Fraud detection database

• US 10,043,189 B1
• Filed: 01/30/2017
• Issued: 08/07/2018
• Est. Priority Date: 03/21/2014
• Status: Active Grant

• Current Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Original Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Inventors: Jones, Raymond F.
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US15/419,573
• Time in Patent Office: 554 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: H04M 15/47 Fraud detection or prevention means
• CPC Class Codes: H04M 2203/301 Management of recordings
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

Embodiments of techniques or systems for fraud detection are provided herein. A communication may be received where the communication includes one or more voice signals from an individual. Frequency responses associated with these voice signals may be determined and analyzed and utilized to determine whether or not potential fraudulent activity is occurring. For example, if a frequency response is greater than a frequency threshold, potential fraudulent activity may be determined. Further, frequency responses may be cross referenced with voice biometrics, voice printing, or fraud pathway detection results. In this way, voice stress or frequency responses may be utilized to build other databases related to other types of fraud detection, thereby enhancing one or more aspects of fraud detection. For example, a database may include a voice library, a pathway library, or a frequency library which include characteristics associated with fraudulent activity, thereby facilitating identification of such activity.

Claims

1. A system for fraud detection, comprising:

a processor that executes the following executable components;

a monitoring component that receives a communication, wherein the communication comprises one or more voice segments, wherein the one or more voice segments include audio of an individual making one or more requests associated with an account and one or more verification segments;

a detection component that determines one or more frequency response characteristics associated with the one or more verification segments of the voice segments of the communication;

an analysis component that analyzes only the one or more frequency response characteristics associated with the one or more verification segments, wherein the analysis represents frequency fluctuations present within the one or more verification segments; and

a fraud component that flags the communication as fraudulent or non-fraudulent based at least in part upon the analysis.

2. The system of claim 1, wherein the fraud component employs a frequency threshold difference between at least two of the one or more frequency response characteristics to determine whether or not to flag.

3. The system of claim 2, wherein the fraud component updates a frequency library with one or more of the frequency response characteristics associated with the individual.

4. The system of claim 1, wherein the fraud component further deems activity associated with the account to be fraudulent based on a comparison between one or more frequency response characteristics and one or more voice samples of a voice library.

5. The system of claim 1, wherein the detection component further determines one or more artifacts associated with the communication and the fraud component deems activity associated with the account to be fraudulent based on a comparison between one or more of the frequency response characteristics and one or more artifacts associated with the communication.

6. The system of claim 1, wherein the communication deemed to be fraudulent is determined prior to action related to the account in response to the communication.

7. The system of claim 1, wherein the activity is deemed to be fraudulent in near real-time.

8. A method for fraud detection, comprising:

receiving, via a system comprising a processing unit and a memory, a communication, wherein the communication comprises one or more voice segments of an individual making one or more requests associated with an account; and

determining fraudulent activity based at least in part upon comparison of one or more frequency response characteristics associated only with one or more verification segments of the one or more voice segments of the communication.

9. The method of claim 8, comprising updating a voice library or a pathway library based on activity deemed to be fraudulent associated with the account, wherein the voice library comprises one or more voice samples of individuals deemed to be fraudsters, and wherein the pathway library comprises one or more sets of characteristics deemed to be associated with fraudulent communication.

10. The method of claim 9, comprising updating a frequency library with one or more frequency responses associated with the individual.

11. The method of claim 9, comprising deeming activity associated with the account to be fraudulent based on a match between one or more of the voice segments and one or more of the voice samples of the voice library.

12. The method of claim 8, wherein the communication further comprises one or more artifacts associated with the communication and wherein determining fraudulent activity further comprises deeming activity associated with the account to be fraudulent based on a match between one or more of the frequency response characteristics and one or more of the artifacts associated with the communication.

13. A system for fraud detection, comprising:

a processor that executes the following executable components;

a monitoring component that receives a communication associated with a financial transaction, wherein the communication comprises one or more voice segments;

a detection component that determines one or more frequency response characteristics associated with the communication, wherein each of the one or more frequency response characteristics corresponds to a corresponding one or more verification segments; and

a fraud determination component that analyzes only the one or more frequency response characteristics to establish a determination if fraud exists based upon at least a threshold comparison of at least two of the one or more frequency response characteristics.

14. The system of claim 13, wherein the detection component further determines one or more artifacts associated with the communication and wherein the fraud determination component updates a voice library with one or more of the voice signals based on a match between one or more of the frequency response characteristics and one or more artifacts associated with the communication.

15. The system of claim 13, wherein the fraud determination component updates a voice library with one or more of the voice segments based on one or more frequency responses of one or more of the verification segments of the one or more the voice segments of the communication.

16. The system of claim 13, wherein the fraud determination component updates a pathway library with one or more frequency response characteristics of the communication based on a match between one or more of the voice segments and one or more voice samples of a voice library.

17. The system of claim 13, wherein the fraud determination component updates a pathway library with one or more characteristics of the communication based on one or more frequency responses of one or more of the verification segments of the one or more of the voice segments of the communication.

18. The system of claim 13, comprising an analysis component that determines one or more frequency responses of one or more of the verification segments of one or more of the voice segments of the communication.

19. The system of claim 13, wherein the fraud component updates a frequency library with one or more frequency responses associated with an individual.

20. The system of claim 13, wherein the monitoring component filters noise from one or more voice segments of the communication.