Intelligent video verification of point of sale (POS) transactions

• US 9,277,185 B2
• Filed: 04/08/2011
• Issued: 03/01/2016
• Est. Priority Date: 05/25/2006
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Fortress Corporation (Motorola Solutions, Inc.)
• Inventors: Lipton, Alan J., Venetianer, Pter L., Yu, Li, Hu, Yongtong, Scanlon, W. Andrew, Zhang, Zhong, Yin, Weihong
• Primary Examiner(s): Iwarere, Seye
• Application Number:
  US13/082,686
• Publication Number:
  US 20110191195A1
• Time in Patent Office: 1,789 Days
• Field of Search: 705/16
• US Class Current: 1/1
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/401 Transaction verification
• CPC Class Codes: G07G 1/0036 Checkout procedures
• CPC Class Codes: G07G 3/00 Alarm indicators, e.g. bells
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A method of monitoring a point of sale (POS) transaction including: receiving non video data regarding the POS transaction; defining exceptional transaction rules based at least on predetermined non video POS data events; inferring a potentially exceptional transaction based on a corresponding exceptional transaction rule and the received POS non video data; and verifying the inferred potentially exceptional transaction with video data regarding a corresponding POS transaction.

Claims

1. A non-transitory computer-readable medium comprising software that monitors a point of sale (POS) transaction at a POS terminal, which software, when executed by a computer system, causes the computer system to perform operations comprising:

receiving non-video data regarding the POS transaction;

defining one or more exceptional transaction rules based on one or more predetermined non-video POS data events;

inferring that the POS transaction comprises a potentially exceptional transaction based on a corresponding one of the one or more exceptional transaction rules and the received non-video data;

obtaining video data regarding the POS transaction, wherein the obtaining comprises one of;

receiving the video data regarding the POS transaction from a video camera, and

storing the video data regarding the POS transaction obtained by the video camera in an archive and receiving the video data regarding the POS transaction from the archive;

generating one or more video primitives by processing the received video data regarding the POS transaction, the one or more video primitives comprising data descriptions of content of the received video data regarding the POS transaction; and

determining that the inferred potentially exceptional transaction comprises a verified exceptional transaction by automatically analyzing the received video data regarding the POS transaction, wherein the determining includes;

generating a video event based on the one or more video primitives and a corresponding video rule; and

confirming the inferred potentially exceptional transaction as an exceptional transaction based on the generated video event.

2. The non-transitory computer-readable medium as set forth in claim 1, wherein receiving video data further includes:

receiving auxiliary video data obtained by one or more auxiliary video cameras.

3. The non-transitory computer-readable medium as set forth in claim 1, wherein the operations further include:

defining one or more policy violation rules based at least on one or more predetermined exceptional transactions; and

determining a policy violation based on a corresponding policy violation rule of the one or more policy violation rules and at least one of the verified exception transaction or the potentially inferred exceptional transaction.

4. The non-transitory computer-readable medium as set forth in claim 3, wherein the operations further include:

generating a policy violation report based on the determined policy violation.

5. The non-transitory computer-readable medium as set forth in claim 1, wherein the operations further include:

generating an exceptional transaction report based on at least one of the verified exception transaction or the potentially inferred exceptional transaction.

6. A method for monitoring a point of sale (POS) transaction at a POS terminal, comprising:

receiving non-video POS transaction data by one or more processors;

defining, by the one or more processors, one or more exceptional transaction rules based on one or more predetermined video data events;

inferring, by the one or more processors, that the POS transaction comprises a potentially exceptional transaction based on a corresponding one of the exceptional transaction rules and the received non-video POS transaction data;

obtaining, by the one or more processors, video data regarding the POS, wherein obtaining comprises one of;

receiving, by the one or more processors, the video data regarding the POS transaction from a video camera, and

storing the video data regarding the POS transaction obtained by the video camera in an archive and receiving, by the one or more processors, the video data regarding the POS transaction from the archive;

generating, by the one or more processors, one or more video primitives by processing the received video data regarding the POS transaction, the one or more video primitives comprising data descriptions of content of the received video data regarding the POS transaction; and

determining, by the or more processors, that the inferred potentially exceptional transaction comprises a verified exceptional transaction by automatically analyzing the video data regarding the POS transaction, wherein the determining includes;

generating, by the one or more processors, a video event based on the one or more video primitives and corresponding video rule; and

confirming, by the one or more processors, the inferred potentially exceptional transaction as an exceptional transaction based on the generated video event.

7. The method for monitoring a point of sale (POS) transaction according to claim 6, wherein the method is performed locally.

8. The method for monitoring a point of sale (POS) transaction according to claim 6, wherein the method further includes:

receiving the non-video POS transaction data via a communication channel at a remote location;

defining, at the remote location, the one or more exceptional transactions rules based on one or more predetermined non-video data events and the one or more predetermined video data events; and

inferring, at the remote location, the potentially exceptional transaction.

9. The method for monitoring a point of sale (POS) transaction according to claim 8, wherein the method further includes:

requesting transmission of the video data regarding the POS transaction to the remote location;

receiving, at the remote location, the video data regarding the POS transaction via the communication channel;

generating, at the remote location, video primitives based on the received video data;

generating, at the remote location, a video event based on a video rule and the video primitives; and

confirming, at the remote location, the inferred potentially exceptional transaction based on the video event.

11. A method comprising at least one of:

downloading software to a computer system, which software, when executed by the computer system, causes the computer system to perform operations comprising the method of claim 6;

or

providing downloadable software to a computer system, which software, when executed by the computer system, causes the computer system to perform operations comprising the method of claim 6.

10. A method comprising:

downloading software or providing downloadable software to a computer system, the computer system comprising one or more processors, which software, when executed by the one or more processors, causes the computer system to perform operations comprising;

receiving non-video data regarding a point of sale (POS) transaction;

generating one or more POS primitives by processing the received non-video POS data the one or more POS primitives comprising data descriptions of the content of the received non-video POS data;

receiving video data regarding the corresponding POS transaction;

processing the received video data to generate one or more video primitives using the first or a second computer processor, the one or more video primitives being data descriptions of the content of the received video data;

defining one or more exceptional transaction rules based on at least one predetermined video data event and at least one predetermined non-video data event; and

inferring an exceptional transaction based on a corresponding one of the one or more exceptional transaction rules and at least one of the one or more POS primitives or at least one of the one or more video primitives.