Method and system therefor of establishing an acceptance threshold for controlling fraudulent telephone calls

• US 6,327,345 B1
• Filed: 09/16/1994
• Issued: 12/04/2001
• Est. Priority Date: 09/16/1994
• Status: Expired due to Term

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: MCI Communications Corporation (Verizon Communications Inc.)
• Inventors: Jordan, David P.
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US08/307,249
• Time in Patent Office: 2,636 Days
• Field of Search: 379/67, 379/88, 379/89, 379/189, 379/196, 379/199, 379/249, 379/67.1, 379/88.01, 379/88.02, 379/213, 379/214, 379/114.14, 379/210.02, 379/207.13, 704/2.79, 704/2.82, 704/2.84
• US Class Current: 379/88.02
• CPC Class Codes: H04M 15/47 Fraud detection or prevention means
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/6027 Fraud preventions
• CPC Class Codes: H04M 2215/0148 Fraud detection or prevention means
• CPC Class Codes: H04M 3/2218 Call detail recording
• CPC Class Codes: H04M 3/38 Graded-service arrangements, i.e. some subscribers prevented from establishing certain connections queuing arrangements H04Q3/64
• CPC Class Codes: H04M 3/382 using authorisation codes or passwords
• CPC Class Codes: H04M 3/385 using speech signals
• CPC Class Codes: H04M 3/42 Systems providing special services or facilities to subscribers specially adapted for wireless communication networks H04W4/00
• CPC Class Codes: H04M 7/00 Arrangements for interconnection between switching centres

Abstract

The present invention advanced voice application system takes advantage of information, or attributes, built into a telecommunications network to determine the risk that a call is a fraudulent call in a voice recognition and verification system. To achieve this end, information relating to the telecommunications network are stored in a database as various risk factors. Thus, depending on the type of risk factors associated with a particular call, the risk assigned to that call can be raised or lowered so that the network would not reject a valid caller even though the voice pattern of the caller does not match exactly with the prestored enrolled voice print of the caller. Such risk assessment allows the management of the network to tighten the security of the system without overburdening the caller with questions and also permits calls to be completed for valid subscribers that otherwise would have been rejected. Past calling history may be added to the database as it relates to the different risk factors so that constantly updated risk factors may be used for further assessing whether a call is to be completed.

Claims

1. A method of controlling fraudulent telephone calls in a telecommunications network, comprising:

recognizing an utterance spoken by a voice of a caller who is placing a telephone call via the telecommunications network;

matching the voice of the caller against a pre-stored voice signature of an authentic caller; and

if the voice of the caller does not match the pre-stored voice signature, evaluating at least one risk factor associated with the telephone call to determine if the telephone call is not fraudulent, said evaluating being performed automatically without receiving additional information from the caller.

2. The method of claim 1, wherein said matching is performed using a matching threshold, the matching threshold not being a function of any risk factor associated with the telephone call.

3. The method of claim 1, wherein said matching is performed using a matching threshold, the matching threshold being predetermined with respect to all callers.

4. The method of claim 1, wherein said matching is performed using a single matching threshold.

5. The method of claim 1, wherein the at least one risk factor is further associated with a plurality of callers.

6. The method of claim 1, wherein the at least one risk factor is further associated with at least one prior telephone call placed by the authentic caller.

7. The method of claim 1, wherein the at least one risk factor comprises a destination to which the telephone call is placed.

8. The method of claim 1, wherein the at least one risk factor comprises a location from which the telephone call is placed.

9. The method of claim 1, further comprising:

deciding whether the telephone call will be competed based on said evaluating.

10. The method of claim 1, further comprising:

if said evaluating does not determine that the telephone call is not fraudulent, receiving additional information from the caller to determine if the telephone call is not fraudulent based on pre-stored information associated with the authentic caller.

11. The method of claim 10, wherein said receiving is performed via at least one of:

(i) a voice response received from the caller, (ii) a DTMF tone received from the caller, and (ii) an operator station associated with the telecommunications network.

12. A method of controlling fraudulent telephone calls in a telecommunications network, comprising:

identifying a telephone call being placed by a caller via the telecommunication network;

prompting the caller to speak an utterance;

recognizing the utterance spoken by a voice of the caller;

matching the voice of the caller against a pre-stored voice signature of an authentic caller using a matching threshold that is not a function of any risk factor associated with the telephone call;

evaluating at least one risk factor associated with the telephone call to determine if the telephone call is not fraudulent, said evaluating being performed (i) only if the voice of the caller does not match the pre-stored voice signature and (ii) automatically without receiving additional information from the caller; and

completing the telephone call if the voice of the caller matches the pre-stored voice signature or if said evaluating determines that the telephone call is not fraudulent.

13. A system to control fraudulent telephone calls in a telecommunications network, comprising:

means for recognizing an utterance spoken by a voice of a caller who is placing a telephone call via the telecommunications network;

means for matching the voice of the caller against a pre-stored voice signature of an authentic caller; and

means for evaluating at least one risk factor associated with the telephone call to determine if the telephone call is not fraudulent, the evaluating being performed automatically without receiving additional information from the caller if the voice of the caller does not match the pre-stored voice signature.