Amazon Technologies, Inc.

Srinivas Palla

Thomas Jay Hoover

Arun Ponniah Sethuramalingam

Ashish Rangole

Jun Zhao

Sameer Vinod Shah

Yaser Khan

Robert Dreaper McDonald, Jr

Mark Lawrence

Kevin R MacKenzie

Aravindhan Rathakrishnan

Ritesh Patel

Jason Wang

Michael A Shaver

Maitri Prraveg Shroff

Anupam Kumar

Manoj Mandam

Jen-Chieh Tom Tang

Andrei Dorin Zaharia

Piyush Kandpal

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.

Query enhancements for contextual data aggregator

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

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.

Obtaining context data

Various embodiments of a system and method for labor allocation across distinct processes of a materials handling facility are described. Embodiments may include a computer system configured to generate a model of a materials handling facility. The model may indicate, for each of multiple distinct quantities of work processed via a respective materials handling process, a quantity of labor resources processing that quantity of work in accordance with the respective materials handling process. The computer system may evaluate the model to determine that one or more additional labor resources are needed to process a particular quantity of work in accordance with a particular materials handling process. The computer system may select a labor resource processing a different quantity of work in accordance with a different materials handling process and generate an instruction that directs that labor resource to process the particular quantity of work via the particular materials handling process.

System and method for resource allocation across distinct processes of a materials handling facility

Various embodiments of a system and method for integrated stowing and picking in a materials handling facility may include a process control component for monitoring processes within the materials handling facility in order to implement opportunistic picking and stowing. To implement an opportunistic pick, the process control component may determine that an agent has stowed a unit at a respective inventory location. The process control component may determine that the inventory location (or a nearby inventory location) includes a unit designated to be picked and may issue an instruction to opportunistically pick that unit. To implement an opportunistic stow, the process control component may determine that an agent has picked a unit from a respective inventory location. The process control component may determine that a conveyable receptacle utilized by the agent includes a unit that is designated to be stowed and may issue an instruction to opportunistically stow that unit.

System and method for integrated stowing and picking in a materials handling facility

Growing community of inventors

Seattle, WA, United States of America

Srinivas Palla