US 12,233,797 B2
System and method for a voice-activated user support system
Gaurav Talwar, Novi, MI (US); Alaa M. Khamis, Courtice (CA); Xu Fang Zhao, LaSalle (CA); and Kenneth R. Booker, Grosse Pointe Woods, MI (US)
Assigned to GM Global Technology Operations LLC, Detroit, MI (US)
Filed by GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed on Sep. 16, 2022, as Appl. No. 17/946,477.
Prior Publication US 2024/0092292 A1, Mar. 21, 2024
Int. Cl. B60R 16/037 (2006.01); G10L 15/22 (2006.01); G10L 25/63 (2013.01)
CPC B60R 16/0373 (2013.01) [G10L 15/22 (2013.01); G10L 25/63 (2013.01); G10L 2015/223 (2013.01); G10L 2015/225 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A user support system for a vehicle, comprising:
a microphone, and a visual display arranged in a vehicle cabin;
a controller in communication with the microphone and the visual display;
the controller including an instruction set, the instruction set being executable to:
receive, via the microphone, a voice-based request from a user;
employ a virtual assistant to determine a user interaction in real time and to determine a specific intent for the voice-based request, including capturing metadata;
determine, via a user interaction routine, a user interaction parameter associated with the virtual assistant based upon the voice-based request from the user;
determine, via a user sentiment analysis routine, a user satisfaction parameter associated with the virtual assistant based upon the voice-based request from the user, wherein the user interaction parameter is determined based upon a quantity of dialogue iterations, a system latency time, and a recognition of a domain to determine the specific intent for the voice-based request;
respond in real-time to the voice-based request based upon the user satisfaction parameter and the user interaction parameter associated with the virtual assistant; and
transfer the voice-based request from the user to a second assistant based upon the user satisfaction parameter and the user interaction parameter;
wherein the second assistant comprises a live advisor, and wherein the controller is arranged to transfer the voice-based request from the user to the live advisor in real-time when either the user satisfaction parameter is less than a first threshold or the user interaction parameter is less than a second threshold; and
wherein the user interaction parameter is inversely related to the quantity of dialogue iterations, the system latency time, and an inability to recognize the domain.