Generating an alert based on absence of a given person in a transaction

• US 8,429,016 B2
• Filed: 10/31/2008
• Issued: 04/23/2013
• Est. Priority Date: 10/31/2008
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Bobbitt, Russell Patrick, Fan, Quanfu, Hampapur, Arun, Kjeldsen, Frederik, Pankanti, Sharathchandra Umapathirao, Yanagawa, Akira, Zhai, Yun
• Primary Examiner(s): Zeender, F.
• Assistant Examiner(s): BUCHANAN, CHRISTOPHER R
• Application Number:
  US12/262,454
• Publication Number:
  US 20100114746A1
• Time in Patent Office: 1,635 Days
• Field of Search: None
• US Class Current: 705/16
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

Techniques for generating an alert based on absence of a given person in a transaction are provided. The techniques include monitoring, via video, a transaction, wherein the transaction includes presence of a given person in the transaction, relating the video of the transaction to a corresponding portion of a transaction log (TLOG), using the video and corresponding portion of the TLOG to detect if the given person in the transaction is present, and generating an alert if the given person is not present at the transaction.

Claims

1. A method for generating an alert based on absence of a given person in a transaction, comprising the steps of:

monitoring, via video from a camera, a transaction at an enterprise retail checkout;

relating the video of the transaction to a corresponding portion of a transaction log to match a description of the transaction in question with the video of the transaction, wherein the transaction log includes a description of checkout events at the enterprise retail checkout and one or more specific people required by enterprise policy to be present in the transaction;

comparing the video of the transaction and the description of the transaction from the corresponding portion of the transaction log to detect if the one or more specific people required by the enterprise policy in the description of the transaction is present in the video, wherein comparing the video of the transaction and the description of the transaction from the corresponding portion of the transaction log to detect if the one or more specific people required by the enterprise policy in the description of the transaction is present in the video is carried out by a visual analytic engine module executing on a hardware processor; and

generating an alert if the one or more specific people required to be present by the enterprise policy are not present in the video of the transaction, wherein generating an alert is carried out by a module executing on a hardware processor.

2. The method of claim 1, wherein detecting if the given person in the transaction is present comprises:

using a model of checkout events; and

using a visual analytic engine to analyze the video of the transaction.

3. The method of claim 1, wherein the transaction comprises at least one of a void, a refund and an override.

4. The method of claim 1, wherein detecting if the given person in the transaction is present comprises using a visual analytic engine to detect one or more persons in the transaction.

5. The method of claim 4, further comprising using a visual analytic engine to categorize each of the one or more persons as one of a shopper, a cashier, and a manager.

6. The method of claim 1, wherein the transaction comprises a retail transaction at a retail checkout.

7. The method of claim 1, further comprising detecting a foreground object in the video of the transaction.

8. The method of claim 1, further comprising obtaining a signal from the transaction log that the transaction is a transaction that requires one or more specific people.

9. The method of claim 1, further comprising generating an alert if a mis-match between a visual result and the transaction log is detected.

10. A computer program product comprising a computer readable non-transitory medium having computer readable program code for generating an alert based on absence of a given person in a transaction, said computer program product including:

computer readable program code for monitoring, via video from a camera, a transaction at an enterprise retail checkout;

computer readable program code for relating the video of the transaction to a corresponding portion of a transaction log to match a description of the transaction in question with the video of the transaction, wherein the transaction log includes a description of checkout events at the enterprise retail checkout and one or more specific people required by enterprise policy to be present in the transaction;

computer readable program code for comparing the video of the transaction and the description of the transaction from the corresponding portion of the transaction log to detect if the one or more specific people required by the enterprise policy in the description of the transaction is present in the video; and

computer readable program code for generating an alert if the one or more specific people required to be present by the enterprise policy are not present in the video of the transaction.

11. The computer program product of claim 10, wherein the computer readable program code for detecting if the given person in the transaction is present comprises:

computer readable program code for using a model of checkout model events; and

computer readable program code for using a visual analytic engine to analyze the video of the transaction.

12. The computer program product of claim 10, wherein the computer readable program code for detecting if the given person in the transaction is present comprises computer readable program code for using a visual analytic engine to detect one or more persons in the transaction.

13. The computer program product of claim 12, further comprising computer readable program code for using a visual analytic engine to categorize each of the one or more persons as one of a shopper, a cashier, and a manager.

14. The computer program product of claim 10, further comprising computer readable program code for detecting a foreground object in the video of the transaction.

15. The computer program product of claim 10, further comprising computer readable program code for obtaining a signal from the transaction log that the transaction is a transaction that requires one or more specific people.

16. The computer program product of claim 10, further comprising computer readable program code for generating an alert if a mis-match between a visual result and the transaction log is detected.

17. The computer program product of claim 10, wherein the transaction comprises at least one of a void, a refund and an override.

18. A system for generating an alert based on absence of a given person in a transaction, comprising:

a memory; and

at least one processor coupled to said memory and operative to;

monitor, via video from a camera, a transaction at an enterprise retail checkout;

relate the video of the transaction to a corresponding portion of a transaction log to match a description of the transaction in question with the video of the transaction, wherein the transaction log includes a description of checkout events at the enterprise retail checkout and one or more specific people required by enterprise policy to be present in the transaction;

compare the video of the transaction and the description of the transaction from the corresponding portion of the transaction log to detect if the one or more specific people required by the enterprise policy in the description of the transaction is present in the video; and

generate an alert if the one or more specific people required to be present by the enterprise policy are not present in the video of the transaction.

19. The system of claim 18, wherein in detecting if the given person in the transaction is present the at least one processor coupled to said memory is further operative to:

use a model of checkout model events; and

use a visual analytic engine to analyze the video of the transaction.

20. The system of claim 18, wherein in detecting if the given person in the transaction is present the at least one processor coupled to said memory is further operative to use a visual analytic engine to detect one or more persons in the transaction.

21. The system of claim 20, wherein the at least one processor coupled to said memory is operative to use a visual analytic engine to categorize each of the one or more persons as one of a shopper, a cashier, and a manager.

22. The system of claim 18, wherein the at least one processor coupled to said memory is operative to detect a foreground object in the video of the transaction.

23. The system of claim 18, wherein the at least one processor coupled to said memory is operative to obtain a signal from the transaction log that the transaction is a transaction that requires one or more specific people.

24. The system of claim 18, wherein the at least one processor coupled to said memory is operative to generate an alert if a mis-match between a visual result and the transaction log is detected.

25. An apparatus for generating an alert based on absence of a given person in a transaction, said apparatus comprising:

means for monitoring, via video from a camera, a transaction at an enterprise retail checkout;

means for relating the video of the transaction to a corresponding portion of a transaction log to match a description of the transaction in question with the video of the transaction, wherein the transaction log includes a description of checkout events at the enterprise retail checkout and one or more specific people required by enterprise policy to be present in the transaction;

means for comparing the video of the transaction and the description of the transaction from the corresponding portion of the transaction log to detect if the one or more specific people required by the enterprise policy in the description of the transaction is present in the video; and

means for generating an alert if the one or more specific people required to be present by the enterprise policy are not present in the video of the transaction.