Amazon Technologies, Inc.

Mark Lawrence

Trausti Thor Kristjansson

Andrew Dean Christian

Srivatsan Kandadai

Anna Chen Santos

Miroslav Ristic

Joseph Pedro Tavares

Ashish Rangole

Valere Joseph Vanderschaegen

Andrew Smith

Melanie C B Gens

Yaser Khan

Srinivas Palla

Balsa Laban

Samer A Sarhan Hussein

Jyoti Chhabra

Zenon Harley

Raja Bose

Kent V Lam

Piyush Kandpal

Jason Wang

Ritesh Patel

Ramya Chaganti

Ryan McCrate

Zexiong Yan

Matthew Williams

Sergii Kovba

Systems and methods for selective on-device latency reduction include receiving data requesting that an application associated with a user device be utilized and identifying on-device functionality enabled for the application. Data may be generated that includes a subset of content associated with the on-device functionality and is configured to be utilized by a device in the environment to perform the on-device functionality. This data may be sent to the device in question and may configure the device to process input data associated with the on-device functionality and utilize commands associated with the subset of content based at least in part on processing the input data with the on-device functionality.

Selective on-device latency reduction

Techniques for enabling access in a multi-assistant speech processing system are described, where a first assistant system may use components of a second assistant system as data processing components. Runtime operational data and user input data related to the first assistant may be kept separate from the processing data and input data related to the second assistant by propagating a first account ID, for user inputs directed to the first assistant, through the processing pipeline, and using a second account for user inputs directed to the second assistant. A mapping between the first account ID and the second account ID may be accessible to a select number of system components. Handoffs between the two assistants are handled in a manner where data related to one assistant is not accessible by the other assistant.

Data processing in a multi-assistant system

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.

Access to multiple virtual assistants

Growing community of inventors

Bainbridge Island, WA, United States of America

Mark Lawrence