Unmanned Store Checkout With AI Recognition and Product Alignment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing product checkout process in stores is inefficient, leading to increased customer waiting times and operational costs due to manual barcode scanning, which causes congestion and requires additional manpower.

Innovation Solution

An unmanned store product checkout system utilizing artificial intelligence learning data, product alignment through rollers, and a combination of barcode and image scanners to enhance product recognition, along with a control unit to manage the transfer, alignment, and classification of products.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual barcode scanning is used for product checkout, then product identification can be performed, but customer waiting time increases and store congestion occurs

Engineering Contradiction:
Improveproduct identification accuracyVSAvoidcustomer waiting time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical barcode scanning with an automated optical scanning system. The scan unit automatically captures barcode images and product images without requiring manual intervention, thereby maintaining accurate product identification while eliminating the time-consuming manual scanning process that causes customer waiting

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

Solution Approach 2:

The system implements self-service checkout by automatically performing product identification, image recognition, and checkout processing without requiring store employees. The automated system handles the entire checkout process, reducing customer waiting time while maintaining accurate product identification through multi-modal recognition

Inventive Principle:
Principle #25Self-service

2Ease of operation

If manual product checkout is performed by employees, then products can be scanned and processed, but operational costs increase due to hiring additional staff

Engineering Contradiction:
Improveproduct checkout operationVSAvoidoperational cost
Core Design Contradiction:
Ease of operationVSLoss of energy

Solution Approach 1:

The patent implements a fully automated checkout system that performs product scanning, identification, and processing without human intervention. The system uses automatic product detection, barcode scanning, and image recognition to handle checkout operations, eliminating the need to hire additional employees while maintaining ease of operation

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces human employees with an automated system comprising scan units, processors, and control units. This substitution eliminates labor costs associated with hiring staff for product checkout while maintaining operational efficiency through automated product identification and processing

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

3Productivity

If product scanning is performed quickly, then customer waiting time decreases, but product recognition accuracy may be compromised

Engineering Contradiction:
Improvecheckout speedVSAvoidproduct recognition rate
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent divides the product recognition process into multiple independent stages: barcode scanning, image capture, AI-based image recognition, and verification. This segmentation allows each stage to operate at optimized speeds, with parallel processing of multiple products, thereby maintaining high checkout speed while ensuring accurate product recognition through multi-modal verification

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by capturing both barcode images and product images simultaneously as products pass through the scanning area. The AI model pre-processes and analyzes these images in parallel, preparing recognition results before final verification, thereby maintaining high recognition accuracy without slowing down the checkout process

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4700681A1Method and apparatus for product checkout in unmanned store
Publication Date: 2026.02.25 GAEASOFT
  • EP4700681A1 patent drawingFigure 1
  • EP4700681A1 patent drawingFigure 2
  • EP4700681A1 patent drawingFigure 3

AI summary

A method and an apparatus for product checkout in an unmanned store are disclosed. The apparatus for product checkout in an unmanned store according to an embodiment of the present invention may comprise: a transfer unit for transferring a product; a first product recognition unit for recognizing that the product has been placed on the transfer unit; a height sensor for measuring the height of the product; a weight sensor for measuring the weight of the product; a scan unit for scanning a barcode and an image of the product transferred by the transfer unit; a processor for identifying what the product is, by using artificial intelligence learning data; a product alignment unit for aligning the product to increase a recognition rate of the product; a second product recognition unit for recognizing that the product has arrived at a third point; a product classification unit for classifying the product; and a control unit for controlling operations of the transfer unit, the product alignment unit, and the product classification unit.