-
公开(公告)号：US20160062815A1
公开(公告)日：2016-03-03
申请号：US14475550
申请日：2014-09-02
Applicant: Microsoft Corporation
Inventor： Olga Ivanova , Smita Ojha , Alexandre de Baynast , Markus Cozowicz , Ulrich Pinsdorf , Yi Wang , Philipp Kranen , Venkat Narayanan
CPC classification number: G06F11/0751 , G06F11/008 , G06F11/0709 , G06F11/3072 , G06F11/3438 , G06F2201/81 , G06F2201/88 , G06N7/005 , G06N99/005
Abstract: Anomalies detection in error signals of a cloud based service is provided. An application such as an analysis application identifies a machine learning algorithm that matches error signals of components of a cloud based service. A periodic pattern from the error signals is removed with the machine learning algorithm to filter the periodic pattern from an error count in the error signals. The error signals are processed with the machine learning algorithm to detect one or more anomalies with the components. The machine learning algorithm is updated while processing new data to detect new patterns.
Abstract translation: 提供了基于云服务的错误信号中的异常检测。 诸如分析应用程序的应用程序识别与基于云的服务的组件的错误信号相匹配的机器学习算法。 使用机器学习算法去除误差信号的周期性模式，以从误差信号中的误差计数中滤除周期性模式。 误差信号用机器学习算法进行处理，以检测组件的一个或多个异常。 在处理新数据以检测新模式时更新机器学习算法。
-
公开(公告)号：US20150269050A1
公开(公告)日：2015-09-24
申请号：US14218119
申请日：2014-03-18
Applicant: Microsoft Corporation
Inventor： Vitaly Filimonov , Panagiotis Periorellis , Dmitry Starostin , Alexandre de Baynast , Eldar Akchurin , Aleksandr Klimov , Thomas Minka , Alexander Spengler
CPC classification number: G06F11/3409 , G06F11/3452 , G06N7/005 , G06N99/005 , G06Q10/06 , G06Q10/0639
Abstract: Examining time series sequences representing performance counters from executing programs can provide significant clues about potential malfunctions, busy periods in terms of traffic on networks, intensive processing cycles and so on. An unsupervised anomaly detector can detect anomalies for any time series. A combination of known techniques from statistics, signal processing and machine learning can be used to identify outliers on unsupervised data, and to capture anomalies like edge detection, spike detection, and pattern error anomalies. Boolean and probabilistic results concerning whether an anomaly was detected can be provided.
Abstract translation: 从执行程序中检测表示性能计数器的时间序列序列可以提供关于潜在故障，网络流量繁忙时段，密集处理周期等方面的重要线索。 无监督异常检测器可以检测任何时间序列的异常。 可以使用来自统计学，信号处理和机器学习的已知技术的组合来识别无监督数据的异常值，并捕获诸如边缘检测，尖峰检测和模式错误异常的异常。 可以提供关于是否检测到异常的布尔和概率结果。
-
公开(公告)号：US09378079B2
公开(公告)日：2016-06-28
申请号：US14475550
申请日：2014-09-02
Applicant: Microsoft Corporation
Inventor： Olga Ivanova , Smita Ojha , Alexandre de Baynast , Markus Cozowicz , Ulrich Pinsdorf , Yi Wang , Philipp Kranen , Venkat Narayanan
CPC classification number: G06F11/0751 , G06F11/008 , G06F11/0709 , G06F11/3072 , G06F11/3438 , G06F2201/81 , G06F2201/88 , G06N7/005 , G06N99/005
Abstract: Anomalies detection in error signals of a cloud based service is provided. An application such as an analysis application identifies a machine learning algorithm that matches error signals of components of a cloud based service. A periodic pattern from the error signals is removed with the machine learning algorithm to filter the periodic pattern from an error count in the error signals. The error signals are processed with the machine learning algorithm to detect one or more anomalies with the components. The machine learning algorithm is updated while processing new data to detect new patterns.
Abstract translation: 提供了基于云服务的错误信号中的异常检测。 诸如分析应用程序的应用程序识别与基于云的服务的组件的错误信号相匹配的机器学习算法。 使用机器学习算法去除误差信号的周期性模式，以从误差信号中的误差计数中滤除周期性模式。 误差信号用机器学习算法进行处理，以检测组件的一个或多个异常。 在处理新数据以检测新模式时更新机器学习算法。
-
-
Search Results
3
records
(took 0.011 seconds)
