公开(公告)号：US10028405B1

公开(公告)日：2018-07-17

申请号：US14494437

申请日：2014-09-23

Applicant: Amazon Technologies, Inc.

Inventor： Jignesh Gandhi ,  Robert Anthony Smith ,  Dong Wang ,  Ross Michael Wampler ,  Wei Liu ,  Junlin Yi ,  Justin Michael Dodson ,  Adam Thomas Creswell

IPC: H05K7/14 ,  H05K7/18

Abstract: A data center rack allocation system allocates rack computer systems to be installed at particular rack positions based at least in part upon correlating infrastructure support requirements of the rack computer systems with infrastructure support capacities associated with the rack position. Such allocation can enable rapid incremental deployment of infrastructure and rack computer systems in a data center with flexibility to allocate various types of rack computer systems, with various support requirements, to available infrastructure. The system can identify infrastructure connections available to provide certain types of support capacity and can associate such connections with various rack positions in data centers. The system can determine the support requirements of a rack computer system in response to a determination that the rack computer system is presently inbound for delivery to a data center. The system can allocate particular infrastructure connections to a rack computer system allocated to a rack position.

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.