Method and apparatus for fraud control in cellular telephone systems

• US 5,950,121 A
• Filed: 06/10/1996
• Issued: 09/07/1999
• Est. Priority Date: 06/29/1993
• Status: Expired due to Term

• Current Assignee: Cellco Partnership, Inc. (Verizon Communications Inc.)
• Original Assignee: Airtouch Communications, Inc.
• Inventors: Daniels, David L., Kennedy, Mary H., Kaminsky, William J., Sanpore, Jeffrey G.
• Primary Examiner(s): Urban, Edward F.
• Assistant Examiner(s): Nguyen, Thuan T.
• Application Number:
  US08/633,406
• Time in Patent Office: 1,184 Days
• Field of Search: 380/21, 380/23, 455/67.1, 455/227, 455/228, 455/405, 455/410, 455/411, 455/517, 340/825.31, 340/825.34, 340/825.5
• US Class Current: 455/410
• CPC Class Codes: H04M 15/00 Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
• CPC Class Codes: H04M 15/47 Fraud detection or prevention means
• CPC Class Codes: H04M 2215/0148 Fraud detection or prevention means
• CPC Class Codes: H04M 2215/32 Involving wireless systems
• CPC Class Codes: H04W 12/06 Authentication
• CPC Class Codes: H04W 12/126 Anti-theft arrangements, e.g. protection against subscriber identity module [SIM] cloning
• CPC Class Codes: H04W 12/79 Radio fingerprint

Abstract

A method and apparatus for fraud control in cellular telephone systems. The invention identifies relative fraud probabilities for call records from the cellular telephone system, associates the call records with radio frequency (RF) signatures, and identifies the radio frequency signatures as being fraudulent or valid based on the relative fraud probabilities for the associated call records.

Claims

1. A method of identifying valid or fraudulent RF signatures of phones in a cellular telephone system, comprising the steps of:

(a) identifying relative valid or fraud probabilities using call records from the cellular telephone system;

(b) associating the calls with corresponding-radio frequency (RF) signatures; and

(c) identifying the radio frequency signatures as being fraudulent or valid based on the relative fraud probabilities for the associated calls.

2. The method as set forth in claim 1 above, wherein the associating step comprises the step of matching the call records with the radio frequency signatures based on one or more characteristics of both the call records and the radio frequency signature, wherein the characteristics are selected from a group comprised of:

time of day, day of week, cell site originating location, and dialed digits for an associated call.

3. The method as set forth in claim 2, further comprising the steps of receiving a call transmitted from a cellular telephone, generating a radio frequency signature for the cellular telephone, comparing the generated radio frequency signature to radio frequency signatures identified as fraudulent or valid, and preventing the call from completing when the comparison indicates the generated radio frequency signature is fraudulent.

4. The method as set forth in claim 3, wherein the associating step comprises the step of matching the call records with the radio frequency signatures based on one or more characteristics of both the call records and the radio frequency signature, and wherein the characteristics are selected from a group comprised of:

time of day, day of week, cell site originating location, and dialed digits for an associated call.

5. The method as set forth in claim 3, wherein the identifying step comprises the step of assigning a high fraud probability to call records containing a called number identical to known fraud dialed digits.

6. The method as set forth in claim 3, wherein the identifying step comprises the step of assigning a low fraud probability to call records containing a called number identical to known frequently called numbers for valid subscribers.

7. The method as set forth in claim 1 above, wherein the identifying step comprises the step of assigning a high fraud probability to call records containing a called number identical to known fraud dialed digits.

8. The method as set forth in claim 1 above, wherein the identifying step comprises the step of assigning a low fraud probability to call records containing a called number identical to known frequently called numbers for valid subscribers.

9. The method as set forth in claim 1 above, further comprising the steps of receiving a call transmitted from a cellular telephone, generating a radio frequency signature for the cellular telephone, comparing the generated radio frequency signature to the radio frequency signatures identified as fraudulent or valid, and preventing the call from completing when the comparison indicates the generated radio frequency signature is fraudulent.

10. The method as set forth in claim 9, wherein the associating step comprises the step of matching the call records with the radio frequency signatures based on one or more characteristics of both the call records and the radio frequency signature, and wherein the characteristics are selected from a group comprised of:

time of day, day of week, cell site originating location, and dialed digits for an associated call.

11. The method as set forth in claim 9, wherein the identifying step comprises the step of assigning a high fraud probability to call records containing a called number identical to known fraud dialed digits.

12. The method as set forth in claim 9, wherein the identifying step comprises the step of assigning a low fraud probability to call records containing a called number identical to known frequently called numbers for valid subscribers.

13. The method as set out in claim 1, wherein the step of identifying the fraud probability includes identifying a call to either including fraud dialed digits, or a frequently called number.

14. The method as claimed in claim 1, wherein the identifying step includes computing a score for dialed digits based on a number of fraudulent MIN/ESN combinations of calls placed to the dialed digits, the average score of each of these fraudulent MIN/ESN combinations, the number of calls placed by the fraudulent MIN/ESN combinations, the duration of calls placed by the fraudulent MIN/ESN combinations, the number of non-fraudulent MIN/ESN combinations of calls to the dialed digits, the average score of each of the non-fraudulent MIN/ESN combinations, the number of calls placed by the non-fraudulent MIN/ESN combinations, and the duration of calls placed by the non-fraudulent MIN/ESN combinations.

15. The method as claimed in claim 1, wherein the fraud identifying step includes computing a score for each set of dialed digits in a dialed digits database for a MIN/ESN combination, wherein the score is based on the number of days dialed digits are called, the number of calls made to the dialed digits, the duration of calls to the dialed digits, and the call locations for the calls to the dialed digits.

16. The method as claimed in claim 1 wherein the identification of the radio frequency signatures is effected at substantially the same time that a telephone call is made.

17. The method as claimed in claim 1 wherein the identification of the radio frequency signatures is effected at a time after a telephone call is made.

18. An apparatus for identifying valid or fraudulent phones in a cellular telephone system, comprising:

a computer system coupled to a switch in the cellular telephone system, the computer system including means for;

(1) identifying relative valid or fraud probabilities using call records received from the switch in the cellular telephone system;

(2) associating the call with corresponding radio frequency (RF) signatures; and

(3) identifying the radio frequency signatures as being fraudulent or valid based on the relative fraud probabilities for the associated calls.

19. The apparatus as set forth in claim 18 above, wherein the means for associating comprises means for matching the call records with the radio frequency signatures based on one or more characteristics of both the call records and the radio frequency signature, wherein the characteristics are selected from a group comprised of:

time of day, day of week, cell site originating location, and dialed digits for an associated call.

20. The apparatus as set forth in claim 18 above, wherein the means for identifying comprises means for assigning a high fraud probability to call records containing a called number identical to known fraud dialed digits.

21. The apparatus as set forth in claim 18 above, wherein the means for identifying comprises means for assigning a low fraud probability to call records containing a called number identical to known frequently called numbers for valid subscribers.

22. The apparatus as set forth in claim 18 above, further comprising a radio frequency signature system, coupled to the cellular telephone system and the computer system, for receiving a call transmitted from a cellular telephone, for generating a radio frequency signature for the cellular telephone, for comparing the generated radio frequency signature to the radio frequency signatures identified as fraudulent or valid, and for preventing the call from completing when the comparison indicates the generated radio frequency signature is fraudulent.