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.