Virtual Test System Port Mapping Using ML Confidence Scores

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for configuring virtual test systems for vehicle functions are labor-intensive and resource-consuming, particularly when integrating control units into simulation systems, often prone to errors due to manual port naming and configuration processes.

Innovation Solution

A computer-implemented procedure using machine learning algorithms to determine confidence values for port connections, automating the integration process by creating lists of high-confidence port assignments and allowing user validation, thereby reducing manual effort and processing time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual configuration via graphical user interface or automation using port names is used, then the virtual test system can be configured, but significant time expenditure and user effort are required

Engineering Contradiction:
Improveease of configurationVSAvoidtime expenditure
Core Design Contradiction:
Ease of manufactureVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical configuration operations (drag & drop in GUI) and simple text-based automation with a machine learning-based automated system. The ML algorithm analyzes port metadata, names, and communication patterns to automatically determine correct port connections, substituting human cognitive effort with algorithmic processing.

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

Solution Approach 2:

The configuration system performs self-service by automatically analyzing port characteristics and determining connections without requiring manual intervention. The ML algorithm independently processes port data, generates connection recommendations, and can automatically configure connections based on confidence thresholds, making the system self-configuring rather than requiring external human operation.

Inventive Principle:
Principle #25Self-service

2Productivity

If automation based on port names is used, then configuration effort is reduced, but errors occur due to slightly different naming conventions

Engineering Contradiction:
Improveconfiguration speedVSAvoidconfiguration accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent transforms the configuration approach from relying on exact port name matching to analyzing multiple parameters including port metadata, communication patterns, data types, and semantic meanings. The ML algorithm evaluates these multiple parameters to determine connections, changing the basis of automation from simple string matching to multi-dimensional parameter analysis, thereby improving both speed and accuracy.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements feedback mechanisms where the ML algorithm generates confidence scores for each recommended connection. Users can review these confidence levels and provide corrections, which are then fed back to retrain and improve the algorithm. This feedback loop continuously enhances configuration accuracy while maintaining automated speed.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If the number of simulated artifacts is increased, then more vehicle functions can be tested, but the effort for configuring the simulation system constantly increases

Engineering Contradiction:
Improvetesting capabilityVSAvoidsystem configuration complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the configuration task into independent port-level operations rather than requiring holistic system configuration. The ML algorithm processes individual port connections independently, analyzing each port's characteristics and determining connections on a case-by-case basis. This segmentation allows the system to scale to larger numbers of artifacts without proportionally increasing overall configuration complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-analyzing port metadata, communication patterns, and artifact interfaces before actual configuration is needed. The ML algorithm is trained on historical configuration data and port characteristics in advance, so that when new artifacts are added to the simulation system, the configuration process is already optimized and requires minimal additional effort regardless of system size.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4307121B1Computer-implemented method for configuring a virtual test system and training method
Publication Date: 2025.01.29 DSPACE DIGITAL SIGNAL PROCESSING & CONTROL ENGINEERING GMBH
  • EP4307121B1 patent drawingFigure 1
  • EP4307121B1 patent drawingFigure 2~3

AI summary

The invention relates to a computer-implemented method for configuring a virtual test system for testing vehicle functions of a motor vehicle, wherein for each of the plurality of input ports (10) of the artifact (12) to be tested, an assignment (S3a) of the output port (14) having the highest confidence value (K) of the at least one further artifact (16) to be tested is carried out depending on a first condition (B1), a list of output ports (14) having the highest confidence values ​​(K) is created depending on a second condition (B2), or an output port (14) is not assigned (S3c) depending on a third condition (B3) to configure a connection of the input ports (10) of the artifact (12) to be tested to suitable output ports (14) of the at least one further artifact (16) to be tested is carried out.The invention further relates to a computer-implemented method for providing a trained machine learning algorithm (A1) for configuring a virtual test system for testing vehicle functions of a motor vehicle.