利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.012 秒)

    ANOMALY ALERTS ACCREDITATION
    2.
    发明公开
    ANOMALY ALERTS ACCREDITATION 审中-公开

    公开(公告)号：EP4443301A1

    公开(公告)日：2024-10-09

    申请号：EP24168401.8

    申请日：2024-04-04

    申请人： GOOGLE LLC

    发明人： ANJANEYULU, Harish Kumar Bheemarthi

    IPC分类号： G06F11/32 ,  G06F11/34 ,  G06F18/2433

    CPC分类号： G06F11/327 ,  G06F11/3452 ,  G06F11/3466 ,  G06F18/2433

    摘要： The technology is generally directed to generating an alert based on a direction and depth of a detected anomaly. The direction of the anomaly may provide an indication as to whether the anomaly is broadening or normalizing, and the depth of the anomaly may provide an indication of the magnitude of the direction as compared to the detected anomaly. The direction may be positive, indicating that the anomaly is normalizing or moving towards an expected value, or negative, indicating that the anomaly is broadening or moving further from the expected value. Based on the determined direction and depth, a trend of the anomaly may be determined. A normalizing trend may indicate that the anomaly is likely to normalize and, therefore, an alert is not necessary. A broadening trend may indicate that the anomaly is likely to broaden and, therefore, an alert should be generated.

    REAL-TIME ANOMALY DETECTION AND CORRELATION OF TIME-SERIES DATA
    7.
    发明公开
    REAL-TIME ANOMALY DETECTION AND CORRELATION OF TIME-SERIES DATA 审中-实审

    公开(公告)号：EP4369220A2

    公开(公告)日：2024-05-15

    申请号：EP24164831.0

    申请日：2018-09-25

    申请人： Google LLC

    发明人： WANG, Xiang ,  SAFAVI, Tara

    IPC分类号： G06F17/18 ,  H04L9/40 ,  G06F18/2433

    CPC分类号： G06F17/18 ,  G06F2218/1220230101 ,  G06F18/2433 ,  H04L63/1425

    摘要： Various aspects of the subject technology related to systems and methods for detecting and correlating anomalous time-series data. A system may be configured to receive and process time-series data associated with one or more network data streams to generate sets of aligned time-series data. The system may detect anomalous time-stamped data points in the sets of aligned time series data and generate groups of annotated time-series data. The annotation identifies specific time-stamped data points as anomalous. The system may determine the number of anomalous groups of annotated time-series data within all groups of annotated time-series data and may further determine the probability that one or more anomalous groups belong to at least one of the groups of annotated time-series data using a generative statistical model and outputting one or more correlated anomalous groups. The system may generate a details statistical report for each correlated anomalous group and output an aggregated statistical report for the correlated groups.

    REAL-TIME ANOMALY DETECTION AND CORRELATION OF TIME-SERIES DATA
    10.
    发明公开
    REAL-TIME ANOMALY DETECTION AND CORRELATION OF TIME-SERIES DATA 审中-实审

    公开(公告)号：EP4369220A3

    公开(公告)日：2024-05-22

    申请号：EP24164831.0

    申请日：2018-09-25

    申请人： Google LLC

    发明人： WANG, Xiang ,  SAFAVI, Tara

    IPC分类号： G06F17/18 ,  H04L9/40 ,  G06F18/2433

    CPC分类号： G06F17/18 ,  G06F2218/1220230101 ,  G06F18/2433 ,  H04L63/1425

    摘要： Various aspects of the subject technology related to systems and methods for detecting and correlating anomalous time-series data. A system may be configured to receive and process time-series data associated with one or more network data streams to generate sets of aligned time-series data. The system may detect anomalous time-stamped data points in the sets of aligned time series data and generate groups of annotated time-series data. The annotation identifies specific time-stamped data points as anomalous. The system may determine the number of anomalous groups of annotated time-series data within all groups of annotated time-series data and may further determine the probability that one or more anomalous groups belong to at least one of the groups of annotated time-series data using a generative statistical model and outputting one or more correlated anomalous groups. The system may generate a details statistical report for each correlated anomalous group and output an aggregated statistical report for the correlated groups.