Optimizing the Supply Chain with Knowledge Graphs, IoT and Digital Twins_Moore.pdf

© 2022 Neo4j, Inc. All rights reserved.
1
C H I C A G O

2
Optimizing the
Supply Chain
with Knowledge
Graphs, IoT and
Digital Twins

Michael Moore, Ph.D.
Principal, Partner Solutions & Technology
Neo4j

Agenda
• Supply Chain Challenges
• Digital Twins
• IOT
• Knowledge Graphs

5
Supply Chain Problems Are Data Problems
75%
938
of Fortune 1000 had a T1-2 supplier
impacted by the pandemic
Good forecasts are just
less bad forecasts
of executives aren’t confident in
their data quality

Consider: What Drives Your Business?
It’s not the numbers, it’s the relationships behind them
Plants
Warehouses
Suppliers
Distributors
Competitors
Partners
Regulations
Employees
Citizens
Customers
Products
Parts
Services
Regions

This is a Graph

Neo4j, Inc. All rights reserved 2021
“By 2025, graph technologies will be
used in 80% of data and analytics
innovations...”
Top 10 Trends in Data and Analytics, 11 May 2020, Rita Sallam et al.

9
Graphs have low complexity and high fidelity
SQL RDBMS ER Diagram Graph (“Whiteboard”)

Depict the business
as a graph
Squash the graph
into tables
Jam in foreign keys
to relate the records,
populate global index
10
Cheap Memory makes Graphs Compelling
https://jcmit.net/memoryprice.htm
SQL RDBMS workarounds to conserve memory
1979: Oracle v2.0 Released (yes, 43 years ago!)
= hidden technical debt
per MB
per MB

11
Neo4j Graph Model Enables Performance at Scale

Demand Shaping Inventory Positioning Perfect Fulfillment Sustainability
Consider a omni
-channel, multi
-
echelon supply chain and demand
& supply risk to determine
optimized inventory levels
Combine distributed order
management with warehouse and
transportation optimization and
enable automation of processes
Reduce energy consumption across
operations, measure risks, measure
gas emissions, adopt a circular
economy and measure the social
impact of your supply chain
Understand customers and market
trends to dynamically adjust
segmentation, promotions and
generate highly accurate forecasts
Demand Shaping Inventory Positioning Perfect Fulfillment Sustainability
Supply Chain Complexity Issues

13
GHG Reporting Requirements
GHG
Reporting
Timelines
• March 21, 2022:
SEC released new
proposals for climate-
related risk
disclosures.
• February 2024:
First disclosures on
Scope 1 and 2 for
large organizations.
• February 2025:
Disclosures on Scope
3 emissions and
emissions intensity
required for large
organizations.

14
Neo4j Graph Data Platform
Data Sources
Native Graph Database
The foundation of the Neo4j platform; delivers enterprise-scale
and performance, security, and data integrity for transaction and
analytical workloads.
Graph Data Science and Analytics Tools
Explorative tools, rich algorithm library, and Integrated
supervised Machine Learning framework.
Development Tools & Frameworks
Tooling, APIs, query builder, multi-language support for
development, admin, modeling, and rapid prototyping needs.
Discovery & Visualization
Code-free querying, data modeling and exploration tools for data
scientists, developers, and analysts.
Graph Query Language Support
Cypher & openCypher; ongoing leadership and standards work
(GQL) to establish lingua franca for graphs.
Ecosystem & Integrations
Rich ecosystem of tech and integration partners. Ingestion tools
(JDBC, Kafka, Spark, BI Tools, etc.) for bulk and streaming needs.
Runs Anywhere
Deploy as-a-Service (AuraDS) or self-hosted within your cloud of
choice (AWS, GCP, Azure) via their marketplace, or on-premises.
Data Connectors
Transactions Analytics
Graph Database
Data Consolidation
Contextualization
Enterprise Ready
Data Science & MLOps
Graph Data Science
Neo4j
Bloom
Neo4j
Browser
BUSINESS
USERS
DEVELOPERS
DATA
SCIENTISTS
DATA
ANALYSTS
BI
Connectors
AutoML
Integrations
Language
interfaces
OLTP OLAP

15
Supply Chain
Digital Twins

Digital Twins are Graphs DT Asset
Nested BOM
(Canonical
Model)
DT Field
Instance
Sensor Data
DT Field
Instance(s)
Nested BOM
(As Built)
DT Asset
Documents &
Drawings
DT Field
Instance
Metadata
DT Field
Instance
Extended
Data

Digital Supply Chain Twins
Digital Supply Chain Twins—Conceptual Clarification, Use Cases and Benefits
Benno Gerlach, Simon Zarnitz, Benjamin Nitsche and Frank Straube
Logistics 2021, 5, 86. https://doi.org/10.3390/logistics5040086
Network Level
Site Level

