公开(公告)号：US09806944B2

公开(公告)日：2017-10-31

申请号：US14940429

申请日：2015-11-13

Applicant: Telefonica, S.A.

Inventor： Luis Miguel Contreras ,  Diego R. Lopez ,  Antonio Agustin Pastor

IPC: H04L12/24 ,  H04L12/721 ,  H04L29/12 ,  H04L29/06 ,  H04L12/715 ,  H04L12/717

CPC classification number: H04L41/0806 ,  H04L41/0803 ,  H04L41/0813 ,  H04L41/0816 ,  H04L45/04 ,  H04L45/42 ,  H04L45/44 ,  H04L45/64 ,  H04L45/70 ,  H04L61/1511 ,  H04L61/1541 ,  H04L63/0263

Abstract: A network controller and a method for automatically define forwarding rules to configure a computer networking device,The network controller (100) is connected to a sub-network (A) of a communication network and comprises: a controller manager (101) that receives a request for a given service, defines forwarding rules related to said service and installs the defined forwarding rules into a computer networking device (120a) in order to configure it for said given service; a deciding module (102) configured to communicate with the controller manager (101) and configured to interact with a DNS server (150) to receive a determined resolution for a DNS request of said request for said given service, and with a database (300) to retrieve information supplementary for the DNS request, in order to assist the controller manager (101) in performing the defining of the forwarding rules; and a plurality of interfaces (SA, SB, SD) for allowing the communication between the different elements.

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：US20190392292A1

公开(公告)日：2019-12-26

申请号：US16446649

申请日：2019-06-20

Applicant: Telefonica, S.A

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

IPC: G06N3/04

Abstract: A system and method for optimizing event prediction in data systems, wherein at least one source (100) comprises: a data collector periodically collecting (101) real data values (300) to generate a stream of data modeled as a time series; a generator (110) of prediction models (M1, M2, M3, . . . , Mx) to which the collected values from the data collector are input; a first forecast module (120) receiving (102) one of the generated prediction models (M1, M2, M3, . . . , Mx) for generating a predicted value (310) and computing a committed error (320) by comparing the predicted value (310) with the real data value (300); and wherein the source (100) sends (105) the committed error (320) within the time series to the destination (200) only if the committed error (320) exceeds a threshold and wherein the destination (200) comprises: a second forecast module (210) receiving (204) the same prediction model (M1, M2, M3, . . . , Mx) from the generator (110) through a communication channel (103); a correction module (220) for obtaining (203) the real data value by the generated prediction model (M1, M2, M3, . . . , Mx) and applying the committed error (320) if received (202) from the source (100).

公开(公告)号：US10396993B2

公开(公告)日：2019-08-27

申请号：US15480659

申请日：2017-04-06

Applicant: Telefonica, S.A.

Inventor： Pedro A. Aranda Gutiérrez ,  Diego R. Lopez ,  Norisy C. Orea Barrios

IPC: H04L9/32 ,  H04L9/06 ,  H04L12/833 ,  H04L12/801 ,  H04L29/06 ,  H04L9/14 ,  H04L12/701

Abstract: The method comprising, in a network based on a chain of individual Service Functions, SFs, that are composed to implement Network Services, NSs: assigning, at an ingress node of a network architecture, to at least one data packet received by said ingress node from the network, a unique cryptographic tag; processing said assigned unique cryptographic tag using a cryptographic function specific to each Service Function, SF; and verifying, at a given point of the network architecture, said processed unique cryptographic tag by applying a cryptographic verification function composed by the inverse functions of the cryptographic functions associated to the SFs traversed by the at least one data packet.

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.