公开(公告)号：WO2019064048A1

公开(公告)日：2019-04-04

申请号：PCT/IB2017/055872

申请日：2017-09-26

Applicant: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

Inventor： GRIFFIOEN, Robert

IPC: H04L12/24 ,  H04L12/26 ,  H04W88/08 ,  H04W24/02

CPC classification number: H04L41/0893 ,  H04L41/0816 ,  H04L41/16 ,  H04L43/0876 ,  H04W24/02 ,  H04W88/085

Abstract: The solution presented herein facilitates the individual and dynamic configuration of each Remote Radio Head (RRH). The RRH comprises at least one hardware component, which comprises one or more performance sensors. The RRH adapts the configuration of its hardware component responsive to one or more performance metrics retrieved from that hardware component's performance sensor(s). In so doing, the RRH accounts for its hardware component's particular performance characteristics, including accounting for tolerance differences that occur at manufacturing and different performance degradations due to different environments. With time, the RRH develops configuration rule sets that account for current operating mode, component age, and environmental conditions. As such, the solution presented herein helps each RRH achieve optimum performance.

公开(公告)号：WO2019053715A1

公开(公告)日：2019-03-21

申请号：PCT/IL2018/051020

申请日：2018-09-12

Applicant: CYBER 2.0 (2015) LTD.

Inventor： KAPLAN HAELION, Erez

IPC: H04L29/06 ,  G06F9/54

CPC classification number: H04L41/0893 ,  G06F21/44 ,  G06F21/53 ,  G06F21/554 ,  H04L41/085 ,  H04L41/16 ,  H04L63/101 ,  H04L63/20

Abstract: A method, a computerized apparatus and a computer program product for automatic generation of security configuration and deployment thereof. The method comprises monitoring programs executed by a device within an organizational network, to identify an attempt to transmit outgoing communications. In response to determining a program executed by the device is attempting to transmit an outgoing communication: checking whether the program is listed in a base list of authorized programs. In response to determining that the program is listed in the base list, adding the program to a list of authorized programs.

公开(公告)号：WO2019025944A1

公开(公告)日：2019-02-07

申请号：PCT/IB2018/055688

申请日：2018-07-30

Applicant: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

Inventor： VAKILINIA, Shahin ,  KEMPF, James ,  LEMIEUX, Yves ,  TRUCHAN, Catherine

IPC: G06N3/04 ,  G06N7/00 ,  G06F9/50 ,  H04L12/24

CPC classification number: G06N7/005 ,  G06F9/5072 ,  G06N3/0445 ,  H04L41/142 ,  H04L41/147 ,  H04L41/16 ,  H04L41/5012 ,  H04L41/5025 ,  H04L43/04 ,  H04L43/0817

Abstract: A method, node and system for enforcement of rules associated with cloud services are provided. A node for probabilistic action triggering for service level agreement, SLA, management for cloud services is provided. The node includes processing circuitry configured to: monitor cloud service data associated with a cloud network, generate a conditional probability distribution, CPD, of performance metrics of the cloud network based on the monitored data, determine a plurality of predicted future states of the performance metrics based on generated CPD, determine a plurality of transition events where each transition event corresponding to a transition from a first predicted future state that does not meet a predefined rule to a second predicated future state that meets the predefined rule, correlate the plurality of transition events, and trigger at least one management action for execution based on the correlation of the plurality of transition events.

公开(公告)号：WO2018152303A1

公开(公告)日：2018-08-23

申请号：PCT/US2018/018325

申请日：2018-02-15

Applicant: EDGEWISE NETWORKS, INC.

Inventor： O'NEIL, John

IPC: H04L29/06 ,  H04L12/24

CPC classification number: H04L41/145 ,  G06N3/126 ,  G06N5/003 ,  G06N5/025 ,  G06N20/00 ,  H04L41/16 ,  H04L63/0236 ,  H04L63/0263

Abstract: Embodiments of the present invention generate network communication policies by applying machine learning to existing network communications, and without using information that labels such communications as healthy or unhealthy. The resulting policies may be used to validate communication between applications (or services) over a network.