Robust Graph Algorithms & ML methods
● Compute metrics about the topology and connectivity
● Build predictive models to enhance your graph
● Highly parallelized and scale to 10’s of billions of nodes
18
Neo4j Graph Data Science
Mutable In-Memory
Workspace
Computational Graph
Native Graph Store
Efficient & Flexible Analytics Workspace
● Automatically reshapes transactional graphs into
an in-memory analytics graph
● Optimized for global traversals and aggregation
● Create workflows and layer algorithms
● Store and manage predictive models in the
model catalog

19
65+ Graph Data Science Techniques in Neo4j
Pathfinding &
Search
• Shortest Path
• Single-Source Shortest Path
• All Pairs Shortest Path
• A* Shortest Path
• Yen’s K Shortest Path
• Minimum Weight Spanning Tree
• K-Spanning Tree (MST)
• Random Walk
• Breadth & Depth First Search
Centrality &
Importance
• Degree Centrality
• Closeness Centrality
• Harmonic Centrality
• Betweenness Centrality & Approx.
• PageRank
• Personalized PageRank
• ArticleRank
• Eigenvector Centrality
• Hyperlink Induced Topic Search (HITS)
• Influence Maximization (Greedy, CELF)
Community
Detection
• Triangle Count
• Local Clustering Coefficient
• Connected Components (Union Find)
• Strongly Connected Components
• Label Propagation
• Louvain Modularity
• K-1 Coloring
• Modularity Optimization
• Speaker Listener Label Propagation
Supervised
Machine Learning
• Node Classification
• Link Prediction
… and more!
Heuristic Link
Prediction
• Adamic Adar
• Common Neighbors
• Preferential Attachment
• Resource Allocations
• Same Community
• Total Neighbors
Similarity
• Node Similarity
• K-Nearest Neighbors (KNN)
• Jaccard Similarity
• Cosine Similarity
• Pearson Similarity
• Euclidean Distance
• Approximate Nearest Neighbors (ANN)
Graph
Embeddings
• Node2Vec
• FastRP
• FastRPExtended
• GraphSAGE
• Synthetic Graph Generation
• Scale Properties
• Collapse Paths
• One Hot Encoding
• Split Relationships
• Graph Export
• Pregel API (write your own algos)

Graph Algorithms in Supply Chains
Graph algorithms enable reasoning
about network structure
K-Shortest Paths to identify the best
alternative routes

21
Graph Algorithms in Supply Chain
alternative routes
Betweenness Centrality to find
critical bottlenecks or risk points
Degree Centrality to see distribution
centers with high use

Graph Algorithms in Supply Chain
alternative routes
Similarity to find providers that can
step in during a disruption
Betweenness Centrality to find
critical bottlenecks or risk points
Degree Centrality to see distribution
centers with high use

23
Demo

24
North American Rail
Network Digital Twin
North American Rail Network
Total 527K Miles of Track
NS: 41,756 Miles of Track
555K nodes, 1.2M relationships
1GB

25
Graph Data Science Pathfinding
:param generatedName => ('in-memory-graph-ssp');
:param graphConfig => ({
nodeProjection: 'Node',
relationshipProjection: {
relType: {
type: 'CONNECTS_MIO',
orientation: 'UNDIRECTED',
properties: {
MILES: {
property: 'MILES',
defaultValue: 1
}
}
}
}
});
CALL gds.graph.project($generatedName, $graphConfig.nodeProjection, $graphConfig.relationshipProjection, {});
CALL gds.shortestPath.dijkstra.stream($generatedName,
{relationshipWeightProperty: 'MILES', sourceNode: id(start), targetNode: id(end)})
What is the lowest cost path between two points?
“Cost” could be physical distance, fuel consumption,
trackage fees, carbon emissions, etc
Minimize this Cost

26
Supply Chain
IoT

27
Real World Fidelity
● Neo4j’s flexible graph data model
easily handles complex relationships
and addition of new data sources
● Provides holistic “360°” view of
assets, processes & related data
with full spatial support
● Quickly traverse the network to
understand dependencies, co-
location, performance, history
● Scales to billions of nodes and
relationships
Nodes:
Regions, Sites, Leases,
Well Pads, Well Heads, Tanks,
Compressors, Heaters Treaters,
Free Water Knockouts, Sensors
Relationships:
LOCATED_IN, LOCATED_ON,
CONNECTED_TO, MONITORED_BY

ENX IoT Platform https://enxchange.co/platform/iot

Neo4j Kakfa Connector
Sensors IoT Gateway TimeSeries DB Kafka Topic Kafka Neo4j Connect
https://www.confluent.io/partner/neo4j/
Grid
Controller
ENX - SOL Event Filter SOL Excursion Events Stream Events to Graph Graph Analytics

