US 12,080,268 B1
Generating event output
Vinaya Nadig, Bothell, WA (US); Rafael Colorado Vargas, Austin, TX (US); Yugandhar Maram, Redmond, WA (US); and Samarth Bhargava, Redmond, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Mar. 30, 2020, as Appl. No. 16/834,800.
Int. Cl. G10L 13/00 (2006.01); G06F 9/54 (2006.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01)
CPC G10L 13/00 (2013.01) [G06F 9/542 (2013.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving input data representing a natural language input, the input data associated with a first user profile;
processing the input data using a natural language understanding (NLU) component to determine an intent to receive a first notification when an event occurs, the NLU component including at least one machine learned model;
determining, using the input data, first trigger data representing the event;
receiving event data indicating occurrence of the event;
determining, using the first trigger data, that the event data triggers the first notification with respect to the first user profile;
determining first preference data corresponding to the first user profile;
determining a first notification template using the first trigger data and the first preference data;
determining first output data using the first notification template and the event data;
determining to emphasize a portion of the first output data based at least in part on the first preference data;
processing, using text-to-speech (TTS) processing, the first output data to determine first output audio data, a portion of the first output audio data corresponding to the portion of the first output data being emphasized;
determining an output type corresponding to the first notification template;
determining a device output capability corresponding to the output type; determining a first device associated with the first user profile has the device output capability;
causing the first device to present the first output audio data;
determining, using second trigger data, that the event data triggers a second notification with respect to a second user profile using a second notification template;
determining second output data using a second notification template and the event data; and
causing a second device associated with the second user profile to present an output corresponding to the second output data.