| CPC G10L 15/22 (2013.01) | 20 Claims |
|
1. A computer-implemented method, comprising:
identifying a plurality of devices connected to a localized network and capable of processing, or performing one or more actions based at least in part on, one or more voice inputs;
identifying a plurality of voice commands, wherein for each respective voice command of the plurality of voice commands, at least one device of the plurality of devices is capable of processing, or performing one or more actions based at least in part on, the respective voice command;
generating a knowledge graph comprising a first plurality of nodes respectively representing the plurality of devices and a second plurality of nodes respectively representing the plurality of voice commands, wherein a relationship between a first node of the first plurality of nodes and a second node of the second plurality of nodes indicates that a first device represented by the first node is capable of processing, or performing one or more actions based at least in part on, a first voice command represented by the second node;
determining device state information for each of the plurality of devices;
determining, using the knowledge graph and based at least in part on the device state information:
the first voice command as a predicted voice command; and
the first device as a particular device of the plurality of devices for which the predicted voice command is intended, wherein the determination of the predicted voice command and the particular device comprises:
accessing the knowledge graph;
based at least in part on determining that the device state information indicates a status for the particular device of currently available, updating the knowledge graph to comprise a third node representing the currently available status of the particular device, wherein the third node is an intermediate node connected to each of the first node representing the particular device and the second node representing the particular voice command; and
using the updated knowledge graph to determine the predicted voice command and to determine the particular device;
receiving voice input; and
based at least in part on receiving the voice input, causing the particular device to perform an action related to the predicted voice command.
|