Seamless authentication and enrollment

• US 9,620,123 B2
• Filed: 05/02/2013
• Issued: 04/11/2017
• Est. Priority Date: 05/02/2013
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Ltd
• Inventors: Faians, Shahar, Sabban, Alon Moshe, Lousky, Avraham, Hoffman, Elad, Kahn, Jade Tarni, Mandler, Roie
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US13/875,317
• Publication Number:
  US 20140330563A1
• Time in Patent Office: 1,440 Days
• Field of Search: 704236, 704 9, 704273, 704246, 704233, 704231, 99236, 726 26, 726 22, 713185, 713168, 705 44, 705 42, 705 35
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• 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: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231

Abstract

Some aspects of the invention may include a computer-implemented method for enrolling voice prints generated from audio streams, in a database. The method may include receiving an audio stream of a communication session and creating a preliminary association between the audio stream and an identity of a customer that has engaged in the communication session based on identification information. The method may further include determining a confidence level of the preliminary association based on authentication information related to the customer and if the confidence level is higher than a threshold, sending a request to compare the audio stream to a database of voice prints of known fraudsters. If the audio stream does not match any known fraudsters, sending a request to generate from the audio stream a current voice print associated with the customer and enrolling the voice print in a customer voice print database.

Claims

1. A computer-implemented method comprising:

receiving audio streams from an audio server that archives audio data of historical communication sessions between customers and representatives;

for each of at least some of the audio streams generating and enrolling a respective enrolled voice print by;

a management server using a processor to create a preliminary association between an audio stream related to a particular one of the historical communication sessions and an identity of a customer that has engaged in the particular historical communication session based on stored identification information;

determining using the processor a confidence level of the preliminary association based on stored authentication information related to the customer;

if the confidence level is higher than a threshold, checking using the processor the identity of the customer against a suspicious customer list, and if the identity of the customer is not listed in the suspicious customer identification information list, sending a request to compare the audio stream to a database of voice prints of known fraudsters;

if the audio stream does not match any known fraudsters, sending a request to generate from the audio stream a current voice print associated with the customer;

prior to enrolling the current voice print, comparing using the processor the current voice print associated with the customer to a voice print previously enrolled for the customer and comparing using the processor the current voice print associated with the customer to voice prints associated with other customers; and

enrolling using the processor the current voice print, if the current voice print does not match any other voice prints associated with any of the other customers and if the current voice print is consistent with the voice print previously enrolled for the customer, in a customer voice print database as an enrolled voice print;

if the current voice print does match a voice print associated with another customer reporting using the processor the current voice print as suspicious and reporting the voice print associated with the other customer as suspicious;

and

automatically authenticating the customer during a succeeding communication session based on the enrolled voice print.

2. The method of claim 1, further comprising:

prior to enrolling the current voice print, storing the current voice print associated with the customer for a period of time; and

comparing the current voice print to voice prints associated with other customers that were enrolled during the period of time.

3. The method of claim 1, wherein the confidence level is determined based on data provided by the customer during at least one historical communication session.

4. The method of claim 1, wherein the stored authentication information includes parameters related to at least one of:

knowledge based information and secret pass key.

5. The method of claim 1, wherein the stored authentication information includes parameters related to historical actions performed by the customer.

6. The method of claim 1, wherein authenticating the customer based on the enrolled voice print during the succeeding communication session with the customer comprises:

receiving an audio stream related to the succeeding communication session during the succeeding communication session;

receiving the identity of the customer during the succeeding communication session;

seamlessly generating a new voice print during the succeeding communication session without the awareness of the customer;

seamlessly sending a request for authentication of the identity of the customer, during the succeeding communication session based on the enrolled voice print stored in the customer voice print database and the new voice print; and

receiving information related to the authentication of the identity of the customer during the succeeding communication session.

7. The method of claim 1, comprising:

during the succeeding communication session, identifying if customer consent for recording audio data and enrolling a new voice print is required;

if so, receiving the customer consent to record the communication session; and

recording the communication session.

8. The method of claim 7, wherein receiving the consent is related to at least one of:

geographical origin of the communication session or the geographical origin of customer.

