Category: Industry 4.0

Published on

Context Graph Explorer with the latest W3C Standard RDF 1.2 – Application, Visualization, and Prototype

With the new W3C standard RDF 1.2, knowledge graphs can be effectively extended to include time, provenance, and confidence statements, forming a (temporal) Context Graph. This article outlines the fundamentals, several use cases, and the features of the prototype. The prototype provides visualization, import and export functionalities, as well as querying and validation capabilities using a SPARQL 1.2 engine and a SHACL validator.

A traditional Knowledge Graph answers the question "what is related to what?", represented as a directed graph consisting of nodes and edges. A Context Graph complements these statements with additional dimensions related to the context of the node, such as:

  • valid-time — when was the statement valid in the real world?
  • transaction-time — when was it recorded, confirmed, or revised?
  • provenance and confidence — where does it come from and how reliable is this statement?

With the W3C standard RDF 1.2, this can be expressed very effectively using annotation block syntax – indicated by curly braces and pipe symbols – shown here for a giant sequoia in an alluvial forest, measured on September 1, 2015, at a height of 57.1 m.

wst:tree-auenwald  ws:heightMeters "57.1"^^xsd:decimal  {|
    ws:validFrom    "2015-09-01"^^xsd:date ;
    ws:source       wsb:post-hoechster-mammutbaum-deutschlands ;
    ws:certainty    "bestaetigt" ;
    ws:confidence   "1.0"^^xsd:decimal ;
    ws:recordedAt   "2015-10-01T12:00:00Z"^^xsd:dateTime
|} .

This extension of the knowledge graph offers significant added value, for instance, in connection with the product development process, the Digital Product Passport (DPP), or in the management of historical or regulated data. Data changes at specific points in time, sources shift, and new or updated regulations come into force – the context graph allows this to be fully documented and later utilized through queries and validations.

For the prototype, context graphs were generated from two different sources.

  • Wilhelma-Saat — Publications on a nature project documenting the historical giant sequoias of the "Wilhelma-Saat" established by King Wilhelm I of Württemberg (dating back to 1864). The context graph contains 897 triples with 65 annotations and covers the time span from 1781 to 2026. ( https://www.wilhelma-saat.de )
  • KMAIC Blog — The blog of the KMAIC website, with each post timestamped for initial publication and modification. The context graph contains 780 triples with 72 annotations. ( https://www.km-sc.de )

The prototype can ingest context graphs in RDF format and visualize them as a graph or timeline. Details can be queried using the built-in SPARQL engine, and they can also be validated using the integrated SHACL engine.

Outlook

A context graph represents the logical evolution of the knowledge graph. Its value becomes apparent where static statements without additional dimensions are insufficient. Additional applications and use cases are also beneficial in the following areas:

  • Regulatory compliance (DPP, ESPR, Battery Regulation 2023/1542) requires traceable data origin and up-to-date status — both of which can be modeled directly as annotations, queried via SPARQL, and validated using SHACL.
  • Product management, digital twins, and product carbon footprints require tracking when product properties change over time (maintenance status, recycled content, CO₂ footprint, etc.).
  • Modern AI-based knowledge management systems benefit from provenance and confidence annotations when GraphRAG-generated statements coexist with validated statements from a domain expert — the context graph can indicate which source provided which statement at what time and how trustworthy it is.
Published on

Comprehensive (1080°) consulting for enterprises

I am offering another comprehensive (1080°) consulting service for businesses, titled "From Digital Obligation to True Competitive Advantage", in collaboration with two highly experienced partners.

360° Economic Viability & 360° Transformation & 360° Knowledge & Leadership

You can find details about this special offer in the flyer . Please feel free to contact us if you are interested or have any questions about our services.

Published on

Industry 4.0 Orchestrator and Validator Prototype

The first beta version of the IPO prototype is now available. The aim of this prototype is to demonstrate the comprehensive application of industry standards in combination with semantic solutions and Artificial Intelligence. Another key focus during development was the inclusion and integration of validation functions. The main applications of this prototype include the Digital Product Passport, the calculation of the product's Product Carbon Footprint (PCF) in accordance with the ISO 14067 standard, and integration into the company's process landscape. An agile, incremental approach was used to develop the web application.

IPO Prototype – Visualized Knowledge Graph with detailed view and search function

The standards supported in the IPO prototype are BPMN 2.0, SysML v2, AAS (3.0) with submodels, RDF/Turtle, SPARQL, and SHACL. Import and export functions are available for SysML, BPMN 2.0, SysML v2, and AAS.

