IP Library Granted Patent US 11,856,134
Granted Patent B2
US 11,856,134 · App. 17/740,977 · Granted Dec 26, 2023

Fraud detection system and method

Inventor: Haydar Talib (Montreal, CA)
Assignee: Microsoft Technology Licensing, LLC
H04M3/42221H04M3/2281H04M3/42042H04M3/42059H04M3/436H04M2203/6027
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 11,856,134
App. No.
17/740,977
Granted
Dec 26, 2023
Kind
B2
Abstract

A method, computer program product, and computing system for receiving input information concerning a conversation between a caller and a recipient; processing the input information to assess a fraud-threat-level; defining a targeted response based, at least in part, upon the fraud-threat-level assessed, wherein the targeted response is intended to refine the assessed fraud-threat-level; and effectuating the targeted response.

Claims (57)

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

receiving input information concerning a conversation between a caller and a recipient;

processing the input information to assess a fraud-threat-level of a plurality of fraud-threat-levels, wherein processing the input information to determine a fraud-threat-level includes determining if the input information is indicative of fraudulent behavior by comparing biometric information of one of a word and a phrase of the input information to a plurality of fraudulent behaviors and a plurality of legitimate non-fraudulent behaviors, wherein the biometric information includes speech pattern indicia including one or more of inflection patterns, word choice patterns, speech cadence patterns, speech rhythm patterns, and word length patterns;

defining a targeted response based, at least in part, upon the fraud-threat-level assessed, wherein the targeted response is intended to refine the assessed fraud-threat-level; and

effectuating the targeted response.

2. The computer-implemented method of claim 1 wherein the input information further includes one or more of:

a caller conversation portion transcribed into the text; and

a recipient conversation portion transcribed into the text.

3. The computer-implemented method of claim 1 wherein each fraud-threat-level of the plurality of fraud-threat-levels is associated with a different targeted response from the recipient to be effectuated against the caller.

4. The computer-implemented method of claim 1 wherein effectuating the targeted response includes one or more of:

allowing the conversation to continue;

asking a question of the caller;

prompting the recipient to ask a question of the caller;

effecting a transfer from the recipient to a third-party; and

ending the conversation between the caller and the recipient.

5. The computer-implemented method of claim 1 wherein the conversation includes a voice-based conversation between the caller.

6. The computer-implemented method of claim 1 wherein the conversation includes a text-based conversation between the caller and the recipient.

7. The computer-implemented method of claim 1 wherein the plurality of fraudulent behaviors includes a plurality of empirically-defined fraudulent behaviors.

8. The computer-implemented method of claim 7 wherein the plurality of empirically-defined fraudulent behaviors are defined via AI/ML, processing of information concerning a plurality of earlier conversations.

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

receiving input information concerning a conversation between a caller and a recipient;

processing the input information to assess a fraud-threat-level of a plurality of fraud-threat-levels, wherein processing the input information to determine a fraud-threat-level includes determining if the input information is indicative of fraudulent behavior by comparing biometric information of one of a word and a phrase of the input information to a plurality of fraudulent behaviors and a plurality of legitimate non-fraudulent behaviors, wherein the biometric information includes speech pattern indicia including one or more of inflection patterns, word choice patterns, speech cadence patterns, speech rhythm patterns, and word length patterns;

defining a targeted response based, at least in part, upon the fraud-threat-level assessed, wherein the targeted response is intended to refine the assessed fraud-threat-level; and

effectuating the targeted response.

10. The computer program product of claim 9 wherein the input information further includes one or more of:

a caller conversation portion transcribed into the text; and

a recipient conversation portion transcribed into the text.

11. The computer program product of claim 9 wherein each fraud-threat-level of the plurality of fraud-threat-levels is associated with a different targeted response from the recipient to be effectuated against the caller.

12. The computer program product of claim 9 wherein effectuating the targeted response includes one or more of:

allowing the conversation to continue;

asking a question of the caller;

prompting the recipient to ask a question of the caller;

effecting a transfer from the recipient to a third-party; and

ending the conversation between the caller and the recipient.

13. The computer program product of claim 9 wherein the conversation includes a voice-based conversation between the caller.

14. The computer program product of claim 9 wherein the conversation includes a text-based conversation between the caller and the recipient.

15. The computer program product of claim 9 wherein the plurality of fraudulent behaviors includes a plurality of empirically-defined fraudulent behaviors.

16. The computer program product of claim 15 wherein the plurality of empirically-defined fraudulent behaviors are defined via AI/ML, processing of information concerning a plurality of earlier conversations.

17. A computing system including a processor and memory configured to perform operations comprising:

receiving input information concerning a conversation between a caller and a recipient;

processing the input information to assess a fraud-threat-level of a plurality of fraud-threat-levels, wherein processing the input information to determine a fraud-threat-level includes determining if the input information is indicative of fraudulent behavior by comparing biometric information of one of a word and a phrase of the input information to a plurality of fraudulent behaviors and a plurality of legitimate non-fraudulent behaviors, wherein the biometric information includes speech pattern indicia including one or more of inflection patterns, word choice patterns, speech cadence patterns, speech rhythm patterns, and word length patterns;

defining a targeted response based, at least in part, upon the fraud-threat-level assessed, wherein the targeted response is intended to refine the assessed fraud-threat-level; and

effectuating the targeted response.

18. The computing system of claim 17 wherein the input information further includes one or more of:

a caller conversation portion transcribed into the text; and

a recipient conversation portion transcribed into the text.

19. The computing system of claim 17 wherein each fraud-threat-level of the plurality of fraud-threat-levels is associated with a different targeted response from the recipient to be effectuated against the caller.

20. The computing system of claim 17 wherein effectuating the targeted response includes one or more of:

allowing the conversation to continue;

asking a question of the caller;

prompting the recipient to ask a question of the caller;

effecting a transfer from the recipient to a third-party; and

ending the conversation between the caller and the recipient.

21. The computing system of claim 17 wherein the conversation includes a voice-based conversation between the caller.

22. The computing system of claim 17 wherein the conversation includes a text-based conversation between the caller and the recipient.

23. The computing system of claim 17 wherein the plurality of fraudulent behaviors includes a plurality of empirically-defined fraudulent behaviors.

24. The computing system of claim 23 wherein the plurality of empirically-defined fraudulent behaviors are defined via AI/ML processing of information concerning a plurality of earlier conversations.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 9, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065531/0274 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 12, 2022
From: TALIB, HAYDAR
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 059987/0530 →
Continuity (2)
Continuation 17078652 · Oct 23, 2020
Related Publication 20220294900A1 · Sep 15, 2022