Method and system for authenticating customer identities

• US 8,548,818 B2
• Filed: 01/31/2008
• Issued: 10/01/2013
• Est. Priority Date: 01/31/2008
• Status: Active Grant

• Current Assignee: First Data Corporation (Fiserv Incorporated)
• Original Assignee: First Data Corporation (Fiserv Incorporated)
• Inventors: Wagner, Theresa Lynn, Pinkerton, Peggy Ann
• Primary Examiner(s): Coppola, Jacob C.
• Application Number:
  US12/023,537
• Publication Number:
  US 20090198587A1
• Time in Patent Office: 2,070 Days
• Field of Search: 705/1.1
• US Class Current: 705/1.1
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 2221/2103 Challenge-response
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 30/0281 Customer communication at a business location, e.g. providing product or service information, consulting
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G07C 9/32 in combination with an identity check
• CPC Class Codes: G07C 9/38 with central registration

Abstract

This disclosure describes, generally, methods and systems for authenticating the identities of customers. For example, a method comprising receiving a service request from a customer and retrieving customer profile information related to the customer is described. The method further comprises generating questions based on the customer profile information and receiving answers to the questions from the customer. Furthermore, the method comprises analyzing the answers by comparing the answers with the customer profile information and calculating an authentication score based on the analysis of the answers. The method further authenticates the customer based on the authentication score being greater than a threshold score level.

Claims

1. A method for automated authentication of a customer'"'"'s identity, the method comprising:

receiving, by a computer system, a service request from a customer;

retrieving, by the computer system, customer profile information related to the customer;

generating, by the computer system, a first plurality of open-ended questions based on the customer profile information, wherein the first plurality of open-ended questions have question types associated with each question, and wherein the generating of the first plurality of open-ended questions comprises;

tracking the question types associated with each question,

tracking an average score for each question type,

generating a question rating report for each question type based on the average score of each question type, and

presenting higher rated questions to the customer based on the report;

designating, by the computer system, a first plurality of correct answers based on the customer profile information which correspond to the first plurality of open-ended questions;

receiving a first plurality of answers to the first plurality of open-ended questions from the customer;

automatically analyzing, by the computer system, the first plurality of answers by comparing the first plurality of answers with the first plurality of correct answers by parsing each of the first plurality of answers and performing a character-by-character accuracy analysis of the first plurality of answers in comparison to a character-by-character analysis of the first plurality of correct answers;

calculating, by the computer system, authentication scores for each of the first plurality of answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer;

rating each of the plurality of questions based on the correctness each of the plurality of answers relative to the corresponding correct answer;

increasing the frequency of use of the plurality questions as a function of the rating of each of the plurality of questions, wherein the higher the rating of a question the more frequent the question is used; and

authenticating, by the computer system, the customer if each of the authentication scores is cumulatively at least greater than a threshold value.

2. The method of claim 1, further comprising:

presenting, by the computer system, the customer with a second plurality of open- ended questions based on the first authentication scores being less than the threshold value;

designating, by the computer system, a second plurality of correct answers based on the customer profile information which correspond to the second plurality of open-ended questions;

receiving, by the computer system, a second plurality of answers to the second plurality of open-ended questions from the customer;

analyzing, by the computer system, the second plurality of questions by comparing the second plurality of answers with the second plurality of correct answers by parsing each of the second plurality of answers and performing a character-by-character accuracy analysis of the second plurality of answers in comparison to a character-by-character analysis of the second plurality of correct answers;

calculating, by the computer system, authentication scores for each of the plurality of second answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer; and

authenticating, by the computer system, the customer based on the authentication scores from the first and second pluralities of answers being cumulatively greater than the threshold value.

3. The method of claim 1, further comprising:

rejecting, by the computer system, the service request from the customer based on the authentication scores being less than the threshold value.

4. The method of claim 2, further comprising:

processing, by the computer system, the customer profile information to demographically categorize the customer; and

customizing, by the computer system, the first and second plurality of questions based on the demographic categorization of the customer.

5. The method of claim 2, wherein the question types are based on at least one of consumer questions, family relation questions, address history questions, vehicle questions, real estate questions, or business questions.

6. The method of claim 1, wherein the service request includes an associated service request type.

7. The method of claim 6, further comprising:

determining, by the computer system, whether authentication is required based on the service request type associated with the service request.

