System and method for dynamic problem determination using aggregate anomaly analysis
    21.
    发明授权
    System and method for dynamic problem determination using aggregate anomaly analysis 有权
    使用聚合异常分析进行动态问题确定的系统和方法

    公开(公告)号:US09058259B2

    公开(公告)日:2015-06-16

    申请号:US12242153

    申请日:2008-09-30

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06F11/07 H04L12/24 H04L12/26

    摘要: A system and method are provided for determining problem conditions in an IT infrastructure using aggregate anomaly analysis. The anomalies in the metrics occurring in the monitored IT infrastructure are aggregated from all resources reporting metrics as a function of time. The aggregated metric anomalies are then normalized to account for the state of the monitored IT infrastructure to provide a normalized aggregate anomaly count. A threshold noise level is then determined utilizing a variably selectable desired level of confidence such that a problem event is only determined to likely be occurring in the IT infrastructure when the normalized aggregate anomaly count exceeds the threshold noise level. The normalized aggregate anomaly count is monitored against the threshold noise level as a function of time, such that a problem event in the IT infrastructure is identified when the normalized aggregate anomaly count exceeds the threshold noise level at a given time.

    摘要翻译: 提供了一种用于使用聚合异常分析来确定IT基础架构中的问题状况的系统和方法。 受监控的IT基础设施中发生的指标中的异常会从作为时间的函数的所有资源报告指标汇总。 然后对聚合的度量异常进行归一化以考虑受监视的IT基础结构的状态,以提供归一化的聚合异常计数。 然后使用可变地选择的期望可信度来确定阈值噪声电平,使得仅当标准化的聚合异常计数超过阈值噪声电平时,问题事件才被确定为可能在IT​​基础设施中发生。 根据阈值噪声水平作为时间的函数监测归一化的聚集异常计数,使得当标准化的聚集异常计数超过给定时间的阈值噪声水平时,IT基础设施中的问题事件被识别。

    System and method for correlating fingerprints for automated intelligence
    22.
    发明授权
    System and method for correlating fingerprints for automated intelligence 有权
    用于自动智能相关指纹的系统和方法

    公开(公告)号:US08631117B2

    公开(公告)日:2014-01-14

    申请号:US12194197

    申请日:2008-08-19

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06F15/16

    摘要: A system and method for correlating fingerprints in an Information Technology (IT) infrastructure for automated intelligence, where a fingerprint provides an indication of the activity and operation of the IT infrastructure immediately preceding an event. It is determined whether a correlation exists between multiple fingerprints to determine whether such fingerprints separately indicate the occurrence of the event for the same reason. If a degree of match is found to exist between the rule sets of multiple fingerprints that exceeds a certain threshold, the fingerprints are determined to indicate the occurrence of the event for the same reason and the rule sets for those fingerprints can be merged together with the probabilities that such rules will indicate the occurrence of the event adjusted accordingly. In one or more embodiments, the fingerprint matching correlation procedures are implemented to account for time or phase shifts between the rule sets in two fingerprints.

    摘要翻译: 用于将信息技术(IT)基础设施中的指纹与用于自动化智能相关联的系统和方法,其中指纹提供在事件之前的IT基础设施的活动和操作的指示。 确定在多个指纹之间是否存在相关性,以确定这样的指纹是否由于相同的原因分别指示事件的发生。 如果超过某个阈值的多个指纹的规则集之间存在匹配程度,则由于相同的原因确定指纹以指示事件的发生,并且可以将这些指纹的规则集合与 这些规则将表明相应调整事件发生的概率。 在一个或多个实施例中,实施指纹匹配相关程序以考虑两个指纹中的规则集之间的时间或相位偏移。

    SELF-LEARNING INTEGRITY MANAGEMENT SYSTEM AND RELATED METHODS
    23.
    发明申请
    SELF-LEARNING INTEGRITY MANAGEMENT SYSTEM AND RELATED METHODS 有权
    自学习完整性管理系统及相关方法

    公开(公告)号:US20100318487A1

    公开(公告)日:2010-12-16

    申请号:US12857369

    申请日:2010-08-16

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06N5/02

    CPC分类号: G06N99/005

    摘要: An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.

    摘要翻译: 完整性管理系统基于复杂系统中的异常历史,预测复杂系统发生之前的异常。 生成复杂系统节点的拓扑,并根据预定的度量从系统收集数据。 结合动态阈值处理,捕获并加权了在异常发生之前的各个时间间隔内的复杂系统内相关节点的指纹。 然后可以将指纹应用于实时数据,在其实际发生之前提供潜在异常的警报。

    METHODS AND SYSTEMS FOR THE DETERMINATION OF THRESHOLDS VIA WEIGHTED QUANTILE ANALYSIS
    24.
    发明申请
    METHODS AND SYSTEMS FOR THE DETERMINATION OF THRESHOLDS VIA WEIGHTED QUANTILE ANALYSIS 有权
    通过称重数量分析确定阈值的方法和系统

    公开(公告)号:US20100082638A1

    公开(公告)日:2010-04-01

    申请号:US12241631

    申请日:2008-09-30

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06F17/30

    CPC分类号: G06F17/18

    摘要: Methods and systems for determination of thresholds for time-series data. Data is transformed by reducing outliers, dividing the time series data into discrete time intervals, and taking parts of the data corresponding to the range that the thresholds will bound. If data cycles are known, they may be applied to the data and the resulting sets are weighted. Thresholds are then derived from the weighted means and variances of the sets of weighted data.

    摘要翻译: 用于确定时间序列数据阈值的方法和系统。 通过减少异常值,将时间序列数据划分为离散时间间隔,并获取对应于阈值将限制的范围的部分数据来转换数据。 如果数据周期是已知的,则可以将它们应用于数据,并将所得到的集合加权。 然后从加权数据集合的加权均值和方差导出阈值。

    SELF-LEARNING INTEGRITY MANAGEMENT SYSTEM AND RELATED METHODS
    25.
    发明申请
    SELF-LEARNING INTEGRITY MANAGEMENT SYSTEM AND RELATED METHODS 有权
    自学习完整性管理系统及相关方法

    公开(公告)号:US20090063390A1

    公开(公告)日:2009-03-05

    申请号:US12270535

    申请日:2008-11-13

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06N7/02

    CPC分类号: G06N99/005

    摘要: An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.

    摘要翻译: 完整性管理系统基于复杂系统中的异常历史,预测复杂系统发生之前的异常。 生成复杂系统节点的拓扑,并根据预定的度量从系统收集数据。 结合动态阈值处理,捕获并加权了在异常发生之前的各个时间间隔内的复杂系统内相关节点的指纹。 然后可以将指纹应用于实时数据,在其实际发生之前提供潜在异常的警报。

    Self-learning integrity management system and related methods
    26.
    发明授权
    Self-learning integrity management system and related methods 有权
    自学完整性管理系统及相关方法

    公开(公告)号:US07467067B2

    公开(公告)日:2008-12-16

    申请号:US11535818

    申请日:2006-09-27

    申请人: Mazda A. Marvasti

    发明人: Mazda A. Marvasti

    IPC分类号: G06F11/30 G06F11/00

    CPC分类号: G06N99/005

    摘要: An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.

    摘要翻译: 完整性管理系统基于复杂系统中的异常历史,预测复杂系统发生之前的异常。 生成复杂系统节点的拓扑,并根据预定的度量从系统收集数据。 结合动态阈值处理,捕获并加权了在异常发生之前的各个时间间隔内的复杂系统内相关节点的指纹。 然后可以将指纹应用于实时数据,在其实际发生之前提供潜在异常的警报。