公开(公告)号：US11687438B1

公开(公告)日：2023-06-27

申请号：US17248612

申请日：2021-01-29

Applicant: Splunk Inc.

Inventor： Ian Edward Torbett ,  Lila Fridley ,  Tristan Antonio Fletcher ,  Ayyappa Muthusami ,  Tanner Gilligan

IPC: G06F11/34 ,  G06F11/30 ,  G06F11/32

CPC classification number: G06F11/3466 ,  G06F11/3075 ,  G06F11/324 ,  G06F11/3428

Abstract: Systems and methods are described for performing adaptive thresholding on key performance indicator (KPI) values using an online machine learning algorithm as the KPI values or the data from which the KPI values are derived is being ingested. For example, the system can identify outliers in a moving window of KPI values. To implement the adaptive thresholding, the system may identify seasonality and/or trend components in historical KPI values. When a new KPI value is obtained, the system may remove the identified seasonality and/or trend components from the KPI value, and determine whether the modified KPI value is an outlier using sketches or quantiles. The system can then repeat this process for each subsequently received KPI value.

公开(公告)号：US11676072B1

公开(公告)日：2023-06-13

申请号：US17163212

申请日：2021-01-29

Applicant: Splunk Inc.

Inventor： Ramkumar Chandrasekharan ,  William Deaderick ,  Lila Fridley ,  Ramprasad Siva Golla ,  Shailendra Suryawanshi

IPC: G06F7/00 ,  G06N20/00 ,  G06F3/0482 ,  G06F3/0486 ,  G06F16/28

CPC classification number: G06N20/00 ,  G06F3/0482 ,  G06F3/0486 ,  G06F16/285

Abstract: Systems and methods are described for training a machine learning (ML) model to group notable events reflecting operation of a computing system into episodes of related events reflecting an incident on the computing system, such as to enable root cause analysis of the incident. The ML model is trained using pairwise binary similarity labels (PBSLs) indicating that two events must or must not be grouped together. An interface is provided that facilitates rapid generating of PBSLs by relocating one or more events from a first episode to a second episode. The relocation input is translated into PBSLs that are then used to train the ML model.