IP Library › Granted Patent US 12665876

Granted Patent B2

US 12665876 · App. 17/937,609 · Granted Jun 23, 2026

System and method for server monitoring and problem resolution for electronic mail messages

Inventors: Yi Jason Zhang (Frisco, TX); Daniel Joseph Serna (The Colony, TX)

Assignee: Bank of America Corporation

H04L63/0236 H04L63/205

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12665876
App. No.: 17/937,609
Granted: Jun 23, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A method is provided that comprises monitoring for a change in a first security configuration setting in a relay server and comparing the change in the first security configuration setting to historical data that contains validated authentication configuration settings that previously allowed for the delivery of a historical electronic mail message to an external network. The method further comprises identifying a candidate change to the first security configuration setting based on the comparison, where the candidate change to the first security configuration setting when implemented results in the delivery of a first electronic mail message to the external network. The method further comprises implementing the candidate change to the first security configuration setting such that the relay server allows the delivery of the first electronic message to the external network.

Claims (60)

1 . A system comprising:

a server configured to implement a mail transfer protocol for communication of electronic mail messages between computing devices;

a relay server configured to regulate the electronic mail messages that are sent and received between the server and an external network based on one or more security configuration settings,

wherein the relay server is configured to allow delivery of the electronic mail messages received from the server to the external network when the one or more security configuration settings are met and deny the delivery when the one or more security configuration settings are not met; and

a monitoring server comprising a processor and a memory, the processor operably coupled with the relay server via a network interface, the processor configured to:

train a machine learning module to predict whether changes made to the security configuration settings at the relay server are to cause the relay server to deny delivery of one or more electronic mail messages to the external network and to determine candidate changes to the security configuration settings to cause the relay server to allow delivery of the one or more electronic mail message to the external network, wherein the machine learning module is trained based on historical security configuration settings at the relay server that previously allowed historical electronic mail messages to be delivered to the external network; execute the machine learning module to:

monitor, by the machine learning module, for changes to the security configuration settings at the relay server; detect, by the machine learning module based on the monitoring, a change to a first security configuration setting at the relay server;

compare, by the machine learning module, the change in the first security configuration setting at the relay server to the historical security configuration settings at the relay server that previously allowed the relay server to forward historical electronic mail messages received from the server to a first recipient in the external network;

predict, by the machine learning module based on the comparing, that the change in the first security configuration setting will cause the relay server to deny delivery of future electronical mail messages to the first recipient in the external network; and

identify, by the machine learning module, a candidate change to the first security configuration setting at the relay server based on the comparing such that the candidate change to the first security configuration setting when implemented at the relay server causes the relay server to allow forwarding of the future electronic mail message received from the server to the first recipient in the external network, wherein the candidate change implemented during a deployment to update the security configuration settings by rolling back the first security configuration setting to the historical security configuration settings at the relay server that previously allowed the relay server to forward historical electronic mail messages received from the server to the first recipient in the external network; and

perform the candidate change to the first security configuration setting at the relay server to cause the relay server to forward the future electronic mail messages received from the server to the first recipient in the external network, wherein performing the candidate change comprises rolling back the first security configuration setting to the historical security configuration settings at the relay server that previously allowed the relay server to forward historical electronic mail messages received from the server to the first recipient in the external network.

2 . The system of claim 1 , wherein the server comprises a simple mail transfer protocol (SMTP) server and the relay server comprises a SMTP relay server.

3 . The system of claim 1 , wherein the first security configuration setting is selected from an allow list of IP addresses, a deny list of IP addresses, a connection threshold control setting, or an encryption protocol.

4 . The system of claim 1 , wherein the processor is configured to:

determine, using the machine learning module, that a second change to the first security configuration setting will result in the relay server allowing a first electronic message to be delivered to the external network; and

deploy the second candidate change to the first security configuration setting in the relay server to allow the delivery of the first electronic message to the external network.

