公开(公告)号：US20210073200A1

公开(公告)日：2021-03-11

申请号：US16563204

申请日：2019-09-06

Applicant: Salesforce.com, Inc.

Inventor： Ajay Krishna BORRA ,  Gokulakrishnan GOPALAKRISHNAN ,  Manpreet SINGH ,  Brian TOAL ,  Laksh VENKA ,  Metarya RUPAREL

IPC: G06F16/23

Abstract: A metric data stream for a plurality of metrics may be retrieved from a database system. Each metric may measure a respective computing characteristic. The metric data stream may include a plurality of values for each of a sequence of time intervals. Each value may correspond with a respective one of the metrics. A plurality of metric correlation matrices may be determined for the metrics, each of which is associated with a respective time period in the metric data stream. A subset of comparison metric correlation matrices may be selected from the plurality of metric correlation metric matrices. A designated anomaly score may be determined for a designated time period by comparing a designated metric correlation matrix associated with the designated time period with the selected subset of comparison metric correlation metric matrices.

公开(公告)号：US20180349323A1

公开(公告)日：2018-12-06

申请号：US15608375

申请日：2017-05-30

Applicant: salesforce.com, inc.

Inventor： Ajay Krishna BORRA ,  Manpreet SINGH

IPC: G06F17/18 ,  G06F11/30 ,  G06N3/04 ,  G06N3/08

Abstract: Systems, device and techniques are disclosed for outlier discovery system selection. A set of time series data including time series data objects may be received. A sample of time series data objects may be extracted from the time series data. The sample of time series data objects may be decomposed into sub-components. Statistical classification may be used to select an outlier discovery system based on the sub-components. A neural network may be used to select an outlier discovery system based on the sub-components. A level of error of the neural network may be determined based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network. Weight of the neural network may be updated based on the level of error of the neural network.

公开(公告)号：US20190332376A1

公开(公告)日：2019-10-31

申请号：US15966445

申请日：2018-04-30

Applicant: salesforce.com, inc.

Inventor： Ajay Krishna BORRA ,  Manpreet SINGH ,  Himanshu MITTAL ,  Edet NKPOSONG

IPC: G06F8/75 ,  G06F8/41 ,  G06F8/77 ,  G06F11/34 ,  G06F17/30

Abstract: Systems, methods, and computer-readable media are provided for a multi-tenant collaborative learning environment, where information from all tenants in a multi-tenant system is collected and used to provide individual tenants with code fixes and/or optimization recommendations based on the collected information. Other embodiments may be described and/or claimed.

公开(公告)号：US20210073040A1

公开(公告)日：2021-03-11

申请号：US16566209

申请日：2019-09-10

Applicant: salesforce.com, inc.

Inventor： Brian TOAL ,  Manpreet SINGH

IPC: G06F9/50

Abstract: A system is disclosed. The system includes a resource monitor to monitor a resource utilization of a set of resources of one or more instances, the resource utilization corresponding to a first level of performance and cost and an instance type determiner to, based on the resource utilization, determine if there is an instance type for at least one of the one or more instances, with a resource profile, that will provide a second level of performance and cost that is closer to a default level of performance and cost than the first level of performance and cost. In addition, the system also includes an instance type recommender to, based on the determining, perform one of making and not making a recommendation to replace the instance type of the at least one of the one or more instances.

公开(公告)号：US20200334540A1

公开(公告)日：2020-10-22

申请号：US16840783

申请日：2020-04-06

Applicant: salesforce.com, inc.

Inventor： Ajay Krishna BORRA ,  Manpreet SINGH

IPC: G06N3/08 ,  G06F11/30 ,  G06N3/04 ,  G06K9/62

Abstract: Systems, device and techniques are disclosed for outlier discovery system selection. A set of time series data including time series data objects may be received. A sample of time series data objects may be extracted from the time series data. The sample of time series data objects may be decomposed into sub-components. Statistical classification may be used to select an outlier discovery system based on the sub-components. A neural network may be used to select an outlier discovery system based on the sub-components. A level of error of the neural network may be determined based on a comparison of the outlier discovery system selection made using statistical classification and the outlier discovery system selection made by the neural network. Weight of the neural network may be updated based on the level of error of the neural network.