Marketing and couponing in a retail environment using computer vision

Patent metadata

Field	Value
Publication number	US-12086829-B2
Application number	US-202217947209-A
Country	US
Kind code	B2
Filing date	Sep 19, 2022
Priority date	Jan 3, 2018
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

A system and method for digital retail marketing and couponing in a physical retail environment that includes collecting image data across a retail environment; tracking a user within the retail environment; processing the image data and detecting a customer-item interaction event in association with the user; and based in part on the customer-item interaction event, delivering content to an output interface.

First claim

We claim:

1. A method for digital communication in a physical environment comprising:
collecting, from a set of image capture devices, image data across the physical environment;
tracking, based on processing of the image data, an identified user within the retail environment;
synchronizing the identified user in the image data to a detected application instance located within the physical environment, the application instance being operable on a computing device of the identified user;
modeling, using processing of the image data and using pose estimation, attention of the identified user and determining a retail item based on the attention of the identified user and based on relative position of the user to the retail item;
detecting, based on processing of the image data, a customer-item interaction event between the identified user and the retail item;
monitoring a proximity threshold based on proximity of the identified user to the retail item; and
in response to detecting the customer-item interaction event and while the identified user is within the proximity threshold, initiating a real-time content delivery auction, comprising selecting a set of auction bids based in part on the retail item and the identified user, ranking the set of auction bids, selecting content of a digital message based on the ranking of the set of auction bids, and, while the identified user is within the proximity threshold, transmitting, via a network, the digital message to the computing device.

2. The method of claim 1 , wherein the computing device comprises an application instance signed into an account of the user.

3. The method of claim 2 , wherein the digital message is a digital coupon.

4. The method of claim 1 , wherein detecting the customer-item interaction event further comprises detecting the occurrence or non-occurrence of a customer-item interaction event selected from the set of interactions invents including detecting customer attention directed at an item, detecting an item pickup event, detecting item selection, and detecting an item put-back event.

5. The method of claim 1 , further comprising:
wherein tracking the user comprises detecting customer proximity to an item;
monitoring a content delivery condition that is based in part on the customer-item interaction event and the customer proximity to the item; and
wherein transmitting the digital message to the computing device is initiated upon satisfying the content delivery condition.

6. The method of claim 5 , wherein monitoring the content delivery condition comprises detecting occurrence of a first customer-item interaction event selected from a set consisting of a user attention event, an item pickup event, an item selection event, and an item put-back event.

7. The method of claim 6 , wherein monitoring the content delivery condition further comprises detecting a sequence of item-level interaction events that includes a first item-level interaction event.

8. The method of claim 5 , wherein monitoring the content delivery condition comprises detecting omission of a second customer-item interaction event performed by the user when within a defined proximity to the retail item.

9. The method of claim 1 , wherein selecting content of the digital message is further selected based on cart contents of the user.

10. The method of claim 1 , wherein selecting the set of auction bids comprises selecting auction bids for the set of auction bids that are associated with items in proximity to the retail item.

11. The method of claim 10 , wherein selecting the auction bids for the set of auction bids that are associated with items in proximity to the item comprises determining, by processing the image data, items in proximity to the retail item.

12. The method of claim 1 , further comprising tracking a content delivery response and crediting a marketing account of the selected content according to the content delivery response.

13. The method of claim 1 , further comprising tracking a content delivery response to the digital message.

14. A system for digital communication in a physical environment which comprises:
a computer vision monitoring system that comprises a set of imaging devices installed in the environment, and that is configured to:
collect, from the set of imaging devices, image data of the environment,
track a set of users within the retail environment,
for an identified user of the set of users, synchronize the identified user in the image data to a detected application instance located within the physical environment, the application instance being operable on a computing device of the identified user,
model, using processing of the image data and pose estimation, attention of the identified user and determining a retail item based on the attention of the identified user and based on relative position of the user to the retail item,
for the identified user, process the image data and detect a customer-item interaction event between the identified user and the retail item,
monitor a proximity threshold based on proximity of the identified user to the retail item; and

a content marketing system configured to, in response to detection of the customer-item interaction event and while the identified user is within the proximity threshold, initiate a real-time content delivery auction, which comprises:
selecting a set of auction bids based in part on the retail item and the identified user,
ranking the set of auction bids,
selecting content of a digital message based on the ranking of the set of auction bids, and
while the identified user is within the proximity threshold, transmitting, via a network, the digital message to the computing device.

15. The system of claim 14 , wherein the computing device comprises an application instance signed into an account of the user.

16. The system of claim 14 , further comprising a set of environment-installed computing devices; and wherein the content management system is configured to select the computing device from the set of environment-installed computing devices based on device proximity to the user or an item of the customer-item interaction event.

Assignees

• Grabango Co

Inventors

• Glaser William
• Van Osdol Brian

Classifications

• G06V20/00

  Scenes; Scene-specific elements (control of digital cameras H04N23/60) · CPC title

• G06V40/28

  Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113) · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06V20/44

  Event detection · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title