INDIVIDUAL BIOMETRIC-BASED TRACKING

• US 20190333123A1
• Filed: 04/27/2018
• Published: 10/31/2019
• Est. Priority Date: 04/27/2018
• Status: Active Grant

• Current Assignee: NCR Voyix Corporation
• Original Assignee: NCR Corporation (NCR Voyix Corporation)
• Inventors: Licht, Yehoshua Zvi
• Granted Patent: US 10,936,854 B2
• Time in Patent Office: Days
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• 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: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Real-time individual tracking at a site is provided by capturing an image at a specific location for the individual, extracting a limited number of biometric features from the image, and providing a searching mechanism for matching the scored biometric features to the individual at the specific location.

Claims

1. A method, comprising:

extracting features from an image of an individual;

associating the features with a location;

identifying a specific customer from the features; and

reporting the features, the location, and the specific customer.

2. The method of claim 1, wherein extracting further includes extracting the features as a set of unique biometric measurements taken from a face identified in the image.

3. The method of claim 2, wherein extracting further includes identifying the set as 120 unique biometric measurements taken from the face identified in the image.

4. The method of claim 1, wherein extracting further includes extracting some of the features as biometric features for the individual and other ones of the features as non-biometric features for the individual.

5. The method of claim 1, wherein extracting further includes receiving a customer identifier or a link to a customer account with the image.

6. The method of claim 1, wherein associating further includes identifying the location based on a known location for a camera that captured the image.

7. The method of claim 1, wherein identifying further includes scoring the features to produce a score and searching a data store with the score to identify the specific customer.

8. The method of claim 1, wherein identifying further includes providing the features to a machine learning algorithm and receiving as output from the machine learning algorithm an identifier for the specific customer or a link to a customer account associated with the specific customer.

9. The method of claim 1, wherein reporting further includes maintaining a linked list for the specific customer that includes:

the features, the location, and an identifier for the specific customer or a link to a customer account associated with the specific customer.

10. The method of claim 9, receiving a payment token from a transaction of the specific customer and adding the payment token to the linked list.

12. The method of claim 1 further comprising, updating a customer account associated with the specific customer with the features and the location.

13-1. The method of claim 12, wherein checking further includes receiving a notice sent automatically from a customer-operated device when the customer enters the store.

14. The method of claim 12, wherein capturing further includes receiving the image from a camera located in the store at a check-in location.

15. The method of claim 12, wherein extracting further includes extracting the set of biometric features as a predefined number of unique measurements taken from the image for the face.

16. The method of claim 12, wherein updating further includes creating a linked list that includes:

a link to the customer account, a check-in location of the customer based on a particular location of a camera that captured the image, and the set of biometric features while the customer shops in the store.

17. The method of claim 12, wherein tracking further includes updating the customer account with the second set of biometric features and the different locations while the customer shops in the store.

11. The method of claim 11 further comprising, providing the payment token from the linked list as payment for a second transaction of the specific customer.

13. A method, comprising:

checking a customer into a store;

capturing an image of a face of the customer during check-in;

extracting a set of biometric features for the face from the image;

updating a customer account for the customer with the set of biometric features;

obtaining second images of the face at different locations within the store; and

tracking the customer at those different locations based on matching second sets of biometric features extracted from the second images and performing a search against a customer data store that includes the customer account.

18. A system, comprising:

a server having at least one hardware processor;

a real-time order people tracker configured to;

(i) execute on the hardware processor, (ii) extract biometric features from images taken of customers while in a store, (iii) link the biometric features to accounts of the customers, and (iv) track each of the customers and locations of the customers while in the store based on the biometric features.

19. The system of claim 18, wherein the real-time people tracker is further configured to:

(v) link payment tokens to the customer accounts for automated payment by the customers at the locations within the store.

20. The system of claim 18, wherein the real-time people tracker is further configured to:

(v) process a machine-learning algorithm to match specific biometric features to specific customers.