US 12,254,885 B2
Detecting and handling failures in other assistants
Victor Carbune, Zurich (CH); and Matthew Sharifi, Kilchberg (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Jan. 13, 2023, as Appl. No. 18/097,157.
Application 18/097,157 is a continuation of application No. 17/087,358, filed on Nov. 2, 2020, granted, now 11,557,300.
Claims priority of provisional application 63/093,163, filed on Oct. 16, 2020.
Prior Publication US 2023/0169980 A1, Jun. 1, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/32 (2013.01); G10L 15/22 (2006.01)
CPC G10L 15/32 (2013.01) [G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
determining, by a first automated assistant executed at least in part on a computing device operated by a user, that a second automated assistant provided an inaccurate result in response to a request of the user that was directed to the second automated assistant, wherein determining that the second automated assistant provided the inaccurate result in response to the request of the user that was directed to the second automated assistant comprises:
processing, by the first automated assistant, audio data that captures an initial response provided by the second automated assistant responsive to the request; and
determining, by the first automated assistant, and based on the processing of the audio data, that the initial response is the inaccurate result; and
in response to the first automated assistant determining that the second automated assistant provided the inaccurate result in response to the request of the user that was directed to the second automated assistant;
automatically determining, by the first automated assistant, a response that fulfills the request of the user, wherein automatically determining the response that fulfills the request of the user comprises automatically processing, by the first automated assistant, cached audio data, or features of the cached audio data, that captures a spoken utterance of the user comprising the request responsive to which the second automated assistant provided the inaccurate result; and
automatically providing, by the first automated assistant to the user, the response that fulfills the request of the user.