IP Library Granted Patent US 11,416,902
Granted Patent B2
US 11,416,902 · App. 15/894,006 · Granted Aug 16, 2022

Notification system and methods for use in retail environments

Inventors: Malay Kundu (Lexington, MA); Joshua Migdal (Wayland, MA)
Assignee: NCR Corporation
G06Q30/0609
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,416,902
App. No.
15/894,006
Granted
Aug 16, 2022
Kind
B2
Abstract

A scan avoidance monitoring system detects instances in which a respective customer in a retail environment fails to properly scan or tally one or more retail items for purchase. To avoid generating false positives, such as flagging of events as scan avoidances when they really are not or likely are not scan avoidances, the scan avoidance system can be configured to require a level of confirmation by one or more other analyzers to flag a particular circumstance as a scan avoidance.

Claims (24)

1. In a retail environment having item carriages and customer operated handheld scanners in lieu of fixed point of sale (POS) scanning stations, a method of detecting unauthorized retail item movement, comprising:

receiving, by instructions that execute on a hardware processor of a device, video data depicting images of a customer in the retail environment placing a set of retail items into an item carrier apparatus;

receiving, by the instructions, a log of transaction data itemizing presence of at least a portion of the retail items handled by the customer and placed in the item carrier apparatus, the log based on scanning information from an item scanner device operable to scan each item in the portion of retail items as the item is placed into the item carrier apparatus;

detecting, by the instructions, a location of the item carrier apparatus based on analysis of received video data;

detecting, by the instructions, video events based on via video analysis of the received video data, the video events capturing placement and timing of the given retail item in the item carrier apparatus; and

comparing, by the instructions, the received log of transaction data and the video events;

detecting, by the instructions, absence of a transaction record in the log for the given retail item placed in the item carrier apparatus based on a failure to find presence of the transaction record in the log corresponding to a particular video event around the time when the given retail item was placed in the item carrier apparatus.

2. The method of claim 1 further comprising:

receiving item information indicating a location of different retail items available in the retail environment; and

evaluating the log of transaction data in view of the item information to determine if the video events are suspicious.

3. The method of claim 1 further comprising:

receiving, by the instructions, sensor data associated with placing of the set of retail items into the item carrier apparatus, the sensor data generated by sensor hardware other than an item scanner device used by the customer to produce the log of transaction data;

analyzing, by the instructions, the sensor data to detect sensor events; and in the computer system, based on a combined analysis of the video events and the sensor events, confirm that the activity is suspicious.

4. The method of claim 3 further comprising:

generating, by the instructions, a first output value for a detected video event;

generating, by the instructions, a second output value for a detected sensor event;

generating, by the instructions, an aggregated value based on a combination of the first output value and the second output value; and

based on comparison of the aggregated value to a threshold value, generating, by the instructions, an overall output value indicative of whether a customer action corresponding to the detected video event and the detected sensor event is suspicious.

5. The method of claim 4 further comprising:

generating, by the instructions, a first probability value indicating a degree to which a detected video event as captured by the video data is suspicious in view of monitoring a first attribute of a customer action in the shopping area;

generating, by the instructions, a second probability value indicating a degree to which a detected sensor event as captured by the sensor data is suspicious in view of monitoring a second attribute of the customer action in the shopping area;

combining, by the instructions, the first probability value and the second probability value under a probabilistic framework to produce an output value, the output value indicating a degree to which the customer action is suspicious.

6. The method of claim 1 further comprising:

in response to detecting the absence of the transaction record in the log for the given retail item placed in the item carrier apparatus, sending, by the instructions, an alert to a receiving device.

Assignments (4)
CHANGE OF NAME Recorded Dec 7, 2023
From: NCR CORPORATION
To: NCR VOYIX CORPORATION
Reel/Frame 065820/0704 →
SECURITY INTEREST Recorded Oct 25, 2023
From: NCR VOYIX CORPORATION
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 065346/0168 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 9, 2019
From: STOPLIFT, INC
To: NCR CORPORATION
Reel/Frame 050016/0030 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 15, 2019
From: KUNDU, MALAY; MIGDAL, JOSHUA
To: STOPLIFT, INC.
Reel/Frame 048880/0625 →
Continuity (4)
Continuation 13886643 · May 3, 2013
Provisional Application 61642296 · May 3, 2012
Provisional Application 61642740 · May 4, 2012
Related Publication 20180165733A1 · Jun 14, 2018