AUDITING PURCHASING SYSTEM

Abstract

Techniques for auditing purchases are provided. An item for purchase is scanned to determine a first identity of the item. The scanned item is added to a transaction. A first image of the scanned item is captured using a first camera. A second identity of the scanned item from the first image is determined using a trained machine learning (ML) model. Responsive to determining the first and second identities of the item do not match, an audit of the transaction is performed.

Description

Claims

1. A method comprising: scanning an item for purchase to determine a first identity of the item;adding the scanned item to a transaction;capturing, using a first camera, a first image of the scanned item;determining a second identity of the scanned item from the first image using a trained machine learning (ML) model; andresponsive to determining the first and second identities of the item do not match, performing an audit of the transaction.

2. The method of claim 1, further comprising training the ML model, wherein training the ML model further comprises: inputting a plurality of images for a training item, wherein the plurality of images are used to train the ML model to recognize the training item.

3. The method of claim 1, wherein performing an audit of the transaction further comprises: capturing, using a second camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model; anddetermining whether the first identify matches the third identity.

4. The method of claim 3, wherein performing the audit of the transaction further comprises: responsive to determining the first identify and the third identity do not match, notifying an employee.

5. The method of claim 1, wherein performing the audit of the transaction further comprises: capturing, using the first camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model;determining whether the first identify matches the third identity; andresponsive to determining the first identify and the third identity do not match, notifying an employee to take further action.

6. The method of claim 1, wherein the scan takes place at one of the following: a self-service kiosk or a mobile shopping application.

7. The method of claim 1, wherein the audit takes place at one of the following: a self-service kiosk, an audit station, or a mobile shopping application.

8. The method of claim 7, wherein: the audit takes place at the audit station,the first camera is located on the self-service kiosk, anda second camera is located on the audit station.

9. A system, comprising: one or more computer processors; anda memory containing a program which when executed by the one or more computer processors performs an operation, the operation comprising: scanning an item for purchase to determine a first identity of the item;adding the scanned item to a transaction;capturing, using a first camera, a first image of the scanned item;determining a second identity of the scanned item from the first image using a trained machine learning (ML) model; andresponsive to determining the first and second identities of the item do not match, performing an audit of the transaction.

10. The system of claim 9, further comprising training the ML model, wherein training the ML model further comprises: inputting a plurality of images for a training item, wherein the plurality of images are used to train the ML model to recognize the training item.

11. The system of claim 9, wherein performing an audit of the transaction further comprises: capturing, using a second camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model; anddetermining whether the first identify matches the third identity.

12. The system of claim 11, wherein performing the audit of the transaction further comprises: responsive to determining the first identify and the third identity do not match, notifying an employee.

13. The system of claim 9, wherein performing the audit of the transaction further comprises: capturing, using the first camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model;determining whether the first identify matches the third identity; andresponsive to determining the first identify and the third identity do not match, notifying an employee to take further action.

14. The system of claim 9, wherein: the scan takes place at one of the following: a self-service kiosk or a mobile shopping application, andthe audit takes place at one of the following: a self-service kiosk, an audit station, or a mobile shopping application.

15. A computer program product for auditing purchases, the computer program product comprising: a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to: scan an item for purchase to determine a first identity of the item;add the scanned item to a transaction;capture, using a first camera, a first image of the scanned item;determine a second identity of the scanned item from the first image using a trained machine learning (ML) model; andresponsive to determining the first and second identities of the item do not match, perform an audit of the transaction.

16. The computer program product of claim 15, wherein the computer-readable program code is further executable to train the ML model, wherein training the ML model further comprises: inputting a plurality of images for a training item, wherein the plurality of images are used to train the ML model to recognize the training item.

17. The computer program product of claim 15, wherein performing an audit of the transaction further comprises: capturing, using a second camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model; anddetermining whether the first identify matches the third identity.

18. The computer program product of claim 17, wherein performing the audit of the transaction further comprises: responsive to determining the first identify and the third identity do not match, notifying an employee.

19. The computer program product of claim 15, wherein performing the audit of the transaction further comprises: capturing, using the first camera, a second image of the scanned item;determining a third identify of the scanned item from the second image using a second trained ML model;determining whether the first identify matches the third identity; andresponsive to determining the first identify and the third identity do not match, notifying an employee to take further action.

20. The computer program product of claim 15, wherein: the scan takes place at one of the following: a self-service kiosk or a mobile shopping application, andthe audit takes place at one of the following: a self-service kiosk, an audit station, or a mobile shopping application.