Improving industrial data extraction using smart example-based learning
AAS-RAIL: Improving Information Extraction for Asset Administration Shells through Retrieval-Augmented In-Context Learning
Artificial Intelligence
Summary
Extracting technical information from industrial product documents is hard because different companies use their own special terms and formats. The authors created a method called AAS-RAIL that helps computers learn how to pull out this information by looking at similar examples from other products. This approach lets the computer adjust to different company styles without retraining it. Their tests showed this method works much better than traditional ways, improving accuracy by about 30 to 50 percent. This makes turning existing documents into standardized digital records faster and easier.
Asset Administration ShellInformation extractionIndustry 4.0Digital Product PassportLarge language modelsRetrieval-augmented learningIn-context learningFew-shot promptingSemantic retrievalStructured information extraction
Authors
Janek Groß, Jens Heidrich
Abstract
The Asset Administration Shell (AAS) is a cornerstone of Industry 4.0 and the Digital Product Passport, providing standardized digital representations of industrial assets. While manufacturers already maintain extensive technical product documentation, generating AAS instances from existing product datasheets remains a labor-intensive task because technical information is extracted from heterogeneous document structures and often involves company-specific terminology and conventions. In this work, we present AAS-RAIL, a retrieval-augmented information extraction (IE) approach that automatically generates Asset Administration Shells from PDF product datasheets using large language models (LLMs). Instead of relying on a fixed set of few-shot examples, the proposed retrieval-augmented in-context learning (RAIL) approach retrieves LLM-generated extraction helpers from similar Asset Administration Shells to provide instance-specific in-context learning (ICL). This enables the model to adapt its extraction behavior to company-specific naming conventions and formatting styles without fine-tuning. Our core contribution is the dynamic selection of company-specific AAS examples for each datasheet, replacing static prompting with an extraction pipeline that adapts to instances and combines semantic retrieval and structured information extraction. The proposed approach is evaluated on a collection of industrial product datasheets using a selection of open- and closed-weight LLMs. Experimental results show that RAIL consistently improves extraction quality over conventional few-shot prompting, yielding relative improvements of 30.4-52.4%. These results demonstrate that our approach provides an effective improvement for company-specific AAS generation.