Unit I

Knowledge Engineering: Definition – Historical overview and significance in AI. Knowledge representation: Semantic web and Ontologies. Semantic Web Technologies: vision and goals – layered architecture – Semantic web standards: URI, XML, RDF and RDFS.

Unit II

Ontology Engineering: Definition – OWL (Web Ontology Language) – OWL Constructs: Classes, Instances and Properties in OWL – Complex Classes – Property Restrictions. Query Language: SPARQL queries – Advanced SPARQL. GraphsOntology creation and management using Protégé.

Unit III

Knowledge graphs (KG): Definition – DIKW Pyramid – Linked Data and Knowledge Graphs – Anatomy – Construction of KG: Data modelling – Integrating data – Data extraction and transformation – Embedding techniques for knowledge graphs – Building – Querying. Implementation of KG using Neo4j.

Unit IV

Reasoning and Inference in Knowledge: Logical reasoning and inference – Types of reasoning: deductive, inductive, and abductive. Integrating KG and Machine Learning (ML) – KG feature source of ML. Case studies of knowledge graph applications.

Course Description

This course provides an in-depth exploration of knowledge engineering principles and the construction and use of knowledge graphs. It covers how knowledge graphs can be integrated with machine learning (ML) techniques to enhance data-driven insights and reasoning capabilities. The course combines theoretical knowledge with practical skills, enabling students to develop and deploy knowledge-based systems and explore the synergy between knowledge graphs and ML.

Course Objectives

Understand the fundamental concepts of knowledge engineering. Learn about different methods of knowledge representation, including ontologies.. Gain proficiency in constructing and utilizing knowledge graphs. Apply reasoning and inference techniques to extract and derive new knowledge. Explore the integration of knowledge graphs with machine learning models. Implement real-world applications of knowledge graphs with ML.

Course Outcomes

• CO1: Describe fundamental concepts of Knowledge engineering and its representation using semantic web technologies
• CO2: Use ontologies engineering to create and manage knowledge base
• CO3: Illustrate construction and querying of Knowledge Graph (KG)
• CO4: Describe process of KG reasoning and integration of KG with ML models for real world applications

CO-PO Mapping

1. Knowledge engineering and expert systems, Rastogi, P. N, Business Promotion Bureau, New Delhi, 1994.
2. Domain-Specific Knowledge Graph Construction, Mayank Kejriwal, Springer, 2019.
3. Knowledge Graphs -Methodology, Tools and Selected Use Cases, Dieter Fensel, Umutcan Simsek, Springer, 2019.
4. Paul Groth, Frank van Harmelen, Rinke Hoekstra. A Semantic Web Primer, Third Edition, MIT press; 2012.
5. Semantic Web concepts, technologies and applications, K K Breitman, M A Casanova, W Truszkowski, Springer, 2006.