公开(公告)号：WO2018068558A1

公开(公告)日：2018-04-19

申请号：PCT/CN2017/094907

申请日：2017-07-28

Applicant: 腾讯科技(深圳)有限公司

Inventor： 余子军 ,  刘贤彬

IPC: H04L12/911

CPC classification number: H04L41/147 ,  H04L41/0896 ,  H04L41/16 ,  H04L41/5022 ,  H04L43/067 ,  H04L43/0876 ,  H04L43/16

Abstract: 本申请是关于一种网络业务调度方法、装置、存储介质和程序产品。该方法包括：获取各个网络业务各自的历史流量数据，所述历史流量数据包括对应的网络业务在每个历史单位时间段内的实际流量；根据所述各个网络业务各自的历史流量数据，预测所述各个网络业务各自在当前时刻的下一个单位时间段内的预测流量；根据所述预测流量对所述各个网络业务进行业务调度，即根据网络业务历史单位时间段内的实际流量来预测网络业务下一单位时间段内的预测流量，按照预测流量对网络业务进行调度，使得对网络业务的进行调度时，能够基于网络业务在下一个单位时间段内将要产生的流量预先进行业务调度，从而对网络业务进行精确调度，提高对网络业务的调度效果。

公开(公告)号：WO2017103917A1

公开(公告)日：2017-06-22

申请号：PCT/IL2016/051302

申请日：2016-12-06

Applicant: DEEP INSTINCT LTD.

Inventor： CASPI, Guy ,  COHEN, Doron ,  DAVID, Eli ,  MAMAN, Nadav ,  NEEMAN, Yoel

IPC: G06N3/08 ,  G06F11/07

CPC classification number: G06N99/005 ,  G06N3/0445 ,  G06N3/084 ,  H04B1/3822 ,  H04L41/142 ,  H04L41/16 ,  H04L41/22 ,  H04L43/045 ,  H04L43/062 ,  H04L43/065

Abstract: There is provided a method for training a system for data traffic analysis, the system comprising a deep learning algorithm, wherein the deep learning algorithm comprises a prediction model which is trained to take into account the history of data. According to some embodiments, the deep learning algorithm is operated on a graphical processing unit. According to some embodiments, the system for data traffic analysis is configured to detect anomalies in the data, based also on past data. According to some embodiments, the system for data traffic analysis is configured to simultaneously detect anomalies in the data and update its prediction model. Additional methods and systems in the field of data traffic analysis are also provided. According to some embodiments, data of a car are analyzed in order to detect anomalies.

Abstract translation: 提供了一种训练用于数据流量分析的系统的方法，该系统包括深度学习算法，其中深度学习算法包括训练为考虑数据历史的训练模型 。 根据一些实施例，深度学习算法在图形处理单元上运行。 根据一些实施例，用于数据流量分析的系统被配置为还基于过去的数据来检测数据中的异常。 根据一些实施例，用于数据流量分析的系统被配置为同时检测数据中的异常并更新其预测模型。 还提供了数据流量分析领域的其他方法和系统。 根据一些实施例，分析汽车的数据以检测异常。

公开(公告)号：WO2017072356A1

公开(公告)日：2017-05-04

申请号：PCT/EP2016/076213

申请日：2016-10-31

Applicant: OPT/NET CONSULTING B.V. ,  MATSELYUKH, Taras

Inventor： MATSELYUKH, Taras

IPC: H04L29/06 ,  H04L12/24

CPC classification number: H04L63/1425 ,  G06F21/566 ,  H04L41/142 ,  H04L41/16

Abstract: There is provided a method for detecting an anomaly in plurality of data streams originating from a system or network of systems. Data streams are collected from the system or systems and divided into a plurality of time intervals. For each of the plurality of time intervals, a value for a parameter associated with the data stream is determined. A deviation in the determined values is calculated for the parameters associated with the data stream from expected values for the parameters and, if the calculated deviation is above a threshold, an anomaly is detected in the collected data stream.

Abstract translation: 提供了一种用于检测源自系统或系统网络的多个数据流中的异常的方法。 数据流从系统或系统收集并分成多个时间间隔。 对于多个时间间隔中的每一个，确定与数据流相关联的参数的值。 根据参数的期望值计算与数据流相关的参数的确定值的偏差，并且如果计算的偏差高于阈值，则在收集的数据流中检测到异常。

公开(公告)号：WO2017067615A1

公开(公告)日：2017-04-27

申请号：PCT/EP2015/074673

申请日：2015-10-23

Applicant: NEC EUROPE LTD.

Inventor： NIKITAKI, Sofia ,  DUSI, Maurizio ,  AHMED, Mohamed ,  NICCOLINI, Saverio

IPC: H04L12/24 ,  H04L12/26

CPC classification number: H04L41/142 ,  H04L41/16 ,  H04L43/08 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/087

Abstract: A method for supporting detection of irregularities in a network, the method comprising: monitoring features of said network using at least one monitoring device in order to collect spatio-temporal measuring data, providing, in an off-line phase, a training matrix where collected measuring data is aggregated in a predetermined time window such that said training matrix includes spatio-temporal correlations, performing, in said off-line phase, non-negative matrix factorization in order to decompose said training matrix into a coefficient matrix and a basis matrix, wherein temporal correlations and spatial correlations are jointly considered, creating, in an on-line phase, a current runtime matrix on the basis of measuring data newly collected in the on-line phase, computing, in said on-line phase, a current runtime coefficient matrix on the basis of said current runtime matrix and said basis matrix, and comparing, in said on-line phase, said current runtime coefficient matrix with at least one coefficient matrix that was computed previously. Furthermore, a corresponding system is disclosed.

