Intelligent video verification of point of sale (POS) transactions

• US 10,755,259 B2
• Filed: 12/28/2018
• Issued: 08/25/2020
• Est. Priority Date: 05/25/2006
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Fortress Corporation
• Inventors: Lipton, Alan J., Venetianer, Peter L., Yu, Li, Hu, Yongtong, Scanlon, W. Andrew, Zhang, Zhong, Yin, Weihong
• Primary Examiner(s): Iwarere, Oluseye
• Application Number:
  US16/235,073
• Publication Number:
  US 20190251537A1
• Time in Patent Office: 606 Days
• Field of Search: 235383, 705 28
• 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

Methods and systems are provided for monitoring a point of sale (POS) transaction. Operations performed by the methods and systems include generating POS primitives by processing non-video data of a transaction recorded at POS terminal. The operations also include generating video primitives by processing video data of the transaction recorded at the POS terminal. The operations further include determining that the transaction comprises an exceptional transaction by comparing the non-video data and/or the video data to exceptional transaction rules. Additionally, the operations include determining that the exceptional transaction comprises a verified exceptional transaction by generating a video event based on the video primitives and a corresponding video rule.

Claims

1. A computing system comprising:

a processor;

a computer-readable memory device; and

program instructions stored on the computer-readable memory device that, when executed by the processor, causes the computing system to perform operations comprising;

generating one or more point of sale (POS) primitives by processing non-video data of a transaction recorded at a POS terminal, the one or more POS primitives comprising data descriptions of the content of the non-video data;

generating first video primitives by processing primary video data of the transaction recorded at the POS terminal, the first video primitives comprising data descriptions of the content of the primary video data;

generating second video primitives by performing facial recognition on secondary video data different than the first video data, the second video primitives comprising data descriptions of the content of the secondary video data, wherein the secondary video data comprises video of an individual involved in the transaction; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least portions of each of the POS primitives, the first video primitives and the second video primitives.

4. The computing system as claimed in claim 1, further comprising an appliance configured to perform said operations.

5. The computing system as claimed in claim 1, further comprising a digital video recorder configured to perform said operations.

6. The computing system as claimed in claim 1, further comprising a network video recorder configured to perform said operations.

7. The computing system as claimed in claim 1, wherein the primary and secondary video data comprising video data captured by first and second video cameras respectively, and wherein the second video camera provides better face snapshots than the first video camera.

2. A method comprising:

generating one or more point of sale (POS) primitives by processing non-video data of a transaction recorded at a POS terminal, the one or more POS primitives comprising data descriptions of the content of the non-video data;

generating first video primitives by processing primary video data of the transaction recorded at the POS terminal, the first video primitives comprising data descriptions of the content of the primary video data;

generating second video primitives by performing facial recognition on secondary video data different than the first video data, the second video primitives comprising data descriptions of the content of the secondary video data, wherein the secondary video data comprises video of an individual involved in the transaction; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least portions of each of the POS primitives, the first video primitives and the second video primitives.

8. The method as claimed in claim 2, wherein the primary and secondary video data comprising video data captured by first and second video cameras respectively, and wherein the second video camera provides better face snapshots than the first video camera.

3. A non-transitory computer-readable memory device storing program instructions that, when executed by a processor, causes a computer system to perform operations comprising:

generating one or more point of sale (POS) primitives by processing non-video data of a transaction recorded at a POS terminal, the one or more POS primitives comprising data descriptions of the content of the non-video data;

generating first video primitives by processing primary video data of the transaction recorded at the POS terminal, the first video primitives comprising data descriptions of the content of the primary video data;

generating second video primitives by performing facial recognition on secondary video data different than the first video data, the second video primitives comprising data descriptions of the content of the secondary video data, wherein the secondary video data comprises video of an individual involved in the transaction; and

inferring an exceptional transaction based on a corresponding exceptional transaction rule and at least portions of each of the POS primitives, the first video primitives and the second video primitives.

9. The computer-readable memory device as claimed in claim 3, wherein the primary and secondary video data comprising video data captured by first and second video cameras respectively, and wherein the second video camera provides better face snapshots than the first video camera.