18546344. CONTEXTUAL LEARNING AT THE EDGE simplified abstract (Telefonaktiebolaget LM Ericsson (publ))

CONTEXTUAL LEARNING AT THE EDGE

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

Kristijonas Cyras of San Jose CA (US)

Athanasios Karapantelakis of Solna (SE)

Marin Orlic of Bromma (SE)

[[:Category:Jörg Niem�ller of Sollentuna (SE)|Jörg Niem�ller of Sollentuna (SE)]][[Category:Jörg Niem�ller of Sollentuna (SE)]]

Leonid Mokrushin of Uppsala (SE)

Aneta Vulgarakis Feljan of Stockholm (SE)

Ramamurthy Badrinath of Bangalore Karnataka (IN)

CONTEXTUAL LEARNING AT THE EDGE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18546344 titled 'CONTEXTUAL LEARNING AT THE EDGE

Simplified Explanation

The patent application describes a method for selecting features for a machine learning model to be deployed at an edge entity of a network based on available data, features, and contextual information.

• The method involves selecting a first set of features for the machine learning model based on available data, features, and contextual information.
• The machine learning model is to be deployed at an edge entity of the network.
• The selection process is guided by first information about available data, second information about available features, and contextual information associated with the network.

Potential Applications

This technology could be applied in various industries such as telecommunications, IoT, and healthcare for optimizing data analysis at the edge of networks.

Problems Solved

This technology helps in efficiently selecting features for machine learning models based on available data and contextual information, improving the accuracy and performance of data analysis at the edge of networks.

Benefits

- Enhanced data analysis capabilities at the edge of networks - Improved efficiency and accuracy in feature selection for machine learning models - Optimization of resources and network performance

Potential Commercial Applications

Optimizing data analysis in IoT devices Enhancing predictive maintenance in telecommunications networks Improving patient monitoring and diagnosis in healthcare systems

Possible Prior Art

There may be prior art related to feature selection for machine learning models based on available data and contextual information in the field of edge computing and network optimization.

How does this method handle dynamic changes in data and network conditions?

The patent application does not provide details on how the method adapts to dynamic changes in data and network conditions to ensure optimal feature selection for the machine learning model.

What types of machine learning models are compatible with this feature selection method?

The patent application does not specify the types of machine learning models that can effectively utilize the feature selection process described in the method.

Original Abstract Submitted

There is provided a method performed by a central entity of a network. A first set of features is selected for a machine learning model to take into account when analysing data. The machine learning model is to be deployed at an edge entity of the network. The selection is based on first information indicative of data that is available for the machine learning model to analyse, second information indicative of features that are available for the machine learning model to take into account when analysing data, and contextual information associated with the network.