that includes tags, timing data, and labels.
  • The SSLA is trained using the annotated seed data to create a trained SSL model.
  • The trained SSL model is then executed using unlabeled time series process data as input.
  • The output of the trained SSL model is a pre-validation labeled time series process dataset.
  • Output evaluation data associated with the pre-validation labeled dataset is obtained.
  • The trained SSL model is iteratively retrained using the output evaluation data.
  • Convergence of the trained SSL model is determined based on the output evaluation data, indicating that it outputs validated labeled time series data.
  • Once convergence is reached, the trained SSL model is deployed.


Original Abstract Submitted

A method includes obtaining annotated seed data comprising one or more tags associated with corresponding timing data and a respective label, training a semi supervised learning algorithm (SSLA) using the annotated seed data to form a trained SSL model, executing the trained SSL model using unlabeled time series process data as an input, wherein the unlabeled time series process data includes tags different from the tags of the annotated seed data to output a pre-validation labeled time series process dataset, obtaining output evaluation data associated with the pre-validation labeled time series process dataset, iteratively retraining the trained SSL model using the output evaluation data, determining that the trained SSL model has reached convergence based on the output evaluation data indicating that the trained SSL model outputs validated labeled time series data, and in response to determining that the trained SSL model has reached convergence, deploying the trained SSL model.

Retrieved from "http://wikipatents.org/index.php?title=US_Patent_Application_18141628._MACHINE_LEARNING_SYSTEMS_CONFIGURED_TO_GENERATE_LABELED_TIME_SERIES_DATASETS_FOR_MANUFACTURING_OPERATIONS_simplified_abstract&oldid=10217"