公开(公告)号：US11887596B2

公开(公告)日：2024-01-30

申请号：US17945320

申请日：2022-09-15

Applicant: Amazon Technologies, Inc.

Inventor： Rohin Dabas ,  Troy Dean Schuring ,  Rashmi Tonge ,  Michael James Montgomery ,  Kevindra Pal Singh ,  Adam Baran ,  David Thomas ,  Nnenna Eleanya Okwara

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/18 ,  G10L15/183

CPC classification number: G10L15/22 ,  G10L15/1815 ,  G10L15/30 ,  G10L15/183 ,  G10L15/1822 ,  G10L2015/223 ,  G10L2015/228

Abstract: Described herein is a system for enabling a user to perform complex goals using multiple skills/applications of an intelligent assistant device. Skills may register as consumers of an action or providers of an action, and the consumer skills may be configured to invoke provider skills to perform actions. The system receives a request to perform an action from a skill along with some action data. The system validates the action data, selects another skill to perform the action, and forwards the request to the selected skill to perform the action.

公开(公告)号：US11551681B1

公开(公告)日：2023-01-10

申请号：US16714108

申请日：2019-12-13

Applicant: Amazon Technologies, Inc.

Inventor： Rajesh Kumar Pandey ,  Ruhi Sarikaya ,  Shubham Katiyar ,  Arun Kumar Thenappan ,  Isaac Joseph Madwed ,  Jihwan Lee ,  David Thomas ,  Julia Kennedy Nemer ,  Mohamed Farouk AbdelHady ,  Joe Pemberton ,  Young-Bum Kim ,  Arima Vu Ram Thayumanavar ,  Wangyao Ge

IPC: G10L15/22 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183 ,  G06F16/245 ,  G06N20/00 ,  G06F16/22

Abstract: Devices and techniques are generally described for a speech processing routing architecture. In various examples, first data comprising a first feature definition is received. The first feature definition may include a first indication of first source data and first instructions for generating feature data using the first source data. In various examples, the feature data may be generated according to the first feature definition. In some examples, a speech processing system may receive a first request to process a first utterance. The feature data may be retrieved from a non-transitory computer-readable memory. The speech processing system may determine a first skill for processing the first utterance based at least in part on the feature data.

公开(公告)号：US11467835B1

公开(公告)日：2022-10-11

申请号：US16199129

申请日：2018-11-23

Applicant: Amazon Technologies, Inc.

Inventor： Sudipta Sengupta ,  Poorna Chand Srinivas Perumalla ,  Jalaja Kurubarahalli ,  Samuel Oshin ,  Cory Pruce ,  Jun Wu ,  Eftiquar Shaikh ,  Pragya Agarwal ,  David Thomas ,  Karan Kothari ,  Daniel Evans ,  Umang Wadhwa ,  Mark Klunder ,  Rahul Sharma ,  Zdravko Pantic ,  Dominic Rajeev Divakaruni ,  Andrea Olgiati ,  Leo Dirac ,  Nafea Bshara ,  Bratin Saha ,  Matthew Wood ,  Swaminathan Sivasubramanian ,  Rajankumar Singh

IPC: G06F3/00 ,  G06F9/30 ,  G06F9/38

Abstract: Techniques for partitioning data flow operations between execution on a compute instance and an attached accelerator instance are described. A set of operations supported by the accelerator is obtained. A set of operations associated with the data flow is obtained. An operation in the set of operations associated with the data flow is identified based on the set of operations supported by the accelerator. The accelerator executes the first operation.