Published on

Digital Product Passport and Interoperability

The Digital Product Passport requires access to all relevant data as well as the "semantic interconnection" of this data within a company. Furthermore, connectivity with external data from suppliers and partners is also necessary. This interoperability—which also supports the exchange of Digital Twins—can be achieved through the use of the open standard of the Asset Administration Shell (IEC 63278-1). In addition, full interoperability requires seamless integration with existing business processes and models within the company, such as in Product Engineering / Model-Based Systems Engineering, as well as the orchestration of relationships at the data, model, and process levels. Model-based methods and descriptions (BPMN 2.0, SysML v2, AutoML, LLM, Predictive Maintenance) are already applied in many subareas of companies. The complete networking of these complex contexts and aspects can be realized using a semantic enterprise model based on World Wide Web Consortium (W3C) web standards, thereby contributing to further value creation within the company.

DPP.model.arena.11_2025Download

Note: I held this presentation in November 2025 at the tekom annual conference (Arena) in Stuttgart.

Published on

Use Case: Digital Product Passport

This presentation from Semantics 2023 explains the key points of the European Green Deal, related sustainable product initiatives and standards, and—as a use case—concepts for implementing the Digital Product Passport (DPP) based on the latest technologies and frameworks, such as the application of the Asset Administration Shell (AAS) in combination with an Enterprise Knowledge Graph (EKG).

Download presentation (PDF, 2.5 MB)

Published on

Application of LLM, RAG, and GraphRAG Technologies

In today's digital world, Large Language Models (LLMs) and related technologies play a central role in natural language processing and analysis. These models have the potential to fundamentally transform how companies process and utilize information. In this article, we explain the concepts of LLM, Retrieval-Augmented Generation (RAG), and GraphRAG, and how they can be applied in industry.

LLMs are powerful AI models trained to understand and generate human language. They are based on deep neural networks and trained on vast amounts of text data, enabling them to recognize complex patterns and relationships in language. LLMs are used in numerous areas, ranging from chatbots and virtual assistants to automated text analysis and generation.

Retrieval-Augmented Generation (RAG) combines the capabilities of LLMs with information retrieval systems. Instead of relying solely on the trained model, RAG accesses external data sources to provide more accurate and context-relevant information when generating answers. This method significantly improves the accuracy and relevance of generated content by incorporating up-to-date and specialized information into the process.

GraphRAG is an extension of the RAG principle that utilizes the structure of knowledge graphs to further optimize information retrieval and generation processes. Knowledge graphs represent data in a network-like structure that illustrates relationships between different pieces of information. By integrating knowledge graphs, GraphRAG can deliver deeper insights and well-founded answers by not only retrieving relevant data but also taking their interdependencies into account.

These AI technologies offer diverse application possibilities in industry. LLMs can be used to automate customer interactions or support decision-making processes. RAG and GraphRAG enable companies to utilize their data resources more efficiently and make well-founded, data-driven decisions. These technologies can provide significant competitive advantages, particularly in data-intensive sectors such as healthcare, finance, or logistics.

In summary, LLMs, RAG, and GraphRAG represent significant tools for the transformation of business processes. By integrating these technologies, companies can increase their efficiency, boost their innovative strength, and better adapt to market demands.

Published on

AI Standard ISO/IEC 42001:2023

Standards facilitate and ensure the successful, secure, and future-proof implementation of new and complex technologies in business. The ISO/IEC 42001:2023 standard serves as a guideline for introducing and operating AI applications from a (system) management perspective. It outlines the requirements for AI solutions and details the key aspects of successful implementation, operation, and continuous improvement processes for artificial intelligence solutions.

Published on

Digital Transformation and Cognitive Computing

Digital transformation refers to a comprehensive transformation process based on the application of new digital technologies and agile approaches that affects all areas and processes of a company or institution.

In connection with the application and integration of digital technologies, one also speaks of "cognitive computing," which is based on solutions from the fields of Knowledge Discovery, Text Mining, Natural Language Processing, and Machine Learning.

The ability to adapt to changing conditions and information, along with the systematic learning capability of all components, are the most crucial capabilities of cognitive computing, in addition to considering the context of the application.

Digital transformation (as well as any knowledge management transformation) must encompass all domains within a company or institution; transforming technology alone is not sufficient (e.g., organization, employees, processes, strategy – see „Core Elements of Digital Transformation“).