公开(公告)号：US10977711B1

公开(公告)日：2021-04-13

申请号：US15861496

申请日：2018-01-03

Applicant: Amazon Technologies, Inc.

Inventor： Prashant Verma ,  Anoop Balakrishnan ,  Janick M. Bernet

IPC: G06Q30/00 ,  G06Q30/06 ,  G06K9/62 ,  G06Q30/02 ,  G06N20/00

Abstract: An intermediate result set is obtained from a first machine learning model whose input data set comprises values of a first set of properties associated with a session of operations. The intermediate result and a second set of properties associated with the session are provided as input to a second machine learning model. A value of at least one property of the first set is determined before a value of at least one property of the second set is determined. A particular action recommendation, based at least in part on output generated by the second machine learning model, is implemented.

公开(公告)号：US10743036B1

公开(公告)日：2020-08-11

申请号：US15993466

申请日：2018-05-30

Applicant: Amazon Technologies, Inc.

Inventor： Ryan Farris ,  Prashant Verma ,  Ronil Sudhir Mokashi

IPC: H04N21/231 ,  H04N21/25 ,  H04N21/235

Abstract: In some embodiments, a system is provided, and computer-executable instructions cause the system to: receive, at an edge server of a content delivery network (CDN), a request for a first video and a request for a second video; determine that the first video is not cached and that the second video is cached; request the first video from the origin server and log a cache miss; obtain the first video from the origin server and send responsive to the request; send the second video responsive to the request and log a cache hit; obtain a metric indicative of the volume of cache misses, including for the first and second videos, across edge servers of the CDN; and determine, based on the metric, an amount by which to scale resources implementing the origin.

公开(公告)号：US10699023B1

公开(公告)日：2020-06-30

申请号：US15872462

申请日：2018-01-16

Applicant: Amazon Technologies, Inc.

Inventor： Ronil Sudhir Mokashi ,  Francesco De Martino ,  Shreeja Kumar ,  Prashant Verma ,  Vijaya Rama Reddy Kistampalli ,  Sorin Manole ,  Andrii Galyuzin ,  Cristi Ursachi

IPC: G06F21/62 ,  H04L29/06 ,  G06N20/00

Abstract: Various approaches enable real-time data encryption using an encryption profile that enables a customer to specify the type of data to encrypt and the encryption keys to use when encrypting the data. A profile editor that a customer (e.g., a customer of a content provider) can use to create and manage encryption profiles that can be used to encrypt data can be provided. A profile editor or set of request parameters can allow customers to configure content distributions and associate encryption keys with a profile to encrypt user sensitive data. A customer can select, define, and/or modify the encryption options or other configuration settings for a profile. Once set, the profile can be used to securely ingest user-submitted data to customers' web servers. For example, a request can be analyzed to determine data fields of the request. Based on one or more profiles associated with the customer, the data in those fields can be encrypted with the appropriate encryption key per the profiles.