Abstract translation: 一种用于支持检测网络中的不规则性的方法，所述方法包括：使用至少一个监测装置监测所述网络的特征，以便收集空间 - 时间测量数据， 训练矩阵，其中收集的测量数据被聚集在预定时间窗口中，使得所述训练矩阵包括时空相关性，在所述离线相位中执行非负矩阵分解以便将所述训练矩阵分解成 系数矩阵和基矩阵，其中共同考虑时间相关性和空间相关性，在在线阶段基于在线阶段新收集的测量数据创建当前运行时矩阵，在所述在线阶段中计算 在线阶段，基于所述当前运行时矩阵和所述基准矩阵确定当前运行时间系数矩阵，并且在所述在线阶段中比较所述当前运行时间系数矩阵 rix以及之前计算的至少一个系数矩阵。 此外，还披露了相应的系统。

公开(公告)号：WO2017053115A1

公开(公告)日：2017-03-30

申请号：PCT/US2016/051286

申请日：2016-09-12

Applicant: BOARD OF REGENTS, THE UNIVERSITY OF TEXAS SYSTEM

Inventor： BOVIK, Alan ,  GHADIYARAM, Deepti ,  PAN, Janice

IPC: H04H60/33 ,  G06F15/18 ,  G06G7/48 ,  H04L12/26

CPC classification number: H04L65/80 ,  G06N99/005 ,  H04L41/145 ,  H04L41/147 ,  H04L41/16 ,  H04L41/5067 ,  H04L65/4069 ,  H04L65/4084

Abstract: A method, system and computer program product for predicting a viewer's quality of experience while watching mobile videos potentially afflicted with network induced impairments. The length of a stall on a video at time t is received as a first input to a model. The number of stalls up to the time t is received as a second input to the model. Furthermore, the time since a preceding rebuffering event is received as a third input to the model. Additionally, a reciprocal stall density at time t is received as a fourth input to the model. The hysteresis effect is captured using a machine-learning-based model with an input that is an aggregate of the outputs of the first, second, third and fourth inputs to nonlinear input blocks of the model, where the hysteresis effect represents an effect that a viewer's recent level of satisfaction/dissatisfaction has on their overall viewing experience.

Abstract translation: 一种方法，系统和计算机程序产品，用于在观看潜在地受到网络诱发的损伤的移动视频的同时预测观众的体验质量。 作为模型的第一输入，接收时刻t的视频的停顿长度。 直到时间t的档位数被作为模型的第二个输入来接收。 此外，从上一次重新生成事件以来的时间被接收为模型的第三个输入。 此外，在时间t的相互失速密度被接收作为模型的第四输入。 使用基于机器学习的模型捕获滞后效应，其中输入是模型的非线性输入块的第一，第二，第三和第四输入的输出的总和，其中滞后效应表示 观众最近的满意度/不满意度对他们的整体观看体验。

公开(公告)号：WO2017016758A1

公开(公告)日：2017-02-02

申请号：PCT/EP2016/064386

申请日：2016-06-22

Applicant: BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY

Inventor： DI- CAIRANO - GILFEDDER, Carla ,  SHAKYA, Sid ,  OWUSU, Gilbert

IPC: H04L12/24

CPC classification number: H04L41/0823 ,  H04L41/0896 ,  H04L41/145 ,  H04L41/16 ,  H04L41/5025 ,  H04L43/0852

Abstract: An optimum configuration of resources in a network function virtualisation data network is identified by assembling candidate configurations of resources (243), each configuration being an arrangement of the resources into clusters selected such that each cluster provides one or more required services, (212, 213) and assessing the candidate configurations (step 400) to identify an optimum configuration, the assessment of each configuration including measurement of latency (195) in physical links between the resources and, for each candidate configuration, determination of the total latency between the resources within each cluster of the configuration, for a predicted level and pattern of traffic associated with the required service to be operated by each cluster.

Abstract translation: 通过组合资源的候选配置（243）来识别网络功能虚拟化数据网络中的资源的最佳配置，每个配置是将资源排列成所选择的集群，使得每个集群提供一个或多个所需服务（212,213 ）并评估候选配置（步骤400）以识别最佳配置，每个配置的评估包括在资源之间的物理链路中的等待时间（195）的测量，并且对于每个候选配置，确定所述资源内部的资源之间的总等待时间 每个集群的配置，用于与要由每个集群操作的所需服务相关联的流量的预测级别和模式。