公开(公告)号：US10733528B2

公开(公告)日：2020-08-04

申请号：US15057062

申请日：2016-02-29

Applicant: Oracle International Corporation

Inventor： Dustin Garvey ,  Uri Shaft ,  Lik Wong

IPC: G06N20/00

Abstract: Techniques are described for classifying seasonal patterns in a time series. In an embodiment, a set of time series data is decomposed to generate a noise signal and a dense signal, where the noise signal includes a plurality of sparse features from the set of time series data and the dense signal includes a plurality of dense features from the set of time series data. A set of one or more sparse features from the noise signal is selected for retention. After selecting the sparse features, a modified set of time series data is generated by combining the set of one or more sparse features with a set of one or more dense features from the plurality of dense features. At least one seasonal pattern is identified from the modified set of time series data. A summary for the seasonal pattern may then be generated and stored.

公开(公告)号：US20190361693A1

公开(公告)日：2019-11-28

申请号：US16534896

申请日：2019-08-07

Applicant: Oracle International Corporation

Inventor： Dustin Garvey ,  Timothy Mark Frazier ,  Shriram Krishnan ,  Uri Shaft ,  Amit Ganesh ,  Prasad Ravuri ,  Sampanna Shahaji Salunke ,  Sumathi Gopalakrishnan

IPC: G06F8/65 ,  G06F8/60 ,  G06N20/00 ,  G06F16/906 ,  G06F8/61 ,  G06F9/50

Abstract: Techniques are described herein for scalable clustering of target resources by parameter set. In some embodiments, a plurality of parameter sets of varying length are received, where a parameter set identifies attributes of a target resource. A plurality of signature vectors are generated based on the plurality of parameter sets such that the signature vectors have equal lengths. A signature vector may map to one or more parameter sets of the plurality of parameter sets. A plurality of clusters are generated based on the similarity between signature vectors. Operations may be performed on a target resource based on one or more nodes in the plurality of clusters.

公开(公告)号：US10331802B2

公开(公告)日：2019-06-25

申请号：US15057065

申请日：2016-02-29

Applicant: Oracle International Corporation

Inventor： Dustin Garvey ,  Uri Shaft ,  Lik Wong ,  Amit Ganesh

IPC: G06F17/30 ,  G06F17/18 ,  G06F21/55 ,  G06Q10/04 ,  G06N99/00 ,  G06Q10/06

Abstract: Techniques are described for characterizing and summarizing seasonal patterns detected within a time series. A set of time series data is analyzed to identify a plurality of instances of a season, where each instance corresponds to a respective sub-period within the season. A first set of instances from the plurality of instances are associated with a particular class of seasonal pattern. After classifying the first set of instances, a second set of instances may remain unclassified or otherwise may not be associated with the particular class of seasonal pattern. Based on the first and second set of instances, a summary may be generated that identifies one or more stretches of time that are associated with the particular class of seasonal pattern. The one or more stretches of time may span at least one sub-period corresponding to at least one instance in the second set of instances.

公开(公告)号：US20180246941A1

公开(公告)日：2018-08-30

申请号：US15902830

申请日：2018-02-22

Applicant: Oracle International Corporation

Inventor： Sampanna Shahaji Salunke ,  Dustin Garvey ,  Michael Avrahamov

IPC: G06F17/30 ,  G06F12/0802

CPC classification number: G06F16/2477 ,  G06F12/0802 ,  G06F16/1824 ,  G06F16/24552

Abstract: Techniques are described for optimizing scalability of analytics that use time-series models. In one or more embodiments, a stored time-series model includes a plurality of data points representing seasonal behavior in a training set of time-series data for at least one season. A target time for evaluating the time-series model is then determined, and the target time or one or more times relative to the target time are mapped to a subset of the plurality of data points. Based on the mapping, a trimmed version of the time-series model is generated by loading the subset of the plurality of data points into a cache, the subset of data points representing seasonal behavior in the training set of time-series data for a portion of the at least one season. A target set of time-series data may be evaluated suing the trimmed version of the time-series in the cache.

公开(公告)号：US20170249649A1

公开(公告)日：2017-08-31

申请号：US15266987

申请日：2016-09-15

Applicant: Oracle International Corporation

Inventor： Dustin Garvey ,  Sampanna Shahaji Salunke ,  Uri Shaft

IPC: G06Q30/02

CPC classification number: G06T11/206 ,  G06F17/18 ,  G06F21/55 ,  G06K9/00536 ,  G06K9/628 ,  G06N20/00 ,  G06Q10/04 ,  G06Q10/06 ,  G06Q10/0631 ,  G06Q10/06315 ,  G06Q10/1093 ,  G06Q30/0202 ,  G06T11/001

Abstract: Systems and methods for trending patterns within a set of time-series data are described. In one or more embodiments, a set of one or more groups of data points that are associated with a particular seasonal pattern are generated within volatile and/or non-volatile storage. A set of pairwise slopes is determined for data point pairs within the set of one or more groups of data points. Based, at least in part on the plurality of pairwise slopes, a representative trend rate for the particular seasonal pattern is determined. A set of forecasted values is then generated within volatile or non-volatile storage based, at least in part, on the representative trend rate for the particular seasonal pattern.

