AI Standardization of Device Property Entries for ML-Ready Documentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current documentation methods for device properties lack standardization, leading to inconsistencies in format, language, and syntax, which hinder the effective use of data for machine learning models and limit their applicability across different manufacturers and generations.

Innovation Solution

A method using artificial intelligence, specifically a large language model, to adapt text-based property entries into a standardized format, enabling uniform documentation and facilitating the use of data across diverse devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If text-based property entries are documented in free text format with different documentation methods from different manufacturers and users, then flexibility and ease of documentation are improved, but data consistency and usability for machine learning models deteriorate

Engineering Contradiction:
Improveease of documentationVSAvoiddata consistency
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent introduces an intermediary component (AI-based natural language processing system) that translates free text documentation from different manufacturers and users into a standardized format. This mediator preserves the flexibility of free text input while ensuring data consistency by converting various documentation styles into a uniform structure that machine learning models can process effectively.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms the parameters of documentation by converting unstructured free text into structured data with defined parameters and categories. This parameter transformation maintains the ease of documentation (users still write in natural language) while improving data consistency through standardized output parameters that can be directly used by machine learning models.

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If manual data cleaning and harmonization is performed to standardize documentation data, then data consistency for machine learning training is improved, but time consumption and processing effort increase

Engineering Contradiction:
Improvedata consistencyVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent replaces the mechanical process of manual data cleaning and harmonization with an automated AI-based natural language processing system. This substitution eliminates the need for manual intervention while achieving the same goal of data standardization, thereby maintaining data consistency for machine learning training without incurring the time loss associated with manual processing.

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

Solution Approach 2:

The system enables self-service standardization where the documentation data automatically undergoes cleaning and harmonization through AI processing without requiring manual intervention. The system serves itself by transforming raw documentation into standardized format autonomously, eliminating the time-consuming manual data preparation process while ensuring consistency.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If automatic logging systems use different log messages from different manufacturers and component generations, then vendor independence and adaptability are improved, but model applicability and data uniformity deteriorate

Engineering Contradiction:
Improvevendor independenceVSAvoiddata uniformity
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent implements a universal natural language processing framework that can handle log messages from different manufacturers and component generations uniformly. This universal system maintains vendor independence by accepting diverse input formats while producing standardized output that ensures data uniformity, allowing machine learning models to process data from multiple sources without sacrificing adaptability.

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

Data Source

PatentEP4654106A1Method for documenting at least one property of at least one device by means of an electronic computing device, computer program product, computer-readable storage medium and electronic computing device
Publication Date: 2025.11.26 SIEMENS AG
  • EP4654106A1 patent drawing
  • EP4654106A1 patent drawing
  • EP4654106A1 patent drawing

AI summary

The invention relates to a method for documenting at least one property (12, 14) of at least one device (16, 18) using an electronic computing device (10), comprising the steps of: receiving at least one text-based property entry (20, 22) of the device (16, 18) using the electronic computing device (10); adapting the text-based property entry (20, 22) into a standardized format (24) using artificial intelligence (26) of the electronic computing device (10); and storing and documenting the text-based property entry (20, 22) in the standardized format (24) using the electronic computing device (10). The invention further relates to the computer program product, a computer-readable storage medium, and an electronic computing device (10).