Edge Service Model Matching for IoT Integration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The integration of technical devices into complex industrial systems is challenging due to the need for end-to-end integration of operational technologies and enterprise IT layers, requiring efficient service discovery and classification to reduce complexity and costs.

Innovation Solution

A method for controlling technical devices using an optimal model, involving configuration of device features by edge services, automatic classification, and abstraction to select the best application model for IoT service providers, leveraging AI or machine learning for efficient processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual integration of technical devices into industrial systems is performed, then integration accuracy and system reliability are improved, but integration time and complexity increase significantly

Engineering Contradiction:

Improveintegration reliabilityVSAvoidintegration time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automatic self-service through AI-based classification and matching algorithms that autonomously integrate technical devices into industrial systems without manual intervention. The classification service automatically categorizes device features, and the matching service autonomously selects appropriate integration patterns, eliminating the need for manual configuration while maintaining high integration reliability.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual integration processes are replaced by automated software-based systems utilizing machine learning algorithms. The AI classification and matching services substitute human experts' mechanical work with computational processes, dramatically reducing integration time while preserving reliability through algorithmic consistency and reproducibility.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If comprehensive device feature configuration is performed to ensure accurate model matching, then model selection accuracy is improved, but processing complexity and computational resources increase

Engineering Contradiction:

Improvemodel matching accuracyVSAvoidprocessing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The complex integration process is segmented into distinct modular services: device feature extraction, AI-based classification, pattern matching, and model selection. Each service handles a specific aspect of the integration process independently, reducing overall processing complexity while maintaining comprehensive feature analysis for accurate model matching.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

An AI classification service acts as an intermediary between raw device features and the pattern matching process. This intermediary layer abstracts and standardizes device features into classified categories, simplifying subsequent matching operations while preserving the necessary detail for accurate model selection.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If existing architectural knowledge is made explicit and transferred through automated services, then integration efficiency is improved, but system architecture complexity increases

Engineering Contradiction:

Improveintegration efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The edge services are designed with universal functionality to handle diverse device types and integration scenarios through standardized interfaces and processes. The AI classification and matching services can process various device features and match them with different industrial patterns, enabling efficient integration across multiple domains without requiring separate specialized systems for each case.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Facilitates the modeling of digitization platforms, transfers implicit architectural knowledge, and ensures efficient control of devices by selecting the optimal model based on quality attributes and feature fulfillment, reducing integration complexity and development time.

Implementation Method 1

The second edge service carries out the abstraction of the device model using a method for the automatic classification of features, which is based in particular on the principle of artificial intelligence or machine learning.

Methodology Applied

Scientific EffectArtificial intelligence:

Implementation Method 2

Methodology Applied

Scientific EffectMachine learning:

Data Source

PatentEP3716578B1Method and device for controlling a technical device with optimal model

Publication Date: 2023.09.06 SIEMENS AG

Figure 1~2

AI summary

Method for controlling a technical device (101) with an optimal model, comprising the following steps: a) configuring (100) a device feature of the technical device, b) generating (110) an abstract feature, c) generating (120) and configuring an initial relationship between the first edge service and the second edge service, determined by means of an automatic feature classification, d) providing (130) a respective application feature in the form of an application model from at least one IoT service provider using a selection parameter based on the abstract model, e) comparing (140) the abstract model with the application model and selecting the model with the greatest match as the optimal model, f) controlling the technical device (150) with the optimal model.