Conference Agenda
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 18th Apr 2026, 05:29:05pm CEST
|
Agenda Overview |
| Session | ||
D432: AI-DRIVEN KNOWLEDGE AND DECISION SUPPORT IN PRODUCT DEVELOPMENT
| ||
    | ||
Graph retrieval-augmented generation for enhancing LLM-based ML algorithm recommendation in product development University of Duisburg-Essen, Germany Recent advances in machine learning (ML) offer substantial potential for product development (PD), yet adoption remains limited. A crucial step is identifying suitable ML algorithms for a given PD problem, which requires translating domain-specific formulations into appropriate ML tasks. Prior work indicates that LLMs struggle with this step due to insufficient domain knowledge. Therefore, this study investigates whether a domain-specific GraphRAG approach improves model performance by enriching prompts with structured context from a PD knowledge graph. A data-driven approach to studying dominant designs through patent images 1Università di Pisa, Italy; 2Business Engineering for Data Science (B4DS) research group, Italy; 3Coesia, Italy Dominant designs establish de facto standards for all products within an industry, shaping both competition and innovation dynamics. Studying dominant designs enables firms to make informed decisions for new product development and to anticipate technological shifts. This paper presents a computer-based method that automatically extracts the spatial configuration of components from patent drawings to support the analysis of dominant designs and anomaly detection. A case study on eyeglasses validates the approach, demonstrating its potential for data-driven design innovation. AI-based scenario management for SMEs: the need for modular, explainable and reusable foresight pipelines 1Fraunhofer IEM, Germany; 2Paderborn University, Germany Small and medium-sized enterprises often lack the time, expertise, and tools for effective scenario management. This paper proposes a modular, AI-enabled scenario architecture integrating a guided wizard and expert environment on a shared knowledge backbone. The design aims to reduce effort and tool fragmentation while preserving human judgment, structural quality, explainability, and traceability. The proposed pattern outlines a provenance-aware foresight pipeline with human-in-the-loop capabilities that aims to transform one-off projects into reusable organizational knowledge. AI-supported variant management activities – insights from an industrial case study 1Institute for Engineering Design and Industrial Design, University of Stuttgart, Germany; 2PLEASE NOTE THAT THIS ORGANISATION MUST BE REMOVED IN ALL MATERIALS Variant management faces increasing complexity that challenges traditional rule-based configuration approaches. This contribution explores how AI can support the generation of configuration rules (1) by comparing two solution concepts – a deterministic Python-based and an LLM-based approach. Following a structured early-stage AI system development methodology, the research investigates (2) how AI can be methodically integrated into variant management and (3) how implementation factors differ between both approaches. The results reveal distinct trade-offs between transparency and efficiency. | ||
