US 12,406,147 B2
Dialog management for large language model- based (LLM-based) dialogs
Martin Baeuml, Wollerau (CH); Alexander Bailey, Wollerau (CH); Jonas Bragagnolo, Affoltern am Albis (CH); Florent D'Halluin, Zurich (CH); and Trevor Strohman, Sunnyvale, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Mar. 17, 2023, as Appl. No. 18/123,141.
Claims priority of provisional application 63/451,868, filed on Mar. 13, 2023.
Prior Publication US 2024/0311575 A1, Sep. 19, 2024
Int. Cl. G10L 15/22 (2006.01); G06F 40/35 (2020.01); G06N 20/00 (2019.01)
CPC G06F 40/35 (2020.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
receiving natural language (NL) based input associated with a client device, the NL based input being received during a given turn of an ongoing dialog;
generating, based on processing the NL based input using a large language model (LLM), NL based output that is responsive to the NL based input;
causing the NL based output that is responsive to the NL based input to be rendered at the client device;
receiving subsequent NL based input associated with the client device, the subsequent NL based input being received during a given subsequent turn of the ongoing dialog;
determining, based on the NL based output and/or the subsequent NL based input, whether to modify a corresponding NL based output threshold for generating subsequent NL based output that is responsive to the subsequent NL based input received during the given subsequent turn of the ongoing dialog; and
in response to determining to modify the corresponding NL based output threshold for generating the subsequent NL based output that is responsive to the subsequent NL based input received during the given subsequent turn of the ongoing dialog:
modifying the corresponding NL based output threshold to generate a corresponding modified NL based output threshold for generating the subsequent NL based output that is responsive to the subsequent NL based input received during the given subsequent turn of the ongoing dialog;
generating, based on processing the subsequent NL based input using the LLM and based on the corresponding modified NL based output threshold for generating the subsequent NL based output that is responsive to the subsequent NL based input received during the given subsequent turn of the ongoing dialog, the subsequent NL based output that is responsive to the subsequent NL based input; and
causing the subsequent NL based output that is responsive to the subsequent NL based input to be rendered at the client device.