Granted Patent B2

US 12,348,554 · App. 18/584,989 · Granted Jul 1, 2025

Inventors: Brian P. Murphy (Tampa, FL); Joe Partlow (Tampa, FL); Colin O'Connor (Tampa, FL); Jason Pfeiffer (Tampa, FL); Brian Philip Murphy (St. Petersburg, FL); Jonathan R. Echavarria (Tampa, FL)

Assignee: RELIAQUEST HOLDINGS, LLC

H04L63/1441G06F16/345G06F21/552G06F21/554G06F21/566G06F40/103G06F40/154G06F40/56G06N3/0475H04L41/16H04L63/1416H04L63/1425G06F2221/034

Abstract

Claims (73)

1. A computer-implemented method executed on a computing device comprising:

training one or more agents to detect security events based upon one or more of archived data concerning activities and supplemental information;

monitoring, by the one or more agents deployed within one or more of a plurality of security-relevant subsystems within a computing platform, activity within the one or more of the plurality of security-relevant subsystems;

establishing connectivity with the plurality of security-relevant subsystems within the computing platform;

receiving an initial notification of a security event from one of the security-relevant subsystems, wherein the initial notification includes a computer-readable language portion that defines one or more specifics of the security event;

iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification;

prompting a user to provide feedback concerning the summarized human-readable report; and

revising the formatting script based upon, at least in part, provided feedback;

wherein the formatting is revised, at least in part, to produce a new summarized human-readable report with updated recommended mitigation actions.

2. The computer-implemented method of claim 1 wherein receiving an initial notification of a security event from one of the security-relevant subsystems includes:

receiving the initial notification of the security event from an agent executed on one of the security-relevant subsystems.

3. The computer-implemented method of claim 1 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using the generative AI model, the formatting script and/or one or more tools to produce the summarized human-readable report for the initial notification.

4. The computer-implemented method of claim 3 wherein the one or more tools includes one or more of:

a decoding tool to decode an encoded initial notification;

a decompression tool to decompress a compressed initial notification; and

an identification tool to identify an owner of a domain associated with the initial notification.

5. The computer-implemented method of claim 1 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using a large language model.

6. The computer-implemented method of claim 1 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing prompt engineering to produce the summarized human-readable report for the initial notification.

7. The computer-implemented method of claim 1 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing several loops and/or nested loops to produce the summarized human-readable report for the initial notification.

8. The computer-implemented method of claim 1 wherein the summarized human-readable report defines recommended next steps and/or disclaimers.

9. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:

training one or more agents to detect security events based upon one or more of archived data concerning activities and supplemental information;

monitoring, by the one or more agents deployed within one or more of a plurality of security-relevant subsystems within a computing platform, activity within the one or more of the plurality of security-relevant subsystems;

establishing connectivity with the plurality of security-relevant subsystems within the computing platform;

receiving an initial notification of a security event from one of the security-relevant subsystems, wherein the initial notification includes a computer-readable language portion that defines one or more specifics of the security event;

iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification;

prompting a user to provide feedback concerning the summarized human-readable report; and

revising the formatting script based upon, at least in part, provided feedback;

wherein the formatting is revised, at least in part, to produce a new summarized human-readable report with updated recommended mitigation actions.

10. The computer program product of claim 9 wherein receiving an initial notification of a security event from one of the security-relevant subsystems includes:

receiving the initial notification of the security event from an agent executed on one of the security-relevant subsystems.

11. The computer program product of claim 9 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using the generative AI model, the formatting script and/or one or more tools to produce the summarized human-readable report for the initial notification.

12. The computer program product of claim 11 wherein the one or more tools includes one or more of:

a decoding tool to decode an encoded initial notification;

a decompression tool to decompress a compressed initial notification; and

an identification tool to identify an owner of a domain associated with the initial notification.

13. The computer program product of claim 9 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using a large language model.

14. The computer program product of claim 9 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing prompt engineering to produce the summarized human-readable report for the initial notification.

15. The computer program product of claim 9 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing several loops and/or nested loops to produce the summarized human-readable report for the initial notification.

16. The computer program product of claim 9 wherein the summarized human-readable report defines recommended next steps and/or disclaimers.

17. A computing system comprising:

a hardware processor and physical memory configured to perform operations comprising:

training one or more agents to detect security events based upon one or more of archived data concerning activities and supplemental information;

monitoring, by the one or more agents deployed within one or more of a plurality of security-relevant subsystems within a computing platform, activity within the one or more of the plurality of security-relevant subsystems;

establishing connectivity with the plurality of security-relevant subsystems within the computing platform;

receiving an initial notification of a security event from one of the security-relevant subsystems, wherein the initial notification includes a computer-readable language portion that defines one or more specifics of the security event;

iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification;

prompting a user to provide feedback concerning the summarized human-readable report; and

revising the formatting script based upon, at least in part, provided feedback;

wherein the formatting is revised, at least in part, to produce a new summarized human-readable report with updated recommended mitigation actions.

18. The computing system of claim 17 wherein receiving an initial notification of a security event from one of the security-relevant subsystems includes:

receiving the initial notification of the security event from an agent executed on one of the security-relevant subsystems.

19. The computing system of claim 17 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using the generative AI model, the formatting script and/or one or more tools to produce the summarized human-readable report for the initial notification.

20. The computing system of claim 19 wherein the one or more tools includes one or more of:

a decoding tool to decode an encoded initial notification;

a decompression tool to decompress a compressed initial notification; and

an identification tool to identify an owner of a domain associated with the initial notification.

21. The computing system of claim 17 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

iteratively processing the initial notification using a large language model.

22. The computing system of claim 17 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing prompt engineering to produce the summarized human-readable report for the initial notification.

23. The computing system of claim 17 wherein iteratively processing the initial notification using a generative AI model and a formatting script to produce a summarized human-readable report for the initial notification includes:

utilizing several loops and/or nested loops to produce the summarized human-readable report for the initial notification.

24. The computing system of claim 17 wherein the summarized human-readable report defines recommended next steps and/or disclaimers.

Assignments (2)

Continuity (2)

References Cited (168)