US 12,254,881 B2
Word selection for natural language interface
Andrew Starr McCraw, Aliso Viejo, CA (US); Sheena Yang, Redondo Beach, CA (US); Sampat Biswas, Irvine, CA (US); Ryan Summers, Tustin, CA (US); and Michael Sean McPhillips, Arcadia, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 6, 2023, as Appl. No. 18/329,876.
Application 18/329,876 is a continuation of application No. 17/195,177, filed on Mar. 8, 2021, granted, now 11,676,597.
Application 17/195,177 is a continuation of application No. 16/357,264, filed on Mar. 18, 2019, granted, now 10,978,069, issued on Apr. 13, 2021.
Prior Publication US 2023/0377574 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 40/247 (2020.01); G10L 15/18 (2013.01); G10L 15/30 (2013.01)
CPC G10L 15/22 (2013.01) [G06F 40/247 (2020.01); G10L 15/1815 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining first input data representing a natural language input;
determining first data representing a meaning corresponding to a system response to the natural language input;
determining, based at least in part on at least a first word included in the natural language input, second data representing a style;
determining, based at least in part on the first data and the second data, a second word associated with the meaning and with the style; and
generating first output data to be output as the system response including the second word.