Today manufacturing ecosystems deal with increasing quantities of unstructured and semi-structured information in webpages, e-mails, text documents, spreadsheets, news articles, collaborative posts, patents to name but a few, there is a real need to extract this information, to represent it in a meaningful, structured way, to cluster and transform it in multiple formats in order to support interoperability. The FITMAN Specific Enabler for Generation and Transformation of Virtualized Assets (FITMAN GeToVa SE) is aiming at providing a state-of-the-art Information Extraction-driven semantic tool for (semi-)automatic Virtualized intangible Assets in order to heavily reduce manual data entry for the population of the FITMAN-CAM Specific Enabler.
The central part of the GeToVa SE is the Extraction component, which allows the semi-automatic extraction of Ontology based Virtualized Assets from semi-structured data. This is achieved by using the Knowledge Engineering tool GATE. Further a collaborative Tagging system is used for extraction and searching of Virtualized Assets. Extractions of certain Assets can be reused for Assets of similar structure by using this Tagging system. This allows fast automation of Asset extraction.
The tagged and annotated data can be used to search and cluster Virtualized Assets. Alternatively full-text search and fuzzy search is available as well.
The Virtualized Assets can then be transformed between different Ontologies and formats. Most notable the Europass format, Linked-UDSL and JSON-LD, as well as Ontologies developed for different use-cases.
Accessing the FITMAN GeToVa SE is possible by using a rich REST-ful API or a Web-Dashboard. The Web-Dashboard is integrated into the SE as well.
The GeToVa SE provides the following core functionalities:
- Tagging and annotation of semi-structured data to build a vocabulary for extraction
Clustering of assets based on TFID
- Searching of assets using tags, annotations, full-text search and fuzzy search
- Extraction of Virtualized Assets information from real-world semi-structured data and network resources
- Generation of semantic representation of Virtualized intangible Assets according to ontological models
- Multi-format ontology transformation between various formats, mapping and exchanging Future Internet (FI) data e.g. USDL.
- A rich Web-API
A high-level overview of the architecture of the FITMAN GeToVa SE is shown in the following picture: