US 11,886,281 B2
Artificial intelligence engine providing automated error resolution
Prashanth Kolar, San Francisco, CA (US); Vetrivel Murugan Shanmuga Ganapathy, San Francisco, CA (US); Chirag B. Bhavsar, San Francisco, CA (US); and Pavan Chayanam, Alamo, CA (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Aug. 13, 2021, as Appl. No. 17/401,485.
Prior Publication US 2023/0047437 A1, Feb. 16, 2023
Int. Cl. G06F 11/07 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/0793 (2013.01) [G06F 11/0769 (2013.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A computing platform comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive historical error and solution information;
train, using the historical error and solution information, an artificial intelligence engine, wherein training the artificial intelligence engine enables it to automatically identify solutions for current errors for a plurality of users;
identify one or more current errors for a user of the plurality of users; notify the user of the one or more current errors;
receive a request to correct an error of the one or more current errors;
identify, using the artificial intelligence engine, a solution to the error, wherein identifying the solution comprises automatically identifying the solution using the artificial intelligence engine, and wherein identifying the solution further comprises:
generating, using the artificial intelligence engine, a confidence score corresponding to the automatically identified solution,
based on identifying that the confidence score exceeds a first threshold, automatically performing one or more actions to achieve the solution,
based on identifying that the confidence score exceeds a second threshold but not the first threshold, sending a notification of the one or more actions for approval by the user, and
based on identifying that the confidence score does not exceed the second threshold, routing the error to an enterprise computing device for further assistance;
send, after performing the one or more actions, one or more commands directing an event processing system to process an event with which the error was associated, wherein sending the one or more commands directing the event processing system to process the event causes the event processing system to process the event; and
update, by feeding the identified one or more current errors and the automatically identified solution into the artificial intelligence engine, the artificial intelligence engine, wherein updating the artificial intelligence engine increases accuracy of the artificial intelligence engine in automatically identifying solutions to various errors.