US 12,334,073 B2
System and method for speech processing based on response content
Emad Noorizadeh, Plano, TX (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Oct. 16, 2023, as Appl. No. 18/487,817.
Application 18/487,817 is a continuation of application No. 17/363,702, filed on Jun. 30, 2021, granted, now 11,830,489.
Prior Publication US 2024/0038237 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 16/93 (2019.01)
CPC G10L 15/22 (2013.01) [G06F 16/94 (2019.01); G10L 2015/223 (2013.01); G10L 2015/227 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for determining intent associated with a voice signal, comprising:
a processor configured to:
receive a first voice signal, wherein the first voice signal indicates to perform a task;
communicate a first response to the first voice signal, wherein the first response comprises a hyperlink associated with a particular webpage that is used to perform the task;
extract a first set of keywords from the first response;
receive a second voice signal, wherein the second voice signal indicates whether to access the hyperlink;
extract a second set of keywords from the second voice signal;
determine whether or not the first response is annotated with text conveying a first intent;
in response to determining that the first response is not annotated with the text:
compare the first set of keywords with the second set of keywords;
determine whether the first set of keywords corresponds to the second set of keywords; and
in response to determining that the first set of keywords corresponds to the second set of keywords, activate the hyperlink to launch the particular webpage to perform the task; and
a memory, operably coupled with the processor, and operable to store the first voice signal, the second voice signal, and the first response.