公开(公告)号：US11580126B1

公开(公告)日：2023-02-14

申请号：US16915544

申请日：2020-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Ankit Sultania ,  Eric Brian Ceres ,  Karthik Saligrama Shreeram ,  Yong Yuan ,  Saurabh Kumar Singh ,  Priyank Mundra

IPC: G06F16/2458 ,  G06F16/23 ,  G06F16/93 ,  G06F16/22 ,  G06F16/242

Abstract: Techniques for request throttling in a provider network environment are described. A throttle handler controls whether requests will be processed through maintaining a token-based record, per type of request, having a token value indicative of a number of requests that can be processed over a time period. For a request, the token value of the token-based record corresponding to the request type is updated based on calculating an elapsed time between a last update time of the token-based record and the current time, calculating an intermediate token value as the existing token value plus a value of the elapsed time multiplied by a rate, and updating the token value to be the minimum between the intermediate token value and a burst value. The request is serviced when the updated token value is determined to be greater than or equal to a number of tokens needed to perform the request.

公开(公告)号：US11366855B2

公开(公告)日：2022-06-21

申请号：US16697948

申请日：2019-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Jean-Pierre Dodel ,  Zhiheng Huang ,  Xiaofei Ma ,  Ramesh M. Nallapati ,  Krishnakumar Rajagopalan ,  Milan Saini ,  Sudipta Sengupta ,  Saurabh Kumar Singh ,  Dimitrios Soulios ,  Ankit Sultania ,  Dong Wang ,  Zhiguo Wang ,  Bing Xiang ,  Peng Xu ,  Yong Yuan

IPC: G06F16/00 ,  G06F16/901 ,  G06N3/04 ,  G06F16/2457 ,  G06F16/903

Abstract: Techniques for searching documents are described. An exemplary method includes receiving a document search query; querying at least one index based upon the document search query to identify matching data; fetching the identified matched data; determining one or more of a top ranked passage and top ranked documents from the set of documents based upon one or more invocations of one or more machine learning models based at least on the fetched identified matched data and the document search query; and returning one or more of the top ranked passage and the proper subset of documents.