公开(公告)号：US11050706B2

公开(公告)日：2021-06-29

申请号：US15466664

申请日：2017-03-22

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana

IPC: G06F15/16 ,  H04L29/12

Abstract: Network performance data, such as routing trip time between autonomous systems and data centers, is gathered and aggregated to determine optimal mappings of autonomous systems and data centers. Autonomous system based DNS steering may be automated by repeating a life cycle of determining the optimal mappings. Data delivery strategies are applied to a portion of a network to deliver content using the optimal mappings.

公开(公告)号：US10795954B2

公开(公告)日：2020-10-06

申请号：US15836679

申请日：2017-12-08

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana

IPC: G06F16/9535 ,  G06F16/9038 ,  G06F16/242

Abstract: Data analysis is performed through a series of commands that apply functions to an initial scope of data. In a client-server architecture, a data analyst may interact with and view a scope of data through a series of commands. Query formation may be performed at a server to generate reports of data to be presented at the client.

公开(公告)号：US10778522B2

公开(公告)日：2020-09-15

申请号：US15841099

申请日：2017-12-13

Applicant: salesforce.com, inc.

Inventor： Gabriel Tavridis ,  Kartikeya Chandrayana ,  Maria Garcia Cerdeno ,  Russell Larsen ,  Satish Raghunath ,  Shauli Gal ,  Wojciech Koszek

IPC: G06F15/177 ,  H04L12/24 ,  H04L12/26 ,  G06N20/00

Abstract: A dynamic approach to optimizing configuration of network parameters is presented. By gathering operational contexts and aggregating optimized network performance data against a baseline, a training data set may be generated. Client-side policies are determined, in part, by applying machine learning techniques on the training data set to achieve desired outcomes. Data delivery strategies are compiled at user devices to deliver content using the optimized network configuration values based on the operating contexts.

公开(公告)号：US10560332B2

公开(公告)日：2020-02-11

申请号：US16273150

申请日：2019-02-12

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana ,  Tejaswini Ganapathi

IPC: H04L12/26 ,  H04L12/24 ,  H04L29/06 ,  H04L29/08

Abstract: An adaptive multi-phase approach to estimating network parameters is presented. By gathering and aggregating raw network traffic data and comparing against default network parameters, a training data set may be generated. A black box optimization may be used in tandem with a supervised learning algorithm to bias towards better choices and eventually pick network parameters which optimize performance. Data delivery strategies are applied to deliver content using the optimized network policies based on the estimated parameters.

公开(公告)号：US20190173760A1

公开(公告)日：2019-06-06

申请号：US16273150

申请日：2019-02-12

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana ,  Tejaswini Ganapathi

IPC: H04L12/24 ,  H04L29/08 ,  H04L29/06 ,  H04L12/26

CPC classification number: H04L41/0893 ,  H04L41/046 ,  H04L43/16 ,  H04L67/02 ,  H04L67/28 ,  H04L67/2833 ,  H04L69/16

Abstract: An adaptive multi-phase approach to estimating network parameters is presented. By gathering and aggregating raw network traffic data and comparing against default network parameters, a training data set may be generated. A black box optimization may be used in tandem with a supervised learning algorithm to bias towards better choices and eventually pick network parameters which optimize performance. Data delivery strategies are applied to deliver content using the optimized network policies based on the estimated parameters.

公开(公告)号：US20190141542A1

公开(公告)日：2019-05-09

申请号：US15803557

申请日：2017-11-03

Applicant: salesforce.com, inc.

Inventor： Tejaswini Ganapathi ,  Satish Raghunath ,  Shauli Gal

IPC: H04W24/02 ,  G06F15/18 ,  H04L12/24 ,  H04L29/06 ,  H04W24/08

CPC classification number: H04W24/02 ,  G06N20/00 ,  H04L41/0823 ,  H04L41/0893 ,  H04L41/14 ,  H04L69/16 ,  H04W24/08

Abstract: A polytope is generated, based on expert input, in an output parameter space. The polytope constrains network parameters to value ranges that are a subset of possible values represented in the output parameter space. Network traffic data associated with data requests to computer applications based on static policies is collected over a time block. Each static policy in the plurality of static policies comprises parameter values, for network parameters in the set of network parameters, that are constrained to be within the polytope. Machine learning is used to estimate best parameter values for the network parameters that are constrained to be within the polytope. The best parameter values are verified by comparing to parameter values determined from a black box optimization. The best parameter values are propagated to be used by user devices to make new data requests to the computer applications.

公开(公告)号：US20190052597A1

公开(公告)日：2019-02-14

申请号：US15674945

申请日：2017-08-11

Applicant: salesforce.com, inc.

Inventor： Satish Raghunath ,  Kartikeya Chandrayana ,  Shauli Gal

IPC: H04L29/12 ,  H04L12/24 ,  G06N99/00

Abstract: Network performance data metrics are gathered and aggregated. A policy engine chooses an optimal selection of networking protocol based on the metrics. Data delivery strategies are applied to a portion of a network to deliver content using the received choice of networking protocol policy optimized by machine learning techniques.

公开(公告)号：US20180331908A1

公开(公告)日：2018-11-15

申请号：US15593635

申请日：2017-05-12

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana ,  Tejaswini Ganapathi

IPC: H04L12/24 ,  H04L29/06 ,  H04L29/08 ,  H04L12/26

CPC classification number: H04L41/0893 ,  H04L41/046 ,  H04L43/16 ,  H04L67/02 ,  H04L67/28 ,  H04L67/2833 ,  H04L69/16

Abstract: An adaptive multi-phase approach to estimating network parameters is presented. By gathering and aggregating raw network traffic data and comparing against default network parameters, a training data set may be generated. A black box optimization may be used in tandem with a supervised learning algorithm to bias towards better choices and eventually pick network parameters which optimize performance. Data delivery strategies are applied to deliver content using the optimized network policies based on the estimated parameters.

公开(公告)号：US20180278571A1

公开(公告)日：2018-09-27

申请号：US15466664

申请日：2017-03-22

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana

IPC: H04L29/12 ,  H04L12/841

CPC classification number: H04L61/1511

Abstract: Network performance data, such as routing trip time between autonomous systems and data centers, is gathered and aggregated to determine optimal mappings of autonomous systems and data centers. Autonomous system based DNS steering may be automated by repeating a life cycle of determining the optimal mappings. Data delivery strategies are applied to a portion of a network to deliver content using the optimal mappings.

公开(公告)号：US20230065718A1

公开(公告)日：2023-03-02

申请号：US17894121

申请日：2022-08-23

Applicant: Salesforce.com, Inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana ,  Gabriel Tavridis ,  Kevin Wang

IPC: H04L43/16 ,  H04L43/08 ,  H04L41/046 ,  H04L41/0816 ,  H04L43/04 ,  H04L43/12

Abstract: A data-driven approach to network performance diagnosis and root-cause analysis is presented. By collecting and aggregating data attribute values across multiple components of a content delivery system and comparing against baselines for points of inspection, network performance diagnosis and root-cause analysis may be prioritized based on impact on content delivery. Recommended courses of action may be determined and provided based on the tracked network performance analysis at diagnosis points.