公开(公告)号：US10534965B2

公开(公告)日：2020-01-14

申请号：US15926745

申请日：2018-03-20

Applicant: Amazon Technologies, Inc.

Inventor： Nitin Singhal ,  Vivek Bhadauria ,  Ranju Das ,  Gaurav D. Ghare ,  Roman Goldenberg ,  Stephen Gould ,  Kuang Han ,  Jonathan Andrew Hedley ,  Gowtham Jeyabalan ,  Vasant Manohar ,  Andrea Olgiati ,  Stefano Stefani ,  Joseph Patrick Tighe ,  Praveen Kumar Udayakumar ,  Renjun Zheng

IPC: G06K9/00 ,  G06T7/00

Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.

公开(公告)号：US20190156124A1

公开(公告)日：2019-05-23

申请号：US15926745

申请日：2018-03-20

Applicant: Amazon Technologies, Inc.

Inventor： Nitin SINGHAL ,  Vivek BHADAURIA ,  Ranju DAS ,  Gaurav D. GHARE ,  Roman GOLDENBERG ,  Stephen GOULD ,  Kuang HAN ,  Jonathan Andrew HEDLEY ,  Gowtham JEYABALAN ,  Vasant MANOHAR ,  Andrea OLGIATI ,  Stefano STEFANI ,  Joseph Patrick TIGHE ,  Praveen Kumar Udayakumar ,  Renjun ZHANG

IPC: G06K9/00

CPC classification number: G06K9/00744 ,  G06F16/71 ,  G06K9/00228 ,  G06K9/00718 ,  G06K9/00765 ,  G06K2009/00738

Abstract: Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.

公开(公告)号：US09860155B1

公开(公告)日：2018-01-02

申请号：US14040188

申请日：2013-09-27

Applicant: Amazon Technologies, Inc.

Inventor： Phillip Scott Segel ,  Michael Leo Weiss ,  Aravindhan Vijayaraghavan ,  Praveen Kumar Udayakumar

IPC: G06F15/16 ,  H04L12/26 ,  G06F12/00

CPC classification number: H04L43/50 ,  H04L43/0876 ,  H04L43/16

Abstract: Techniques described herein provide for real-time observation of utilization of one or more resources by a system in response to an input. The real-time observation by a system may occur in an environment in which end users supply inputs to the system (e.g., a production environment). In various embodiments, a server system may provide a service to a client system. A client system may take advantage of this service by sending an input to the server system. In response, the server system may perform the provisioned service using the input from the client system. In connection with the service, the utilization of resources (e.g., by a process) and/or the client system-supplied input may be recorded, such as when resources are utilized in an unexpected or interesting manner. These records may be used at a later time for testing and analysis.