US 11,769,506 B1Granted

Response orchestrator for natural language interface

AssigneeAmazon Technologies, Inc.

InventorsPrashant Jayaram Thakare, Karthik Parameswaran, Deepak Uttam Shah, Prathyusha Nadella, Janita Shah, Venkat Chakravarthy, Michael Trinh

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Techniques for providing device functionalities using device components are described. A system receives a system-generated directive from a skill system and determines a workflow to execute. The system implements a response orchestrator that operates based on the workflow that includes interception points where cross-cutting functionalities can be invoked as pluggable components. The interception points occur pre-system-generated directive, pre-device-facing directive, post-device-facing directive generation, post-device-facing directive dispatch, and the like. The system supports asynchronous execution, conditional execution, and sequential execution of components. Data determined by the cross functionality components can be used by other components for processing.

Claims20

Dependent claims

A computer-implemented method comprising:

receiving, from a skill component, a first message including a first action and a first payload, the first message being received in response to a first spoken natural language input;
determining, using a first cross functionality component, a first device directive corresponding to the first message, the first device directive including first output data included in the first payload, first data indicative of a first device component to be used to present the first output data and the first action, wherein the first cross functionality component is configured to determine device directives based on messages received from the skill component;
sending the first device directive to a device, receipt of the first device directive causing the device to execute the first device component to present the first output data;
determining, using definition data associated with a second cross functionality component, that the second cross functionality component is to execute after sending the first device directive, wherein the second cross functionality component is configured to disable wakeword-free interactions with the device based on the first device directive;
and
sending, to the second cross functionality component, the first device directive, wherein the second cross functionality component disables wakeword-free interactions with the device based at least in part on the first data and the first action being included in the first device directive.

3 more elements

A computer-implemented method comprising:

receiving, from a first component, a first message including a first action and a first payload;
determining, using a first cross functionality component, a first device directive corresponding to the first message, the first device directive including first output data included in the first payload and first data indicative of a first device component to be used to perform the first action, wherein the first cross functionality component is configured to determine device directives based on received messages;
sending, to a device, the first device directive to cause the device to perform the first action, using the first device component, with respect to at least a portion of the first output data;
determining that a second cross functionality component is to execute after the first device directive is sent, wherein the second cross functionality component is configured to disable wakeword-free interactions with the device;
and
sending, to the second cross functionality component, the first device directive, wherein the second cross functionality component disables wakeword-free interactions with the device based at least in part on the first data.

3 more elements

A computing system comprising:

at least one processor;
and
at least one memory comprising instructions that, when executed by the at least one processor, cause the computing system to:
receive, from a first component, a first message including a first action and a first payload;
determine, using a first cross functionality component, a first device directive corresponding to the first message, the first device directive including first output data included in the first payload and first data indicative of a first device component to be used to perform the first action, wherein the first cross functionality component is configured to determine device directives based on received messages;
send, to a device, the first device directive to cause the device to perform the first action, using the first device component, with respect to at least a portion of the first output data;
determine that a second cross functionality component is to execute after the first device directive is sent, wherein the second cross functionality component is configured to disable wakeword-free interactions with the device;
and
send, to the second cross functionality component, the first device directive, wherein the second cross functionality component disables wakeword-free interactions with the device based at least in part on the first data.

6 more elements

Dependencies are inferred from the claim text.