公开(公告)号：US10991364B1

公开(公告)日：2021-04-27

申请号：US16134492

申请日：2018-09-18

Applicant: Amazon Technologies, Inc.

Inventor： Thomas Jay Hoover ,  Srinivas Palla ,  Anupam Kumar ,  Aravindhan Rathakrishnan ,  Andrei Dorin Zaharia

IPC: G10L15/00 ,  G10L15/18 ,  G10L15/30 ,  G10L15/22 ,  G06F16/2452 ,  G06F40/295 ,  G10L15/08

Abstract: Systems including a universal context aggregator configured to pre-fetch context information that may be used to perform various processes with respect to a user input are described. The aggregator may have access to data representing what context information components of the system routinely request in various situations. When a particular situation is present, prior to being queried, the aggregator may pre-fetch context information that the aggregator is likely to be queried for.

公开(公告)号：US11922938B1

公开(公告)日：2024-03-05

申请号：US17532586

申请日：2021-11-22

Applicant: Amazon Technologies, Inc.

Inventor： Yaser Khan ,  Piyush Kandpal ,  Ritesh Patel ,  Mark Lawrence ,  Srinivas Palla ,  Ashish Rangole ,  Jason Wang

IPC: G10L15/00 ,  G10L13/02 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L15/32

CPC classification number: G10L15/22 ,  G10L13/02 ,  G10L15/1815 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/223

Abstract: A multi-assistant speech-processing system that centrally determines multiple execution plans to respond to a user input. A central component determines whether a particular input should be processed using a requested assistant or a different assistant or should be terminated. Assistant handoff may be determined based on system policies as well as user input-specific data. A ranked list of execution options may be supplemented by augmented data corresponding to messages to a user. The system may attempt to execute plans in the ranked order until a plan succeeds.

公开(公告)号：US12248463B1

公开(公告)日：2025-03-11

申请号：US17393139

申请日：2021-08-03

Applicant: Amazon Technologies, Inc.

Inventor： Srinivas Palla ,  Manoj Mandam ,  Maitri Prraveg Shroff

IPC: G06F16/00 ,  G06F16/242 ,  G06F16/2453 ,  G06F16/248 ,  G10L15/22 ,  G10L15/30

Abstract: Devices and techniques are generally described for query enhancements for a contextual data aggregator. In some examples, a context aggregator component may receive from a first computing device, a first query directed to a graph database. In some examples, the first query may include a first sub-query and a second sub-query. In some cases, the context aggregator component may determine that a first input to the first sub-query includes first output data from the second sub-query. In various examples, the first output data may be determined from the second sub-query. In further examples, the first output data may be provided from the second sub-query as the first input to the first sub-query to generate first result data. In various examples, the first result data may be sent to the first computing device.