-
公开(公告)号:US20230169079A1
公开(公告)日:2023-06-01
申请号:US17547831
申请日:2021-12-10
Applicant: Amazon Technologies, Inc.
Inventor: Gaurav Saxena , Balakrishnan Narayanaswamy , Ippokratis Pandis , Naresh Chainani , Mohammad Rezaur Rahman , Davide Pagano , Fabian Oliver Nagel
IPC: G06F16/2453
CPC classification number: G06F16/24545 , G06F16/24537
Abstract: Scaling of query processing resources for efficient utilization and performance is implemented for a database service. A query is received via a network endpoint associated with a database managed by a database service. Respective response times predicted for the query using different query processing configurations available to perform the query are determined. Those query processing configurations with response times that exceed a variability threshold determined for the query may be excluded. A remaining query processing configuration may then be selected to perform the query.
-
公开(公告)号:US11636124B1
公开(公告)日:2023-04-25
申请号:US17105201
申请日:2020-11-25
Applicant: Amazon Technologies, Inc.
Inventor: Balakrishnan Narayanaswamy , Gokul Soundararajan , Jiayuan Chen , Yannis Papakonstantinou , Vuk Ercegovac , George Constantin Caragea , Sriram Krishnamurthy , Nikolaos Koulouris
IPC: G06F16/00 , G06F16/2458 , G06F16/2453 , G06K9/62 , G06N20/00 , G06F16/28
Abstract: A database system may include a machine learning model which may be used to perform various data analytics for data stored in the database system. In response to a request to invoke the machine learning model to generate a prediction from data stored in the database system, the database system may perform one or more optimization operations, as part of a query plan, to prepare the data to make it suitable for use by the machine learning model.
-
公开(公告)号:US10860629B1
公开(公告)日:2020-12-08
申请号:US15943287
申请日:2018-04-02
Applicant: Amazon Technologies, Inc.
Inventor: Rashmi Gangadharaiah , Balakrishnan Narayanaswamy , Charles Elkan
IPC: G06F16/332 , H04L12/58 , G06N20/00 , G06F16/33
Abstract: Techniques for intelligent task-oriented multi-turn dialog system automation are described. A seq2seq ML model can be trained using a corpus of training data and a loss function that is based at least in part on a distance to a goal. The seq2seq ML model can be provided a user utterance as an input, and a vector of a plurality of values output by a plurality of hidden units of a decoder of the seq2seq ML model can be used to select one or more candidate responses to the user utterance via a nearest neighbor algorithm. In some embodiments, the specially adapted seq2seq ML model can be trained using unsupervised learning, and can be adapted to select intelligent, coherent agent responses that move a task-oriented dialog toward its completion.
-
-