Point of sale integration with video analytics for fraud detection

• US 9,137,500 B1
• Filed: 12/09/2011
• Issued: 09/15/2015
• Est. Priority Date: 12/10/2010
• Status: Active Grant

• Current Assignee: Cognyte Technologies Israel Ltd. (Cognyte Software Ltd.)
• Original Assignee: Verint Systems Incorporated
• Inventors: Wachman, Eran, Dudovich, Boaz
• Primary Examiner(s): WONG, ALLEN C
• Application Number:
  US13/316,218
• Time in Patent Office: 1,376 Days
• Field of Search: 348/143, 348/150
• US Class Current: 1/1
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/208 Input by product or record sensing, e.g. weighing or scanner processing
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G07G 3/003 Anti-theft control theft alarms G08B13/00
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A method of operating a video system to detect fraudulent return transactions comprises receiving an indication of a return transaction from a point of sale system, wherein the indication of the return transaction indicates a time when the return transaction occurred. The method further comprises receiving video data of an area proximate to the point of sale system captured at the time when the return transaction occurred. The method further comprises processing the video data to determine whether a first person is located in a return area and whether a second person is located proximate to the point of sale system. The method further comprises determining whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system.

Claims

1. A method of operating a video system to detect fraudulent return transactions, the method comprising:

receiving an indication of a return transaction from a point of sale system, wherein the indication of the return transaction indicates a time when the return transaction occurred;

receiving video data of an area proximate to the point of sale system captured at the time when the return transaction occurred;

processing, by a processor, the video data to determine whether a first person is located in a return area and whether a second person is located proximate to the point of sale system; and

determining, by the processor, whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system;

wherein determining whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises flagging, by the processor, the return transaction as potentially fraudulent when the first person is located in the return area, the second person is located proximate to the different point of sale system, and a third person is located proximate to the point of sale system.

2. The method of claim 1 wherein determining whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises determining, by the processor, that the return transaction is legitimate when the first person is located in the return area and the second person is located proximate to the point of sale system.

3. The method of claim 1 wherein determining whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises determining, by the processor, that the return transaction is legitimate when the first person is located in the return area, no person is located proximate to the point of sale system, and the second person is located proximate to a different point of sale system.

4. The method of claim 1 wherein determining whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises flagging, by the processor, the return transaction as potentially fraudulent when the first person is not located in the return area and the second person is located proximate to the point of sale system.

5. The method of claim 1 further comprising providing the return transaction for review if the return transaction is determined to be fraudulent.

6. The method of claim 1 wherein receiving the video data of the area proximate to the point of sale system captured at the time when the return transaction occurred comprises, in response to receiving the indication of the return transaction from the point of sale system, requesting the video data captured at the time when the return transaction occurred and responsively receiving the video data of the area proximate to the point of sale system captured at the time when the return transaction occurred.

7. The method of claim 1 wherein processing the video data to determine whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises analyzing, by the processor, the video data to identify the return area and an area proximate to the point of sale system.

8. The method of claim 7 wherein analyzing the video data to identify the return area comprises analyzing, by the processor, the video data to recognize predetermined coordinates of the return area relative to the video data.

9. A non-transitory computer-readable medium having program instructions stored thereon for operating a video system to detect fraudulent return transactions, wherein the program instructions, when executed by a computer system, direct the computer system to:

receive an indication of a return transaction from a point of sale system, wherein the indication of the return transaction indicates a time when the return transaction occurred;

receive video data of an area proximate to the point of sale system captured at the time when the return transaction occurred;

process the video data to determine whether a first person is located in a return area and whether a second person is located proximate to the point of sale system; and

determine whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system;

wherein the program instructions, to direct the computer system to determine whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system, instruct the computer system to flag the return transaction as potentially fraudulent when the first person is located in the return area, the second person is located proximate to the different point of sale system, and a third person is located proximate to the point of sale system.

10. The non-transitory computer-readable medium of claim 9 wherein the program instructions, to direct the computer system to determine whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system, instruct the computer system to determine that the return transaction is legitimate when the first person is located in the return area and the second person is located proximate to the point of sale system.

11. The non-transitory computer-readable medium of claim 9 wherein the program instructions, to direct the computer system to determine whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system, instructs the computer system to determine that the return transaction is legitimate when the first person is located in the return area, no person is located proximate to the point of sale system, and the second person is located proximate to a different point of sale system.

12. The non-transitory computer-readable medium of claim 9 wherein the program instructions, to direct the computer system to determine whether the return transaction is legitimate or fraudulent based on whether the first person is located in the return area and whether the second person is located proximate to the point of sale system, instruct the computer system to flag the return transaction as potentially fraudulent when the first person is not located in the return area and the second person is located proximate to the point of sale system.

13. The non-transitory computer-readable medium of claim 9 further comprising the program instructions configured to direct the computer system to provide the return transaction for review if the return transaction is determined to be fraudulent.

14. The non-transitory computer-readable medium of claim 9 wherein the program instructions, to direct the computer system to receive the video data of the area proximate to the point of sale system captured at the time when the return transaction occurred, instruct the computer system to, in response to receiving the indication of the return transaction from the point of sale system, request the video data captured at the time when the return transaction occurred and responsively receive the video data of the area proximate to the point of sale system captured at the time when the return transaction occurred.

15. The non-transitory computer-readable medium of claim 9 wherein the program instructions, to direct the computer system to process the video data to determine whether the first person is located in the return area and whether the second person is located proximate to the point of sale system, instruct the computer system to analyze the video data to identify the return area and an area proximate to the point of sale system.

16. The non-transitory computer-readable medium of claim 15 wherein the program instructions, to direct the computer system to analyze the video data to identify the return area, instruct the computer system to analyze the video data to recognize predetermined coordinates of the return area relative to the video data.

17. A method of operating a video system to detect fraudulent return transactions, the method comprising:

receiving an indication of a return transaction from a point of sale system, wherein the indication of the return transaction indicates a time when the return transaction occurred;

receiving video data of an area proximate to the point of sale system captured at the time when the return transaction occurred;

processing, by a processor, the video data to determine whether a first person is located in a return area and whether a second person is located proximate to the point of sale system;

if the first person is located in the return area and the second person is located proximate to the point of sale system, determining that the return transaction is legitimate;

if the first person is located in the return area, no person is located proximate to the point of sale system, and the second person is located proximate to a different point of sale system, determining, by the processor, that the return transaction is legitimate;

if the first person is located in the return area, the second person is located proximate to the different point of sale system, and a third person is located proximate to the point of sale system, flagging, by the processor, the return transaction as potentially fraudulent; and

if the first person is not located in the return area and the second person is located proximate to the point of sale system, flagging, by the processor, the return transaction as potentially fraudulent.

18. The method of claim 17 wherein processing the video data to determine whether the first person is located in the return area and whether the second person is located proximate to the point of sale system comprises analyzing, by the processor, the video data to identify the return area and an area proximate to the point of sale system.