Fraud Behavior Recognition Device Using Video and POS Screen Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Self-service POS terminals lack effective fraud detection mechanisms, leading to increased risk of fraudulent activities such as theft or improper registration of merchandise due to reduced oversight and interaction with store employees.

Innovation Solution

A fraud behavior recognition device that uses cameras and processor units to analyze customer behavior and operations at self-service POS terminals, recognizing fraudulent actions through image and screen data analysis, and notifying attendants of suspicious activities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If self-service POS terminals are introduced to reduce labor costs and prevent disease transmission, then operational efficiency and hygiene are improved, but fraud detection capability deteriorates due to reduced employee oversight

Engineering Contradiction:
Improveoperational efficiencyVSAvoidfraud detection capability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent replaces manual employee oversight with an automated video analysis system using cameras and AI processing. The system automatically detects customer behaviors, compares them against operation data, and identifies fraudulent activities without requiring human intervention, thus maintaining productivity while restoring fraud detection capability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces video images as an intermediary between the customer and the fraud detection system. Cameras capture customer behaviors, which are then processed by the processor to detect anomalies. This intermediary enables automated monitoring without direct employee involvement, resolving the contradiction between self-service efficiency and fraud detection

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If self-service POS terminals operate without employee interaction, then service speed and hygiene are improved, but the ability to detect and suppress fraudulent activities deteriorates

Engineering Contradiction:
Improveservice speedVSAvoidfraudulent activities
Core Design Contradiction:
SpeedVSObject-affected harmful factors

Solution Approach 1:

The patent performs preliminary detection of fraudulent behaviors by continuously analyzing video feeds and comparing customer actions against expected operation sequences. The system identifies anomalies before they result in actual fraud losses, enabling preventive intervention while maintaining self-service speed

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where detected fraudulent behaviors trigger notifications to store employees. The system continuously monitors customer actions, provides real-time feedback when anomalies are detected, and enables rapid response to prevent fraud, thus maintaining service speed while countering harmful activities

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4029412A1Fraud behavior recognition device, control program thereof, and fraud behavior recognition method
Publication Date: 2022.07.20 TOSHIBA TEC KK
  • EP4029412A1 patent drawingFigure 1
  • EP4029412A1 patent drawingFigure 2
  • EP4029412A1 patent drawingFigure 3

AI summary

A detection device for detecting a fraud behavior of a customer at a point-of-sale (POS) terminal in a store, including a first interface circuit configured to receive a first image of the customer from a camera, a second interface circuit configured to receive a second image that is displayed on the POS terminal, and a processor configured to acquire one or more first images via the first interface circuit and determine one or more behaviors of the customer based on the acquired first images, acquire one or more second images via the second interface circuit and determine, based on the acquired second images, one or more operations that have been made by the customer on the POS terminal, and determine that one of the behaviors is fraudulent based on one or more of the operations that have been made by the customer before said one of the behaviors. (FIG. 1)