8. A system for authentication of a customer'"'"'s identity, the system comprising:

a processor coupled with a computer-readable non-transitory storage medium having sets of instructions stored thereon which, when executed by the processor cause the processor implement the following;

a question database configured to store a plurality of open-ended authentication questions;

a customer database configured to store customer profile data; and

a processing center coupled to the question database and the customer database configured to;

receive a service request from a customer;

retrieve customer profile data related to the customer from the customer database;

retrieve the plurality of open-ended authentication questions from the question database based on the customer profile data, wherein the first plurality of open-ended questions have question types associated with each question, and wherein the retrieving of the plurality of open-ended questions comprises;

tracking the question types associated with each question,

tracking an average score for each question type,

generating a question rating report for each question type based on the average score of each question type, and

presenting higher rated questions to the customer based on the report;

designating a plurality of correct answers based on the customer profile information which correspond to the plurality of open-ended authentication questions;

present the plurality of open-ended authentication questions to the customer;

receive a plurality of answers to the plurality of open-ended authentication questions;

automatically analyze the plurality of answers by comparing the plurality of answers with the plurality of correct answers by parsing each of the plurality of answers and performing a character-by-character accuracy analysis of the plurality of answers in comparison to a character-by-character analysis of the plurality of correct answers;

calculate authentication scores for each of the plurality of answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer;

rate each of the plurality of questions based on the correctness each of the plurality of answers relative to the corresponding correct answer;

increase the frequency of use of the plurality questions as a function of the rating of each of the plurality of questions, wherein the higher the rating of a question the more frequent the question is used; and

authenticate the customer if each of the authentication scores is cumulatively at least greater than a threshold value.

9. The system of claim 8, wherein the processing center is further configured to:

retrieve a second plurality of open-ended questions from the question database based on the authentication scores being less than the threshold value;

present the second plurality of questions to the customer;

designating a second plurality of correct answers based on the customer profile information which correspond to the second plurality of open-ended questions;

receive a second plurality of answers to the second plurality of open-ended questions from the customer;

analyze the second plurality of questions by comparing the second plurality of answers with the second plurality of correct answers by parsing each of the second plurality of answers and performing a character-by-character accuracy analysis of the second plurality of answers in comparison to a character-by-character analysis of the second plurality of correct answers;

calculate authentication scores for each of the plurality of second answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer; and

authenticate the customer based on the authentication scores from the first and second pluralities of answers being cumulatively greater than the threshold value.

10. The system of claim 9, wherein the processing center is further configured to reject the customer based on the authentication scores being less than the authentication value.

11. The system of claim 9, further comprising an interactive voice recognition (IVR) system configured to transmit the first and second pluralities of open-ended questions to the customer;

and to receive the first and second pluralities of answers from the customer.

12. A non-transitory machine-readable medium including sets of instructions which, when executed by a machine, cause the machine to:

receive a service request from a customer;

retrieve customer profile information related to the customer;

generate a first plurality of open-ended questions based on the customer profile information, wherein the first plurality of open-ended questions have question types associated with each question, and wherein the generating of the first plurality of open-ended questions comprises;

tracking the question types associated with each question,

tracking an average score for each question type,

generating a question rating report for each question type based on the average score of each question type, and

presenting higher rated questions to the customer based on the report;

designate a first plurality of correct answers based on the customer profile information which correspond to the first plurality of open-ended questions;

receive a first plurality of answers to the first plurality of open-ended questions from the customer;

automatically analyze the first plurality of answers by comparing the first plurality of answers with the first plurality of correct answers by parsing each of the first plurality of answers and performing a character-by-character analysis accuracy analysis of the first plurality of answers in comparison to a character-by-character analysis of the first plurality of correct answers;

calculate authentication scores for each of the first plurality of answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer;

rate each of the plurality of questions based on the correctness each of the plurality of answers relative to the corresponding correct answer;

increase the frequency of use of the plurality questions as a function of the rating of each of the plurality of questions, wherein the higher the rating of a question the more frequent the question is used; and

authenticate the customer if each of the authentication scores is cumulatively at least greater than a threshold value.

13. The non-transitory machine-readable medium of claim 12, wherein the sets of instructions which, when further executed by a machine, cause the machine to:

present the customer with a second plurality of open-ended questions based on the first authentication scores being less than the threshold value;

designate a second plurality of correct answers based on the customer profile information which correspond to the second plurality of open-ended questions;

receive a second plurality of answers to the second plurality of open-ended questions from the customer;

analyze the second plurality of questions by comparing the second plurality of answers with the second plurality of correct answers by parsing each of the second plurality of answers and performing a character-by-character accuracy analysis of the second plurality of answers in comparison to a character-by-character analysis of the second plurality of correct answers;

calculate authentication scores for each of the plurality of second answers, wherein each authentication score represents a correctness of each of the plurality of answers relative to the corresponding correct answer; and

authenticate the customer based on the authentication scores from the first and second pluralities of answers being cumulatively greater than the threshold value.

14. The non-transitory machine-readable medium of claim 12, wherein the sets of instructions which, when further executed by a machine, cause the machine to reject the service request from the customer based on the first authentication score being less than the threshold value.