
Deliverable D3.1 presents the fi rst release of tools and technologies developed for procedural knowledge elicitation within the PERKS project framework. As a demonstration deliverable, this document provides a summary of the implemented solutions and their deployment, rather than an extensive technical report.It contains releases for three solutions:• Solution 1: Tools for automatic collection of procedural knowledge graphs from textual data, focusing on zero-shot extraction methods and intermediate formats for enhanced knowledge representation.• Solution 2: Semi-automatic and manual knowledge collection tools designed for user-friendly interfaces that enable the input, editing, and validation of procedural knowledge while ensuring compatibility with existing ontologies.• Solution 3: Validation of knowledge graphs with human-in-the-loop methodologies, incorporating a multi-step process for ensuring accuracy and reliability of the captured procedures.Each solution leverages state-of-the-art technologies to address challenges such as domain-specific data complexity, integration with human-centric workflows, and the creation of interoperable systems.The deliverable highlights initial implementations, key features, and deployment strategies.The collaboration among the solutions establishes a coherent procedural knowledge ecosystem, facilitating automated and human-guided processes. The deliverable also outlines plans for future iterations, focusing on multimodal data processing, enhanced user interactions, and expanded deployment capabilities. Through these efforts, the PERKS project aims to signifi cantly advance procedural knowledge management in Industry 5.0, fostering a human-centric approach to industrial optimization.This report presents a summary and background of the software released with D3.1.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