5 . The system of claim 1 , wherein the processor is configured to:

determine, using the machine learning module, that a second change to the first security configuration setting will result in the relay server denying a first electronic message to be delivered to the external network; and

determine a second candidate change for altering the second change to the first security configuration setting that will result in the relay server allowing the first electronic message to be delivered to the external network.

6 . The system of claim 5 , wherein the processor is configured to:

generate a report containing the second candidate change and instructions for a user to manually alter the first security configuration setting; and

display the report to a user.

7 . The system of claim 5 , wherein the processor is configured to:

implement the second candidate change automatically to allow the first electronic message to be delivered to the external network.

8 . A non-transitory computer readable medium storing instructions that when executed by a processor cause the processor to:

train a machine learning module to predict whether changes made to security configuration settings at a relay server are to cause the relay server to deny delivery of one or more electronic mail messages to an external network and to determine candidate changes to the security configuration settings to cause the relay server to allow delivery of the one or more electronic mail message to the external network, wherein the machine learning module is trained based on historical security configuration settings at the relay server that previously allowed historical electronic mail messages to be delivered to the external network;

execute the machine learning module to:

monitor, by the machine learning module, for changes to the security configuration settings at the relay server;

detect, by the machine learning module, based on the monitoring, a change to a first security configuration setting at the relay server;

predict, by the machine learning module, based on the comparing, that the change in the first security configuration setting will cause the relay server to deny delivery of future electronical mail messages to the first recipient in the external network; and

9 . The non-transitory computer readable medium of claim 8 , wherein the first security configuration setting is selected from an allow list of IP addresses, a deny list of IP addresses, a connection threshold control setting, an encryption protocol, or a firewall protocol.

10 . The non-transitory computer readable medium of claim 8 , wherein the instructions when executed by the processor further cause the processor to:

implement the second change to the first security configuration setting in the relay server to allow the delivery of the first electronic message to the external network.

11 . The non-transitory computer readable medium of claim 10 , wherein the instructions when executed by the processor further cause the processor to:

generate a report containing the second change and instructions for a user to manually alter the first security configuration setting; and

display the report to a user.

12 . The non-transitory computer readable medium of claim 10 , wherein the instructions when executed by the processor further cause the processor to:

implement the second change automatically to the first electronic message to be delivered to the external network.

13 . A method comprising:

training a machine learning module to predict whether changes made to security configuration settings at a relay server are to cause the relay server to deny delivery of one or more electronic mail messages to an external network and to determine candidate changes to the security configuration settings to cause the relay server to allow delivery of the one or more electronic mail message to the external network, wherein the machine learning module is trained based on historical security configuration settings at the relay server that previously allowed historical electronic mail messages to be delivered to the external network;

executing the machine learning module to:

monitor, by the machine learning module, for changes to the security configuration settings at the relay server;

detect, by the machine learning module, based on the monitoring, a change to a first security configuration setting at the relay server;

(iv) perform the candidate change to the first security configuration setting at the relay server to cause the relay server to forward the future electronic mail messages received from the server to the first recipient in the external network, wherein performing the candidate change comprises rolling back the first security configuration setting to the historical security configuration settings at the relay server that previously allowed the relay server to forward historical electronic mail messages received from the server to the first recipient in the external network.

14 . The method of claim 13 further comprising:

determining, using the machine learning module, that a second change to the first security configuration setting will result in the relay server allowing a first electronic message to be delivered to the external network; and

implementing the second change to the first security configuration in the relay server to allow the delivery of the first electronic message to the external network.

15 . The method of claim 14 further comprising:

generating a report containing the second change and instructions for a user to manually alter the at least one security configuration setting; and

displaying the report to a user.

16 . The method of claim 14 further comprising:

implementing the second change automatically to the first electronic message to be delivered to the external network.

17 . The method of claim 13 , wherein the first security configuration setting is selected from an allow list of IP addresses, a deny list of IP addresses, a connection threshold control setting, an encryption protocol, or a firewall protocol.