Lecture 2 - Industry 4.0 & Knowledge graphs Flashcards
Industry 4.0
4th Industrial revolution: IoT, Cyber Physical Systems, networks
Industry 4.0 key technologies: (5)
- Cyber-physical systems
- Cloud computing
- Internet of Things
- 3D printing
- Big Data, Analytics
Electronic Data Interchange (EDI):
Enable electronic communication between companies in the supply chain based on standards.
Mirror world basic concept (Dai & Vasarhelyi, 2017)
Connection with the real (physical) and virtual (mirror) world.
Items in PW keeps corresponding items in MW to keep real-time information of it.
Industry 3.0 vs 4.0 (5)
- Manufacturing process vs whole product lifetime (also maintenance)
- plan vs act
- lean manufacturing vs smart manufacturing
- decide by experience vs decide by information
- save money vs create new revenue streams
The different layers of the Knowledge graphs (5):
- Application layer
- Data analytic layer
- Cyber layer
- Edge layer
- Device layer
Value drivers of the industry 4.0 are (8)
- Time to market
- Service / aftersales
- Resources
- Asset utilization
- Labor (productivity and smart working)
- Quality
- Personalization
- Supply / demand match
Linked Open Data: standardized data in a decentralized (ungoverned) context has several problems (7):
The problem:
- Data everywhere → but caped over many applications. So how do you combine it? Data must be available and ready to integrate it (so in the same format) that you can combine
- Relevant data is scattered over many files and applications
- Data from multiple sources needs to be used together
- Data needs to be re-used out of context
- Exchange across systems, departments, organizations
- No “integrated schema”
- No centralized data governance possible anymore when you cross organizational borders
Solution on LOD is Linked Data (now called Knowledge Graphs):
- URIs: Universal Identifiers for object identification
- RDF: HTML for Linked Data: data representation
- SPARQL: SQL for Linked Data: data retrieval
The Triples concept is?
All information can be broken down into simple “Subject-Predicate-Object” triples.
Thing - Attribute - Value:
- This course has name “BAET”
- This lecture has data “2020-12-07”
Thing - Relationship - Thing:
- This lecture location is room WZ 104
- This lecture teacher is Weigand
Contribution Knowledge Graphs to Conversational AI: (3)
- The contribution of KG is providing more data from heterogeneous sources, including personal data (personalization)
- KG data can also be used to generate queries that can be used to train the (ML-based) NL Interpreter
- KG data can be used to improve the Intention finder, by attaching domain specific intentions to objects.