Knowledge Engineering and Business Intelligence

Welcome to the lecture in Knowledge Engineering!

We are happy that you plan to participate in our amazing module. However, we would be happy to know who you are. Therefore, please fill the following google with your name, matriculation number and Unicam e-mail. That would allow us to inform you if something is changed (e.g. lecture needs to be postponed, other conference tool etc) and to register your grade in the system.

https://forms.gle/33PZNW31dNc3qHay6

We also have an schedule which you can find here.

Best regards, Holger & Knut

Teacher:

• Prof. Knut Hinkelmann
• Prof. Holger Wache

ESSE3 Link

• Knowledge Engineering and Business Intelligence - AY 2022/23

Scheduling of Lectures:

• We teach block-wise, i.e. not every week. Please refer to our schedule

Degrees:

• MSc in Computer Science (LM-18)

Supporting Knowledge-Intensive Processes

Knowledge-intensive processes are more unstructured processes with a lot of involvements of users with their experience. Supporting such processes at their levels requires modelling and enacting several different forms of knowledge. In general more explicit represented knowledge allows better support. But different forms of knowledge need different intuitive and adequate representations and inferences.

There are several moethods to formally represent knowledge. Graphical models can be an intuitive means to add knowledge into knowledge-based systems. Instead of manually creating knowledge bases, knowledge can also be learned from data. We distinguish between symbolic learning (learning decision trees andss case-based reasoning) and sub-symbolic learning (neural networks)

After completion of this module, the participants will be able to assess which kind of knowledge representation and reasoning is adequate and are able to develop appropriate knowledge-based systems. They can value the advantages of knowledge-based systems with respect to their costs and apply several methods to create knowledge bases.

• Introduction: Knowledge in processes
• Decision Tables
• Rules
  • Textual represented rule (i.e. Horn clauses)
  • Forward and backward chaining
  • Data-driven and Goal-oriented
  • Negation-as-failure
• Fuzzy Logic
• Knowledge Graphs
  • RDFS
  • Ontology Engineering
• Graphical Models
  • Modelling and Meta-modeling
  • Ontology-based meta-modeling
• Machine Learning
  • Learning Decision Trees

Course Material

• Organisation

• Lecture “Introduction”
  • Slides: Introduction
  • Davenport, T. H. (2010). Process Management for Knowledge Work. In J. vom Brocke & M. Rosemann (Eds.), Handbook on Business Process Management 1 (pp. 17–36). Berlin, Heidelberg: Springer.
  • Exercise/Homework: Types of Knowledge

• Lecture “Knowledge in Processes”
  • Slides: Decision-Aware Business Processes
  • Slides: Example: Admission as a Decision-aware Business Process -
• Lecture “Decision Tables”
  • Slides: Decision Tables - DMN
  • Reading: Introduction into DMN
  • Exercise and Solution: Reduction of Decision Tables, Sample Table
  • Exercise and Solution: DMN for Booking Price
    • Example: Price Calculation for Room Booking
  • Homework: Decision Modeling for Admission
  • Tools:
    • Download: Camunda Workflow and Decision Modeler
    • Online: Camunda Decision Simulator
• Lecture “Rule-based Systems”
  • Slides: Rule-based Systems
  • Reasoning examples: simple and ancestor
  • Exercise: University and Solution
  • Exercise: Family and Solution
  • Exercise: Further small examples and Solution
  • Exercise: Mini Sudoku and Solution
  • Exercise: Friendship and Solution
  • Additional Exercise (not discussed in class): Fraud Detection
  • Home Work with Solution
  • Nice browser-based Prolog Engine

• Lecture “Forward- and Backward Chaining”
  • Slides: Forward- and Backward Chaining

• Lecture “Fuzzy logic”
  • Slides: Fuzzy Logic
  • Exercise: Fuzzy Sets and Solution
  • Exercise: Fuzzy Set Operations and Solution
  • Exercise: Credit Analysis and pictures
  • Jamboard as PDF

• Lecture “Knowledge Nets and RDF”
  • Slides: Knowledge Nets and RDF
  • Exercise: RDF Graphs and Solution
  • Exercise: RDF Schema and Solution
  • Exercise: RDF Schema Inferences and Solution

• Lecture “Ontology Engineering”
  • Slides: Ontology Engineering
    • Sample Ontology about Courses and Lecturers
  • Literature: Noy, N. F., & McGuinness, D. L. (2001). Ontology development 101: A guide to creating your first ontology. Stanford Knowledge Systems Laboratory Technical Report KSL-01-05.
  • Download: Protege: Desktop Version (Platform independent or Windows)

• Lecture “Conceptual Modelling”
  • Slides: Conceptual Modelling
    • Icons
  • Download: ADOxx Model Engineering Environment

• Lecture “Ontology-based Modelling”
  • Slides: Ontology-based Modelling
  • Literature: Hinkelmann et al. (2016). A new paradigm for the continuous alignment of business and IT: Combining enterprise architecture modelling and enterprise ontologies
  • Literature: Hinkelmann et al. (2018). Ontology-based Metamodelling.
  • Walkthrough on ontology-based modelling in AOAME
    • Menue ontology
  • AOAME
    • Data/Ontologies: https://aoame-fuseki.herokuapp.com/dataset.html
    • Modeling Environment: https://aoame.herokuapp.com/modeller

• Lecture “Machine Learning”
  • Slides: Introduction to Machine Learning
  • Slides: Symbolic Machine Learning: Learning Decision Trees
  • Reading Material: Decision Tree Learning
  • Exercise: Auto Traders
  • Exercise: Health Insurance: Learning Risk Assessment
  • Tool: WEKA Learning Environment
    • Download WEKA
  • Data Sets: playing tennis, creditworthyness (CSV Files), car sales and Health Insurance (ARFF and Excel file)

• Lecture “Combining Machine Learning and Knowledge Engineering”
  • Slides: Combining Machine Learning and Knowledge Engineering
  • Assignment with Solution: Health Insurance: Combining Learning with Knowledge Engineering

Recordings of the lectures are password protected (passwords on request from the lecturers)

• 6th of March 2023: Introduction: What is knowledge
• 8th of March 2023: Knowledge in Processes, Decision Modeling, Decision Trees
• 20th of March 2023: Rule-Based Systems (Modelling)
• 21st of March 2023: Rule-Based Systems (Reasoning)
• 27th of March 2023: Fuzzy Logic
• 28th of March 2023: Fuzzy Controller
• 17th of April 2023: Knowledge Nets and RDF
• 18th of April 2023: Ontology Engineering
• 16th of May 2023: Conceptual Modelling
• 24th of May 2023: Ontology-based Modelling
• 30th of May 2023: Machine Learning: Learning Decision Trees; Combining Machine Learning and Knowledge Engineering

This module is examined by a project.

The current version of the project description is V2 (06.09.2023). Please send your project to holgererik.wache@unicam.it. Deadline for submitting the project is Sunday, 08.10.2023, 18:00.