公开(公告)号：US20240283712A1

公开(公告)日：2024-08-22

申请号：US18522999

申请日：2023-11-29

Applicant: Nokia Solutions and Networks Oy

Inventor： Borislava Gajic ,  Tejas Subramanya ,  Gerald Lehmann ,  Sivaramakrishnan Swaminathan

IPC: H04L41/50 ,  G06N20/00 ,  H04L41/16

CPC classification number: H04L41/50 ,  G06N20/00 ,  H04L41/16

Abstract: An apparatus for use by a communication network element or communication network function acting as an artificial intelligence, AI, machine learning, ML, management service consumer, the apparatus comprising at least one processing circuitry, and at least one memory for storing instructions that, when executed by the at least one processor, cause the apparatus at least to request an AI/ML energy consumption related parameter from an AI/ML management service producer offering services related to at least one AI/ML entity, to receive, from the AI/ML management service producer, the requested AI/ML energy consumption related parameter, and to process the AI/ML energy consumption related parameter for deriving an energy saving strategy considering the AI/ML energy consumption related parameter.

公开(公告)号：US20230376793A1

公开(公告)日：2023-11-23

申请号：US17749427

申请日：2022-05-20

Applicant: Nokia Solutions and Networks Oy

Inventor： Gerald Lehmann ,  Dan Kushnir ,  Maria Able ,  Gerald Meyer ,  Huseyin Uzunalioglu ,  Robert Seidl

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: Systems, methods, and software for training a machine learning model. The system utilizes training data to train the machine learning model across multiple epochs. The system prepares additional training data by: selecting a set of samples that are unclassified, operating the machine learning model to predict labels that classify the samples, determining an uncertainty of the labels predicted by the machine learning model, calculating a ranking score for each of the samples in the set, selecting a subset of the samples that have more than a threshold ranking score, and submitting the subset to a client for replacement labels. The system receives the replacement labels from the client, and trains the machine learning model, using the subset of the samples as the training data. The labels predicted by the machine learning model for the subset are replaced with corresponding replacement labels from the client.