公开(公告)号：US20220245020A1

公开(公告)日：2022-08-04

申请号：US17705760

申请日：2022-03-28

Applicant: Oracle International Corporation

Inventor： Eric Sutton ,  Dustin Garvey ,  Sampanna Shahaji Salunke ,  Uri Shaft

IPC: G06F11/07 ,  G06N5/04 ,  G06F16/21 ,  G06N20/00

Abstract: Techniques for predictive system remediation are disclosed. Based on attributes associated with applications of one or more system-selected remedial actions to one or more problematic system behaviors in a system (e.g., a database system), the system determines a predicted effectiveness of one or more future applications of a remedial action to a particular problematic system behavior, as of one or more future times. The system determines that the predicted effectiveness of the one or more future applications of the remedial action is positive but does not satisfy a performance criterion. Responsive to determining that the predicted effectiveness is positive but does not satisfy the performance criterion, the system generates a notification corresponding to the predicted effectiveness not satisfying the performance criterion. The system applies the remedial action to the particular problematic system behavior, despite already determining that the predicted effectiveness does not satisfy the one or more performance criteria.

公开(公告)号：US11082439B2

公开(公告)日：2021-08-03

申请号：US16524007

申请日：2019-07-27

Applicant: Oracle International Corporation

Inventor： Sampanna Shahaji Salunke ,  Dustin Garvey ,  Uri Shaft ,  Maria Kaval

IPC: G06K9/62 ,  H04L12/26 ,  H04L29/06

Abstract: Systems and methods for performing unsupervised baselining and anomaly detection using time-series data are described. In one or more embodiments, a baselining and anomaly detection system receives a set of time-series data. Based on the set of time-series, the system generates a first interval that represents a first distribution of sample values associated with the first seasonal pattern and a second interval that represents a second distribution of sample values associated with the second seasonal pattern. The system then monitors a time-series signals using the first interval during a first time period and the second interval during a second time period. In response to detecting an anomaly in the first seasonal pattern or the second seasonal pattern, the system performs a responsive action, such as generating an alert.

公开(公告)号：US11080906B2

公开(公告)日：2021-08-03

申请号：US16859050

申请日：2020-04-27

Applicant: Oracle International Corporation

Inventor： Dustin Garvey ,  Uri Shaft ,  Lik Wong ,  Maria Kaval

IPC: G06T11/20 ,  G06Q30/02 ,  G06N20/00 ,  G06Q10/04 ,  G06F17/18 ,  G06F21/55 ,  G06Q10/06 ,  G06K9/00 ,  G06K9/62 ,  G06F11/34 ,  G06Q10/10 ,  G06T11/00 ,  H04L12/24 ,  G06F9/50

Abstract: Techniques are described for generating period profiles. According to an embodiment, a set of time series data is received, where the set of time series data includes data spanning a plurality of time windows having a seasonal period. Based at least in part on the set of time-series data, a first set of sub-periods of the seasonal period is associated with a particular class of seasonal pattern. A profile for a seasonal period that identifies which sub-periods of the seasonal period are associated with the particular class of seasonal pattern is generated and stored, in volatile or non-volatile storage. Based on the profile, a visualization is generated for at least one sub-period of the first set of sub-periods of the seasonal period that indicates that the at least one sub-period is part of the particular class of seasonal pattern.

公开(公告)号：US10970186B2

公开(公告)日：2021-04-06

申请号：US16213152

申请日：2018-12-07

Applicant: Oracle International Corporation

Inventor： Sampanna Salunke ,  Dustin Garvey ,  Uri Shaft ,  Lik Wong

IPC: G06F11/00 ,  G06F11/34 ,  G06F11/07

Abstract: Techniques are described for modeling variations in correlation to facilitate analytic operations. In one or more embodiments, at least one computing device receives first metric data that tracks a first metric for a first target resource and second metric data that tracks a second metric for a second target resource. In response to receiving the first metric data and the second metric data, the at least one computing device generates a time-series of correlation values that tracks correlation between the first metric and the second metric over time. Based at least in part on the time-series of correlation data, an expected correlation is determined and compared to an observed correlation. If the observed correlation falls outside of a threshold range or otherwise does not satisfy the expected correlation, then an alert and/or other output may be generated.

公开(公告)号：US20210042180A1

公开(公告)日：2021-02-11

申请号：US16532548

申请日：2019-08-06

Applicant: Oracle International Corporation

Inventor： Eric Sutton ,  Dustin Garvey ,  Sampanna Shahaji Salunke ,  Uri Shaft

IPC: G06F11/07 ,  G06N5/04 ,  G06N20/00 ,  G06F16/21

Abstract: Techniques for predictive system remediation are disclosed. Based on attributes associated with applications of one or more system-selected remedial actions to one or more problematic system behaviors in a system (e.g., a database system), the system determines a predicted effectiveness of one or more future applications of a remedial action to a particular problematic system behavior, as of one or more future times. The system determines that the predicted effectiveness of the one or more future applications of the remedial action is positive but does not satisfy a performance criterion. Responsive to determining that the predicted effectiveness is positive but does not satisfy the performance criterion, the system generates a notification corresponding to the predicted effectiveness not satisfying the performance criterion. The system applies the remedial action to the particular problematic system behavior, despite already determining that the predicted effectiveness does not satisfy the one or more performance criteria.