Telefonaktiebolaget Lm Ericsson (publ)

Markus Andersson

Tommy Arngren

Athanasios Karapantelakis

Konstantinos Vandikas

Göran Eriksson

Rafia Inam

Lackis Eleftheriadis

Magnus Westerlund

Bo Burman

Elena Fersman

Tomas Frankkila

Kjell Larsson

Rickard Cöster

David Lindero

Decision-making equipment () is configured for link change decision-making using reinforcement learning. The decision-making equipment () is configured to track rewards (--M) earned for, and outcomes (--M) of, respective link change decisions (--M). In some embodiments, possible outcomes of a link change decision to change a serving link of a wireless device to a target link include at least: a change of the serving link of the wireless device from the target link to another link; and a network-initiated disconnect of the wireless device from the target link. Regardless, the decision-making equipment () is also configured to make a link change decision (-(M+1)) based on the tracked rewards (--M) and outcomes (--M).

Link change decision-making using reinforcement learning based on tracked rewards and outcomes in a wireless communication system

A communications device () for classifying an instance () using Machine Learning (ML) is provided. The communications device is operative to acquire a feature vector representing the instance, classify the instance using a local first ML model, calculate a confidence level, and, if the calculated confidence level is less than a threshold confidence level, acquire information identifying one or more other communications devices, and transmit a classification request message comprising the feature vector to the one or more other communications devices. The one or more other communications devices are selected based on at least one of: an identity of a user of the communications device, a contact list of the user, a type of data comprised in the feature vector, an origin of the feature vector, the classification of the instance using the local first ML model, a location of the communications device, a respective location of the one or more other communications devices, a location associated with the instance, and one or more classified instances which are related to the instance represented by the feature vector.

Classifying an instance using machine learning

There is provided mechanism for providing Web based applications with network information. A need for a Web based application to transmit a real time media flow is acquired. Transport characteristics relating to transmission of the real time media flow over a communications network is acquired. From the acquired transport characteristics and according to a policy criterion a resource allocation to the real time media flow is determined. The determined resource allocation is provided to at least one of the Web based application and a browser associated with the Web based application.

Allocation of resources for real-time communication

A network information system for determining transport conditions in a communications network. Monitoring data is acquired from a plurality of data transport nodes in a communications network. Transport conditions are determined from network information related to transport flows for network transmission of real time media flows. The network information is determined from a subset of the acquired monitoring data. The determined transport conditions are provided to at least one of a network connected device running an application involving the network transmission of real time media flows and a data transport node involved in the network transmission of real time media flows.

Handling of transport conditions

There is provided a network information system for determining transport conditions in a communications network. Monitoring data is acquired from a plurality of data transport nodes in a communications network. Transport conditions are determined from network information related to transport flows for network transmission of real time media flows. The network information is determined from a subset of the acquired monitoring data. The determined transport conditions are provided to at least one of a network connected device running an application involving the network transmission of real time media flows and a data transport node involved in the network transmission of real time media flows.

In a method and device, simple hardware such as a standard User Equipment (UE), a mobile telephone, is used to collect the impulse response of a radio channel. The data generated is used to classify radio channels based on the impulse response estimates by estimating distribution parameters of the impulse response. This makes it possible to distinguish between different types of fading and hence, radio environments by matching the parameters to known radio channel models.

Growing community of inventors

Boden, Sweden

Markus Andersson