Bryers Intellectual Property Ltd

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.

Various example embodiments of a cellular - wireless local area network (WLAN) radio access network (RAN) convergence (CWRC) capability are presented. The CWRC capability may be configured to support architectural and procedural solutions for enabling Layer 2 (L2) convergence between cellular and WLAN access within the RAN.

Apparatus and method of anomaly classification. In an embodiment, the apparatus performs binary classification of data samples in a dataset to classify the data samples into a normal group or an anomalous group, performs multiclass classification to classify the data samples of the anomalous group into anomaly classes, and identifying a set of the data samples in the anomalous group as false positives resulting from the binary classification when the multiclass classification fails to classify the data samples of the first set into one of the anomaly classes.

Apparatus and method of implementing a registry smart contract on a permissioned distributed ledger (PDL). In an embodiment, an apparatus operates the PDL on a distributed network of peer nodes, and executes a registry smart contract deployed on the PDL, in response to receiving a register request regarding a registering peer node, to identify node information comprising at least endpoint information of the registering peer node, generate a transaction proposal to record the node information of the registering peer node on the PDL, provide the transaction proposal to a group of the peer nodes for approval, and record the node information of the registering peer node as a transaction on the PDL when approval is granted.

Described herein is a method, a network node a computer readable medium for providing human interpretable semantic information of one or more network states generated during execution of a network component of a target communication network or a network digital twin, NDT, of a corresponding target communication network. The method is capable of generating a trained network state information model which is configured to identify and anticipate human interpretable semantic information of the one or more network states comprehensible for network experts so that no additional means are required to identify potential errors or conditions within a present network systems, wherein said method comprises at least the steps of: receiving a set of data elements and information identifying pre-defined test cases under which a SWNC is executed in a second target communication network; training, on the basis of the received set of data elements and information, a network state information model to determine human interpretable semantic information of at least one network state of the SWNC identified during execution in the first target communication network based on the identified network states; applying at least one network model including the trained network state information model to the first target communication network to generate at least one human interpretable semantic information of one or more network states of the SWNC determined during execution in the first target communication network; and reporting, by the trained network state information model, the at least one human interpretable semantic information associated with the one or more network states.

A method of a networking device is disclosed comprising: (a) establishing a Media Access Control security (MACsec) key agreement (MKA) session with another networking device; (b) generating a pre-shared key (PSK); (c) distributing the PSK generated in step (b) to the other networking device; and, optionally, (d) establishing a new MKA session using the PSK generated in step (b) to secure the new MKA session.

There are provided measures for efficient utilization of machine learning processing resources. Such measures exemplarily comprise, for preparing, based on initial data, input data for an input layer of a machine learning model having said input layer, at least one inner layer, and an output layer, and being learned and/or deployed at processing hardware providing a plurality of processing channels, each processing channel comprising a dedicated processor and a dedicated memory range, wherein said initial data is arranged in a first array having a first dimension equal to or larger than 1, a second dimension equal to or larger than 1, and a third dimension equal to or larger than 1, wherein a data amount of each element of said first array is equal to a predetermined amount, if said predetermined amount multiplied with a size of said first dimension and a size of said second dimension exceeds a size of said dedicated memory range and if said third dimension is smaller than a number of said plurality of processing channels: partitioning said first array in said first dimension and said second dimension into a plurality of uniform sub-arrays, wherein a number of said plurality of sub-arrays is based on said dedicated memory range, performing, for each sub-array field index position of a plurality of selected sub-array field index positions, a down-sampling operation on said first array of said initial data, said down-sampling operation includes selecting, from each sub-array, a field at said sub-array field index position, and generating, for each index position in said third dimension, a second array including said elements corresponding to said selected fields and said index position in said third dimension, in an arrangement corresponding to an arrangement of said plurality of uniform sub-arrays, and assigning each of generated second arrays in order of generation to a respective processing channel of said plurality of processing channels as said input data.

Method comprisingstoringone or more service profiles for a service and,for the service profiles, one or more function profiles for the respective service profile;receiving a first inquiry comprising an indication of the service and an intent for the service;selecting one of the service profiles based on the intent for the service;replying, in response to the first inquiry, by a first reply comprising the selected one of the service profiles;receiving a second inquiry comprising an indication of the selected service profile and a service plan;selecting one of the function profiles for the selected service profile based on the service plan;replying, in response to the second inquiry, by a second reply comprising the selected one of the function profiles for the selected service profile.

Method comprisingderiving first actions to adapt an allocation of resources of a first slice of a base station to fulfill a first performance requirement independently from an allocation of the resources of a second slice of the base station;providing information about the first actions;deriving a set of second actions to adapt the allocation of the resources of the second slice to fulfill a second performance requirement independently from the allocation of the resources of the first slice;providing information about the second actions;jointly optimizing the allocation of the resources of the first slice and the second slice based on the information about the first actions, the allocation of the resources of the first slice, the information about the second actions, and the allocation of the resources of the second slice to derive modified first actions and modified second actions;instructing the base station to apply the modified first actions and modified second actions.

In some embodiments, there may be provided a method that includes In some embodiments, there may be provided a method that includes receiving an indication to perform a single class inference task using a machine learning model that is trained to perform a multi-class inference task; in response to the indication, applying, during a timeframe of execution of the machine learning model hosted by the user equipment, at least one mask mapped to the single class inference task; and reconfiguring the machine learning model to a state where the first set of nodes and the second set to perform the multi-class inference task. Related systems, methods, and articles of manufacture are also disclosed.