Fitness Testing of Value Documents Using Uncertainty Range

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for checking the fitness of documents, such as banknotes, face challenges in setting suitable threshold values for sensors due to aging or soiling, leading to misclassification of documents as fit or unfit, and require complex management of multiple threshold values for accurate sorting.

Innovation Solution

The method selects at least two fitness criteria for documents, determines a fitness measurement value for each, and uses an unfit function with threshold values and an uncertainty range to assign a degree of unfitness, combining these into an unfit probability for intuitive classification, allowing for easier adjustment of the fitness test severity without changing individual threshold values.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If rigidly predefined threshold values are used for sensor-based fitness checking, then the device complexity is reduced and ease of operation is improved, but measurement precision deteriorates due to aging or soiling of the device and changes in documents over time

Engineering Contradiction:
Improveease of setting threshold valuesVSAvoidaccuracy of fitness classification
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent transforms fixed threshold values into dynamic threshold values that automatically adapt to changes in the measuring device and documents over time. The system determines current threshold values based on reference measurements taken at different points in time, allowing the thresholds to evolve with aging and soiling without requiring manual reconfiguration, thus maintaining both ease of operation and measurement precision

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements a feedback mechanism where reference measurements are continuously taken and used to update the threshold values. This closed-loop approach ensures that the threshold values remain accurate despite changes in the device condition or document characteristics, resolving the contradiction between fixed simplicity and adaptive precision

Inventive Principle:
Principle #23Feedback

2Measurement precision

If multiple fitness criteria with individual threshold values are used, then measurement precision is improved for comprehensive fitness assessment, but device complexity increases due to the large number of parameters to manage

Engineering Contradiction:
Improveaccuracy of fitness classificationVSAvoidnumber of threshold values to manage
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple individual threshold values into a single aggregate threshold value. The system evaluates multiple fitness criteria (such as soiling, damage, and wear) and integrates their results to produce an overall fitness determination based on one threshold, significantly reducing the number of parameters the user must manage while maintaining comprehensive assessment accuracy

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The single aggregate threshold value serves multiple functions by evaluating all fitness criteria simultaneously. This universal threshold replaces numerous individual thresholds, allowing the system to maintain high measurement precision across multiple dimensions while simplifying the user interface and reducing operational complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3170154B1Method and device for fitness testing of value documents
Publication Date: 2021.11.24 GIESECKE & DEVRIENT CURRENCY TECHNOLOGY GMBH
  • EP3170154B1 patent drawingFigure 1a~4
  • EP3170154B1 patent drawingFigure 2a~2c
  • EP3170154B1 patent drawingFigure 3a~3b

AI summary

The invention relates to the fitness testing of value documents. An unfit degree of each value document is determined by means of an unfit function for each of at least two fitness criteria. The unfit function unambiguously assigns each fitness value an unfit degree and comprises two threshold values, beyond which the unfit degree with respect to the relevant fitness criterion is 0 or 1. Between the threshold values there is an uncertainty region, in which the unfit degree lies between 0 and 1 with respect to the relevant fitness criterion and the unfit function runs in a monotonically decreasing or monotonically increasing manner. The unfit degrees of different fitness criteria are subsequently combined to an unfit likelihood of each of the value documents and a fitness classification of each of the value documents is performed on the basis of the unfit likelihood.