Performing enhanced exception processing using cognitive automation tools

Patent metadata

Field	Value
Publication number	US-11631018-B2
Application number	US-202016889242-A
Country	US
Kind code	B2
Filing date	Jun 1, 2020
Priority date	Jun 1, 2020
Publication date	Apr 18, 2023
Grant date	Apr 18, 2023

Abstract

Aspects of the disclosure relate to performing enhanced exception processing using cognitive automation tools. In some embodiments, a computing platform may receive interaction data identifying one or more actions performed by one or more users in resolving a plurality of exception items associated with an exception queue. Subsequently, the computing platform may train, using a learning engine, a machine learning model to resolve a first exception and a second exception of one or more exceptions based on the interaction data. Based on training the machine learning model, the computing platform may generate one or more configuration commands directing a processing module to implement the machine learning model to process additional exception items associated with the exception queue. The computing platform then may send the one or more configuration commands to the processing module.

First claim

What is claimed is:

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, via the communication interface, from at least one analyst user computing device, interaction data identifying one or more actions performed by one or more users of the at least one analyst user computing device in resolving a plurality of exception items associated with an exception queue;
train, using a learning engine, a machine learning model to resolve a first exception of one or more exceptions based on the interaction data identifying the one or more actions performed by the one or more users of the at least one analyst user computing device in resolving the plurality of exception items associated with the exception queue;
train, using the learning engine, the machine learning model to resolve a second exception of the one or more exceptions based on the interaction data identifying the one or more actions performed by the one or more users of the at least one analyst user computing device in resolving the plurality of exception items associated with the exception queue, wherein the second exception of the one or more exceptions is different from the first exception of the one or more exceptions;
based on training the machine learning model to resolve the first exception of the one or more exceptions and training the machine learning model to resolve the second exception of the one or more exceptions, generate one or more configuration commands directing a processing module to implement the machine learning model to process additional exception items associated with the exception queue;
send, to the processing module, the one or more configuration commands directing the processing module to implement the machine learning model to process the additional exception items associated with the exception queue;
after sending the one or more configuration commands directing the processing module to implement the machine learning model to process the additional exception items associated with the exception queue, receive, at the processing module, a third exception item from the exception queue;
apply, using the processing module, the machine learning model to the third exception item received from the exception queue, wherein applying the machine learning model to the third exception item received from the exception queue produces a first resolution pattern and a first confidence score; and
if the first confidence score exceeds a first confidence threshold, execute, using the processing module, the first resolution pattern, wherein executing the first resolution pattern comprises modifying one or more data elements of the third exception item based on the machine learning model.

2. The computing platform of claim 1 , wherein receiving the interaction data identifying the one or more actions performed by the one or more users of the at least one analyst user computing device in resolving the plurality of exception items associated with the exception queue comprises receiving a first portion of interaction data identifying one or more actions performed by the one or more users of the at least one analyst user computing device in resolving one or more check deposit exception items associated with the exception queue.

3. The computing platform of claim 1 , wherein receiving the interaction data identifying the one or more actions performed by the one or more users of the at least one analyst user computing device in resolving the plurality of exception items associated with the exception queue comprises receiving a second portion of interaction data identifying one or more actions performed by the one or more users of the at least one analyst user computing device in resolving one or more cash deposit exception items associated with the exception queue.

4. The computing platform of claim 1 , wherein training the machine learning model to resolve the first exception of the one or more exceptions comprises monitoring and recording a sequence of steps performed by at least one user of the at least one analyst user computing device in modifying one or more data elements of a first exception item to resolve an incorrect amount exception.

5. The computing platform of claim 4 , wherein training the machine learning model to resolve the first exception of the one or more exceptions comprises:
after monitoring and recording the sequence of steps performed by the at least one user of the at least one analyst user computing device in modifying the one or more data elements of the first exception item to resolve the incorrect amount exception, updating a trust value of a first data source from which the first exception item was received.

6. The computing platform of claim 1 , wherein training the machine learning model to resolve the second exception of the one or more exceptions comprises monitoring and recording a sequence of steps performed by at least one user of the at least one analyst user computing device in modifying one or more data elements of a second exception item to resolve a duplicate presentment exception.

7. The computing platform of claim 6 , wherein training the machine learning model to resolve the second exception of the one or more exceptions comprises:
after monitoring and recording the sequence of steps performed by the at least one user of the at least one analyst user computing device in modifying the one or more data elements of the second exception item to resolve the duplicate presentment exception, updating a trust value of a second data source from which the second exception item was received.

8. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
after executing the first resolution pattern, route, using the processing module, the third exception item to a data source from which the third exception item was received.

9. The computing platform of claim 1 , wherein applying the machine learning model to the third exception item received from the exception queue comprises identifying the third exception item as resulting from an incorrect amount exception.

10. The computing platform of claim 1 , wherein applying the machine learning model to the third exception item received from the exception queue comprises identifying the third exception item as resulting from a duplicate presentment exception.

11. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
if the first confidence score does not exceed the first confidence threshold, route, using the processing module, the third exception item to a manual review queue.

12. A method, comprising:
at a computing platform comprising at least one processor, a communication interface, and memory:
receiving, by the at least one processor, via the communication interface, from at least one analyst user computing device, interaction data identifying one or more actions performed by one or more users of the at least one analyst user computing device in resolving a plurality of exception items associated with an exception queue;
training, by the at least one processor, using a learning engine, a machine learning model to resolve a first exception of one or more exceptions based on the interaction data identifying the one or more actions performed by the one

Assignees

• Bank Of America

Inventors

• Malabad Christine
• Goertz Jeffrey R
• Hunt Letishia R
• Chellaraj Clement
• Dryer Eric
• Lee Clarence E
• Harbinson Charles Christopher
• Watson Verlon S

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q20/042

  characterized in that the payment protocol involves at least one cheque · CPC title

• G06Q10/06316

  Sequencing of tasks or work · CPC title

• G06Q20/4016

  involving fraud or risk level assessment in transaction processing · CPC title

• G06N5/043 Primary

  Distributed expert systems; Blackboards · CPC title