Industrial Domain Models from Local Hidden Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data preparation for industrial systems is a repetitive, cost-intensive, time-consuming, and error-prone process that requires domain and data engineering expertise, often leading to delays and confidentiality issues when sharing industrial data with third parties.
Innovation Solution
A computer-implemented method using a distributed system with local and external applications, where Hidden Features are extracted locally and a Machine Learning Model determines a Domain Model for the industrial system without sharing confidential data, ensuring secure and efficient data transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If confidential industrial data is shared with third-party service providers for domain model creation, then domain models can be provided, but data confidentiality is compromised
Solution Approach 1:
The patent extracts only the essential features and patterns from industrial data that are necessary for domain model creation, while leaving out confidential information. This selective extraction allows third-party providers to create accurate domain models without accessing sensitive industrial data, thereby resolving the contradiction between model provision and data confidentiality.
Solution Approach 2:
The patent introduces an intermediary processing layer that transforms confidential industrial data into anonymized representations suitable for domain model creation. This intermediary step acts as a buffer between the original data and the third-party service provider, enabling model provision while maintaining data confidentiality through controlled information transformation.
2Manufacturing precision
If manual data preparation is performed by experts, then data modeling accuracy is improved, but time consumption and cost increase
Solution Approach 1:
The patent performs preliminary automated processing of industrial data to extract relevant features and patterns before domain model creation. This preliminary action prepares the data in advance, reducing the time and expert intervention needed during the actual domain model creation process while maintaining accuracy through systematic feature extraction.
Solution Approach 2:
The patent replaces manual expert-based data preparation with automated machine learning algorithms and computational methods. This substitution of mechanical human effort with automated systems maintains data modeling accuracy through consistent algorithmic processing while dramatically reducing time consumption and operational costs.
3Ease of manufacture
If repetitive ETL activities are performed manually, then data integration is achieved, but effort and error rates increase
Solution Approach 1:
The patent creates a universal automated ETL framework that handles multiple data integration tasks through standardized processes. This universal system performs extraction, transformation, and loading operations across different data sources and formats using consistent methodologies, thereby simplifying the overall process while reducing errors associated with custom manual scripting for each integration scenario.
Data Source
AI summary
Hidden Features are locally extracted from Industrial Data of the industrial system by a Local Application executed on a local computer of a customer. The Hidden Features are uploaded to an external computer of a service provider. A Domain Model for the industrial system is externally determined from an Industrial Model Library (IML) on the external computer based on the uploaded Hidden Features by an External Algorithm including at least one Machine Learning Model (MLM) executed on the external computer. The determined Domain Model for the industrial system is provided to the customer. The at least one MLM has been trained on ranking most appropriate Domain Models for industrial systems based on Hidden Features of the respective industrial systems. The most appropriate Domain Models represent all relevant technical aspects of the respective industrial systems.