9. The method of claim 1, further comprising for at least one of the audio streams, determining not to enroll a respective voice print based on a status of the customer.

10. The method of claim 1, further comprising for at least one of the audio streams, determining not to enroll a respective voice print based on the quality of the audio stream.

11. The method of claim 1, comprising:

if the confidence level is lower than a threshold, not using the audio stream for enrolling a voice print and reporting the voice stream as suspicious; and

if the confidence level is lower than a threshold by a certain percentage generating a voice print and enrolling the generated voice print in the database of voice prints of known fraudsters.

12. The method of claim 1, comprising determining the geographic origin of the communication sessions and determining if enrollment of voice prints is allowed in the geographic origin.

13. The method of claim 1, comprising determining if active consent for enrollment of voice prints is required for the customer whose identity is associated with the audio stream.

14. The method of claim 1, comprising, if active consent for voiceprint enrollment is required, receiving consent for enrollment of voice prints before enrolling a current voice print.

15. An apparatus comprising:

at least one processor configured to;

receive audio streams from an audio server that archives audio data of historical communication sessions between customers and representatives;

for each of at least some of the audio streams generate and enroll a respective enrolled voice print by;

creating a preliminary association between an audio stream related to a particular one of the historical communication sessions and an identity of a customer that has engaged in the particular historical communication session based on stored identification information;

determining a confidence level of the preliminary association based on stored authentication information related to the customer;

if the confidence level is higher than a threshold, checking the identity of the customer against a suspicious customer list, and if the identity of the customer is not listed in the suspicious customer identification information list, sending a request to compare the audio stream to a database of voice prints of known fraudsters;

if the audio stream does not match any known fraudsters, sending a request to generate from the audio stream a current voice print associated with the customer;

prior to enrolling the current voice print, comparing the current voice print associated with the customer to a voice print previously enrolled for the customer and comparing the current voice print associated with the customer to voice prints associated with other customers; and

enrolling the current voice print, if the current voice print does not match any other voice prints associated with any of the other customers, in a customer voice print database as an enrolled voice print;

if the current voice print does match a voice print associated with another customer reporting the current voice print as suspicious and reporting the voice print associated with the other customer as suspicious;

and

automatically authenticate the customer during a succeeding communication session based on the enrolled voice print.

16. The apparatus of claim 15, further comprising an audio server for producing the audio stream.

17. The apparatus of claim 15, further comprising at least one database for storing at least one of:

the identification information and the authentication information.

18. The apparatus of claim 15, wherein the processor is further configured to:

compare the current voice print associated with the customer to voice prints associated with other customers;

if the current voice print does not match any other voice prints associated with any of the other customers, enroll the current voice print.

19. An article comprising a non-transitory computer-readable storage medium, having instructions stored thereon that when executed by at least one processor, cause the at least one processor to:

receive audio streams from an audio server that archives audio data of historical communication sessions between customers and representatives;

for each of at least some of the audio streams generate and enroll a respective enrolled voice print by;

creating a preliminary association between an audio stream related to a particular one of the historical communication sessions and an identity of a customer that has engaged in the particular historical communication session based on stored identification information;

determining a confidence level of the preliminary association based on stored authentication information related to the customer;

if the confidence level is higher than a threshold, checking the identity of the customer against a suspicious customer list, and if the identity of the customer is not listed in the suspicious customer identification information list, sending a request to compare the audio stream to a database of voice prints of known fraudsters;

if the audio stream does not match any known fraudsters, sending a request to generate from the audio stream a current voice print associated with the customer; and

prior to enrolling the current voice print, comparing the current voice print associated with the customer to a voice print previously enrolled for the customer and comparing the current voice print associated with the customer to voice prints associated with other customers;

enrolling the current voice print, if the current voice print does not match any other voice prints associated with any of the other customers and if the current voice print is consistent with the voice print previously enrolled for the customer, in a customer voice print database as an enrolled voice print;

if the current voice print does match a voice print associated with another customer reporting the current voice print as suspicious and reporting the voice print associated with the other customer as suspicious;

and

automatically authenticate the customer during a succeeding communication session based on the enrolled voice print.