Esri ArcGIS Knowledgehttps://www.esri.com/en-us/arcgis/products/arcgis-knowledge

Example Neo4j IoT Digital Twin Architecture
Azure IoT Hub Raw
Stream
Sensor Alerts & Sampled Stream
Neo4j ODBC
Connector
ETL
Pipeline OLTP
Azure TS
Insights
Azure Blob
Store
PowerBI
Reports
Azure Cosmos
DB
Azure Data
Warehouse
Azure SQL
Azure Stream
Analytics
Notification
Services
Event Sources
Azure Device
Provisioning
Neo4j Digital
Twin Graph
Neo4j Bloom
Visualization
Neo4j Desktop IDE (neo4j.com/download)
Unstructured Data, JSON Documents, Structured Data
Raw
Stream
Hot Path
Warm Path
Neo4j Secure
BOLT Driver
Web Apps /
GraphQL API
Power BI Server
Enriching
data sources
Neo4j integrates a wide variety of data
sources (beyond BOM + Sensor Data) to add
additional analytical context to the graph.
● Vendors
● Costs
● Compliance
● Schematics
● Service Records

32
Supply Chain
Knowledge
Graphs

Semantic
Conventions
Resolved
Entities
Operational
Transactions
Graph
Inference
33
What is a Knowledge Graph?
• Ontologies
• Taxonomies
• Friendly Naming
• Schema/Structure
• Master Data
• Slowly Changing Dims
• Hierarchies
• Mappings
• Business Processes
• Signal Events
• Granular Detail
• Real Time Context
• Communities
• Dependencies
• Isomorphic Subgraphs
• ML Predictions
A knowledge graph combines consistent business semantics, entities extracted
and unified from source data, detailed transactional flows, and in-graph
analytics/inference for decision support.

34
The Modern Supply Chain is a Knowledge Graph
https://www2.deloitte.com/content/dam/insights/us/articles/3465_Digital-supply-network/DUP_Digital-supply-network.pdf

Google + Neo4j: Your Supply Chain Control Tower
Supply Chain AI
Provide the best AI/ML algorithm library
for the circular economy
Supply Chain Partners
Establish an innovative
supply chain partner ecosystem
Supply Chain Pulse
Enable supply chain professionals
to have real
-time visibility
Supply Chain Twin
Model the real, networked world
and accept imperfect data
1
2
3
4

● Purpose-built supply chain twin solution
● Planet-scale Infrastructure as a Service. Fully managed
Multi Cloud Data Warehouse
● Industry-leading and flexible ML/AItoolchain
● Global market leader in graph technology
● Aligned with Google Cloud Supply Chain Twin solution
● Compliments Google Cloud AI/MLand analytics
technologies
Neo4j & Google Cloud:
A powerful combination for supply chain
transformation

Supply
Chain Twin
BigQuery
Event
processing
Cloud
functions
PubSub
Use cases
User
Engagement
Neo4j
Connector for BI
Neo4j Bloom
Monitoring and analysis /
Custom applications
Analytics
Graph queries
Looker
Graph store
Supply
Chain AI
Demand
Shaping
Inventory
Positioning
Perfect
Fulfillment
Sustainability
Vertex AI
Dataflow
Data
Engineering
Feature
Engineering
Graph
Data
Science
Data Sources
Private
ERP
WMS
TMS
Telemetry
IoT
Partner (ISV & Tech)
Community
Suppliers
Logistics Providers
Customers
Transportation Visibility
Public
Weather
Risk
Sustainability
Healthcare
Climate
Social
Maps
Events
Canonical
Data Model
Supply Chain
Pulse
Google Workspace

Google Supply Chain Twin L2 Graph Data Model

39
Demo

The knowledge graph codifies data for
inferring new knowledge using connections to
support exploration, discovery and decisions
– by humans, software, or AI systems.
Because the utility of knowledge graphs
increases as they consume adjacent data
domains, knowledge graphs will naturally
grow to massive sizes and will require
new hybrid OLTP/OLAP architectures.
Knowledge Graphs at Scale

Knowledge Lake
What’s Next: Knowledge Lake Architecture
41
Operational Data Stores
● Enterprise Asset
● Petabyte Scale
● Hybrid OLTP/OLAP
● Native Fabric
● Fast Data Transfer
● In-Graph ML
● Common APIs

42
Advantages of Graphs
FAST ELEGANT EFFICIENT UNIFYING INSIGHTFUL
Relationships
(and nodes)
are stored in
memory for
real-time
access
Complex
business
processes are
simply and
faithfully
represented
Queries
traverse
locally-linked
objects with
consistent
performance
Creates a
flexible,
connected
view across
disparate data
domains
Builds up
context,
enabling
reasoning,
inference and
predictions

43
Thank You!
sales@neo4j.com
michael.moore@neo4j.com

Optimizing the Supply Chain with Knowledge Graphs, IoT and Digital Twins_Moore.pdf

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Optimizing the Supply Chain with Knowledge Graphs, IoT and Digital Twins_Moore.pdf

Similar to Optimizing the Supply Chain with Knowledge Graphs, IoT and Digital Twins_Moore.pdf (20)

More from Neo4j

More from Neo4j (20)

Recently uploaded

Recently uploaded (20)

Optimizing the Supply Chain with Knowledge Graphs, IoT and Digital Twins_Moore.pdf