US 11,990,122 B2
User-system dialog expansion
Ruhi Sarikaya, Redmond, WA (US); Hung Tuan Pham, Kirkland, WA (US); Savas Parastatidis, Kirkland, WA (US); Dean Curtis, Seattle, WA (US); Pushpendre Rastogi, Seattle, WA (US); Nitin Ashok Jain, Seattle, WA (US); John Arland Nave, Bellevue, WA (US); Abhinav Sethy, Seattle, WA (US); Arpit Gupta, Seattle, WA (US); Mayank Kumar, Sammamish, WA (US); Nakul Dahiwade, Seattle, WA (US); Arshdeep Singh, Seattle, WA (US); Nikhil Reddy Kortha, Seattle, WA (US); and Rohit Prasad, Lexington, MA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Dec. 7, 2022, as Appl. No. 18/076,987.
Application 18/076,987 is a continuation of application No. 17/024,959, filed on Sep. 18, 2020, granted, now 11,527,237.
Prior Publication US 2023/0215425 A1, Jul. 6, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/26 (2006.01); G06F 16/9032 (2019.01); G10L 13/08 (2013.01); G10L 15/16 (2006.01)
CPC G10L 15/16 (2013.01) [G06F 16/90332 (2019.01); G10L 13/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving first input data representing a first natural language user input of a first dialog session;
processing the first input data to determine natural language understanding (NLU) output data representing the first natural language user input;
sending the NLU output data to a first processing component;
receiving, from the first processing component, first output data responsive to the first natural language user input;
determining first data representing context information of the first dialog session;
processing the first data using a trained machine learning (ML) model to determine information representing a first system functionality is to be output, wherein the trained ML model is based on at least second data corresponding to a second dialog session and indicating a second processing component capable of performing a second system functionality determined to result in receipt of a subsequent user input associated with the second dialog session;
determining second output data representing the information; and
sending the second output data to a first device for presentation.