公开(公告)号：US20190007294A1

公开(公告)日：2019-01-03

申请号：US16122606

申请日：2018-09-05

Applicant: Splunk Inc.

Inventor： Toufic Boubez

IPC: H04L12/26 ,  H04L12/24

CPC classification number: H04L43/0876 ,  H04L41/0686 ,  H04L41/0883 ,  H04L43/04

Abstract: An anomaly detection system is able to detect spatial and temporal environment anomalies and spatial and temporal behavior anomalies, and monitor servers for anomalous characteristics of the environment and behavior. If metrics and/or characteristics associated with a given server are beyond a certain threshold, and alert is generated. Among other options, the alert can take the form of a heat map or a cluster cohesiveness report.

公开(公告)号：US10855712B2

公开(公告)日：2020-12-01

申请号：US16446300

申请日：2019-06-19

Applicant: SPLUNK INC.

Inventor： Adam Jamison Oliner ,  Jonathan La ,  Colleen Kinross ,  Hongyang Zhang ,  Jacob Leverich ,  Shang Cai ,  Mihai Ganea ,  Alex Cruise ,  Toufic Boubez ,  Manish Sainani

IPC: G06F21/00 ,  H04L29/06 ,  G06N3/08 ,  G06N5/00 ,  G06N3/04

Abstract: In some implementations, sequences of time series values determined from machine data are obtained. Each sequence corresponds to a respective time series. A plurality of predictive models is generated for a first time series from the sequences of time series values. Each predictive model is to generate predicted values associated with the first time series using values of a second time series. For each of the plurality of predictive models, an error is determined between the corresponding predicted values and values associated with the first time series. A predictive model is selected for anomaly detection based on the determined error of the predictive model. Transmission is caused of an indication of an anomaly detected using the selected predictive model.

公开(公告)号：US11632383B2

公开(公告)日：2023-04-18

申请号：US17075928

申请日：2020-10-21

Applicant: SPLUNK INC.

Inventor： Adam Jamison Oliner ,  Jonathan La ,  Colleen Kinross ,  Hongyang Zhang ,  Jacob Leverich ,  Shang Cai ,  Mihai Ganea ,  Alex Cruise ,  Toufic Boubez ,  Manish Sainani

IPC: G06F21/00 ,  H04L9/40 ,  G06N3/08 ,  G06N5/00 ,  G06N3/04

Abstract: In some implementations, sequences of time series values determined from machine data are obtained. Each sequence corresponds to a respective time series. A plurality of predictive models is generated for a first time series from the sequences of time series values. Each predictive model is to generate predicted values associated with the first time series using values of a second time series. For each of the plurality of predictive models, an error is determined between the corresponding predicted values and values associated with the first time series. A predictive model is selected for anomaly detection based on the determined error of the predictive model. Transmission is caused of an indication of an anomaly detected using the selected predictive model.

公开(公告)号：US10148540B2

公开(公告)日：2018-12-04

申请号：US14815941

申请日：2015-07-31

Applicant: Splunk Inc.

Inventor： Toufic Boubez

IPC: H04L12/26 ,  H04L12/24

Abstract: An anomaly detection system is able to detect spatial and temporal environment anomalies and spatial and temporal behavior anomalies, and monitor servers for anomalous characteristics of the environment and behavior. If metrics and/or characteristics associated with a given server are beyond a certain threshold, an alert is generated. Among other options, the alert can take the form of a heat map or a cluster cohesiveness report.

公开(公告)号：US10554526B2

公开(公告)日：2020-02-04

申请号：US16122606

申请日：2018-09-05

Applicant: Splunk Inc.

Inventor： Toufic Boubez

IPC: H04L12/26 ,  H04L12/24

Abstract: An anomaly detection system is able to detect spatial and temporal environment anomalies and spatial and temporal behavior anomalies, and monitor servers for anomalous characteristics of the environment and behavior. If metrics and/or characteristics associated with a given server are beyond a certain threshold, and alert is generated. Among other options, the alert can take the form of a heat map or a cluster cohesiveness report.

公开(公告)号：US10375098B2

公开(公告)日：2019-08-06

申请号：US15420737

申请日：2017-01-31

Applicant: SPLUNK INC.

Inventor： Adam Jamison Oliner ,  Jonathan La ,  Colleen Kinross ,  Hongyang Zhang ,  Jacob Leverich ,  Shang Cai ,  Mihai Ganea ,  Alex Cruise ,  Toufic Boubez ,  Manish Sainani

IPC: H04L29/06 ,  G06N3/04 ,  G06N3/08

Abstract: In some implementations, sequences of time series values determined from machine data are obtained. Each sequence corresponds to a respective time series. A plurality of predictive models is generated for a first time series from the sequences of time series values. Each predictive model is to generate predicted values associated with the first time series using values of a second time series. For each of the plurality of predictive models, an error is determined between the corresponding predicted values and values associated with the first time series. A predictive model is selected for anomaly detection based on the determined error of the predictive model. Transmission is caused of an indication of an anomaly detected using the selected predictive model.

公开(公告)号：US10103960B2

公开(公告)日：2018-10-16

申请号：US14765324

申请日：2014-12-23

Applicant: Splunk Inc.

Inventor： Toufic Boubez

IPC: H04L12/26 ,  H04L12/24

Abstract: An anomaly detection system is able to detect spatial and temporal environment anomalies and spatial and temporal behavior anomalies, and monitor servers for anomalous characteristics of the environment and behavior. If metrics and/or characteristics associated with a given server are beyond a certain threshold, an alert is generated. Among other options, the alert can take the form of a heat map or a cluster cohesiveness report.