US 11,989,712 B2
Methods and apparatus for anomaly detection in self-checkout retail environments
David Ciprian Petru, Blackpool (IE); Dan Alexandru Pescaru, Blackpool (IE); Vasile Gui, Blackpool (IE); Cosmin Cernazanu-Glavan, Blackpool (IE); Andrei Pricochi, Blackpool (IE); Ovidiu Parvu, Blackpool (IE); Bogdan Ciubotaru, Blackpool (IE); and Gavin Doyle, Clashanure (IE)
Assigned to EVERSEEN LIMITED, Blackpool (IE)
Appl. No. 17/424,838
Filed by EVERSEEN LIMITED, Blackpool (IE)
PCT Filed Jan. 21, 2020, PCT No. PCT/EP2020/051433
§ 371(c)(1), (2) Date Jul. 21, 2021,
PCT Pub. No. WO2020/152181, PCT Pub. Date Jul. 30, 2020.
Claims priority of application No. 19153108 (EP), filed on Jan. 22, 2019.
Prior Publication US 2022/0122429 A1, Apr. 21, 2022
Int. Cl. G06Q 20/20 (2012.01); A47F 9/04 (2006.01); G06F 17/10 (2006.01); G06Q 20/18 (2012.01); G06Q 20/40 (2012.01); G06V 10/764 (2022.01); G06V 20/52 (2022.01); G07G 1/00 (2006.01)
CPC G06Q 20/20 (2013.01) [A47F 9/047 (2013.01); G06F 17/10 (2013.01); G06Q 20/18 (2013.01); G06Q 20/4016 (2013.01); G06V 10/764 (2022.01); G06V 20/52 (2022.01); G07G 1/0009 (2013.01); G06F 2218/08 (2023.01); G06F 2218/12 (2023.01)] 15 Claims
OG exemplary drawing
 
1. A system for anomaly detection in a self-checkout environment, comprising:
a processing unit configured for:
extracting a set of features from transaction data received from a self-checkout terminal;
characterising an activity based on the set of features;
defining a plurality of active intervals for each characterised activity;
determining a meta-feature vector for each defined active interval of the plurality of active intervals;
comparing each meta-feature vector with a predefined set of vectors;
detecting an anomaly based on the comparison; and
issuing an alert based on detecting the anomaly.