公开(公告)号：US20190294995A1

公开(公告)日：2019-09-26

申请号：US16359336

申请日：2019-03-20

Applicant: TELEFONICA, S.A.

Inventor： Antonio Pastor Perales ,  Diego R. Lopez ,  Alberto Mozo Velasco ,  Sandra Gomez Canaval

IPC: G06N20/00 ,  G06N5/04 ,  H04L12/26

Abstract: A system and method for training and validating ML algorithms in real networks, including: generating synthetic traffic and receiving it along with real traffic; aggregating the received traffic into network flows by using metadata and transforming them to generate a first dataset readable by the ML algorithm, comprising features defined by the metadata; labelling the traffic and selecting a subset of the features from the labelled dataset used in an iterative training to generate a trained model; filtering out a part of real traffic to obtain a second labelled dataset; and selecting a subset of features from the second labelled dataset used for validating the trained model by comparing predicted results for the trained model and the labels; repeating the steps with a different subset of features to generate another trained model until results are positive in terms of precision or accuracy.

公开(公告)号：US11301778B2

公开(公告)日：2022-04-12

申请号：US16359336

申请日：2019-03-20

Applicant: TELEFONICA, S.A.

Inventor： Antonio Pastor Perales ,  Diego R. Lopez ,  Alberto Mozo Velasco ,  Sandra Gomez Canaval

IPC: G06N20/00 ,  G06N5/04 ,  H04L43/026 ,  H04L43/028 ,  H04L43/067 ,  H04L43/12 ,  H04L41/16 ,  H04L41/14 ,  H04L47/10

Abstract: A system and method for training and validating ML algorithms in real networks, including: generating synthetic traffic and receiving it along with real traffic; aggregating the received traffic into network flows by using metadata and transforming them to generate a first dataset readable by the ML algorithm, comprising features defined by the metadata; labelling the traffic and selecting a subset of the features from the labelled dataset used in an iterative training to generate a trained model; filtering out a part of real traffic to obtain a second labelled dataset; and selecting a subset of features from the second labelled dataset used for validating the trained model by comparing predicted results for the trained model and the labels; repeating the steps with a different subset of features to generate another trained model until results are positive in terms of precision or accuracy.