US 12,080,294 B2
System and method for voice controlled automatic information access and retrieval
Ashwini Patil, Richardson, TX (US); Ramakrishna R. Yannam, The Colony, TX (US); Ion Gerald McCusker, Allen, TX (US); Saahithi Chillara, Allen, TX (US); Ravisha Andar, Plano, TX (US); Emad Noorizadeh, Plano, TX (US); Priyank R. Shah, Plano, TX (US); Yogesh Raghuvanshi, Princeton, NJ (US); Sushil Golani, Charlotte, NC (US); and Christopher Keith Restorff, Carrollton, TX (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Sep. 18, 2023, as Appl. No. 18/469,420.
Application 18/469,420 is a continuation of application No. 17/212,076, filed on Mar. 25, 2021, granted, now 11,798,551.
Prior Publication US 2024/0013787 A1, Jan. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/32 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G10L 15/22 (2006.01)
CPC G10L 15/22 (2013.01) [G06N 7/01 (2023.01); G06N 20/00 (2019.01); G10L 2015/225 (2013.01)] 20 Claims
OG exemplary drawing
 
8. A method comprising:
receiving, from a user, a set of voice signals associated with a request for information that is stored within an internal network;
converting the set of voice signals into a set of text;
using a first machine learning algorithm to determine, based on the set of text, to automatically generate a reply to the request, wherein:
the first machine learning algorithm is configured to use the set of text to select between automatically generating the reply to the request and transmitting the request to a device of an agent; and
the set of text is associated with a probability that the automatically generated reply comprises the information sought by the request, the probability greater than a threshold;
in response to determining to automatically generate the reply:
using a second machine learning algorithm to generate, based on the set of text and a first source of data, a first response to the request, wherein the first source of data is stored within the internal network;
transmitting the first response to the user, as the reply to the request; and
in response to transmitting the reply to the request to the user:
receiving feedback associated with the reply, the feedback indicating at least one of:
the reply to the request comprises the information sought by the request; and
the reply to the request does not comprise the information sought by the request; and
using the feedback to update at least one of the first machine learning algorithm and the second machine learning algorithm.