BT & Neo4j: Knowledge Graphs for Critical Enterprise Systems.pptx.pdf

Presented at Gartner Data & Analytics, London Maty 2024. BT Group has used the Neo4j Graph Database to enable impressive digital transformation programs over the last 6 years. By re-imagining their operational support systems to adopt self-serve and data lead principles they have substantially reduced the number of applications and complexity of their operations. The result has been a substantial reduction in risk and costs while improving time to value, innovation, and process automation. Join this session to hear their story, the lessons they learned along the way and how their future innovation plans include the exploration of uses of EKG + Generative AI.

1. Knowledge Graphs for
Critical Enterprise Systems
How knowledge graphs and GenAI combine in real-world solutions
Sreenath Gopalakrishna
Director of Software Engineering, BT
Dr. Jim Webber
Chief Scientist, Neo4j

2. 1.Introduction to Knowledge
Graphs
2.Networks everywhere!
3.Evolution of SRIMS
4.Generative AI as a system
component
5.Competitive advantage
Agenda
Neo4j Inc. All rights reserved 20242

3. Knowledge Graphs are
cool.
Let me show you around
Neo4j Inc. All rights reserved 20243

4. It’s Not What You Know
Neo4j Inc. All rights reserved 20244

5. It’s Who You Know
Neo4j Inc. All rights reserved 20245

6. And where they are
Neo4j Inc. All rights reserved 20246

7. Higher Pay and More Promotions
•People Near Structural Holes
•Organizational Misfits
Network Structure
is Highly Predictive
Photo by Helena Lopes on Unsplash
“Organizational Misfits and the Origins of Brokerage in Intrafirm Networks” A. Kleinbaum
“Structural Holes and Good Ideas” R. Burt
7

8. Relationships
are the strongest
predictors of behavior
But You Can’t Analyse
What You Can’t See
Christakis & Fowler
Neo4j Inc. All rights reserved 20248
●Most data disciplines ignore
relationships
●It’s painful to manually engineer
connected features from tabular
data
●Graphs are built on relationships,
so…
●You don’t have to guess at the
associations
●With graphs, relationships are
built in

9. Node
Represents an entity in the
graph with optional label
Relationship
Connect nodes to each other
Property
Describes a node or
relationship: e.g. name, age,
weight etc
Graph Modeling is Straightforward
MICA ANDRE
Name: “Andre”
Born: May 29, 1970
Twitter: “@andre29”
Name: “Mica”
Born: Dec 5, 1975
CAR
Brand “Volvo”
Model: “V70”
Since:
Jan 10, 2011
OWNS
Neo4j Inc. All rights reserved 20249
BROTHER
SISTER
DRIVES

10. Index-Free Adjacency: Fast, Flexible, Scalable

Relational Database
Person Person-Friend Friend
Native Graph Database
At write time
Data is .connected.
as it is stored
At read time
.Lightning-fast. retrieval of data and
relationships via pointer chasing
Neo4j Inc. All rights reserved 202410

11. These simple
blocks are all
you need
Neo4j Inc. All rights reserved 202411

Nodes&
Labels&
Relationships&
Properties

12. Knowledge Graphs Help
BT Group Deliver Digital
Transformation
Sreenath Gopalakrishna, Director of Software
Engineering BT Group

13. BT Group OSS Division: We develop the
strategies and platforms that help
modernise BT Groups’s infrastructure,
driving convergence and automation.

13BT Group |

14. The traditional network equipment deployment
approaches left a legacy of complexity and risk

•Multiple applications for each network technology
•Multiple vendors
•High maintenance costs
•Complex Application Integrations



Our challenge dimensions
14
Duplication
Closed
Platforms
Siloed
Data
Complexity
BT Group |

15. Our objectives were to create a platform that addressed
these fundamental capabilities:



The Proposed Solution - SRIMS
1.Self-Service framework for our network engineering
teams

1.Accessible digital twin platform

1.Real-time single source of truth

16. Benefits of a Graph
Database Approach
•Consolidation of siloed data
•Easy to extend and adapt
•Provides a single view of customers,
inventory and fault information
•Model physical and virtual environments
•Increased efficiency and performance
•Reduced Total Cost of Ownership

17. 50,000
Product availability check
requests per day

It handles tens of thousands
of product availability checks
requests, each with strict
SLAs.
3,000
Users


With peak time concurrency
regularly passing 1500.
Significant savings per
day


Financial losses resulting
from the inability to transact
and process orders due to
product non-availability.
The business-critical nature of the project is reflected in the numbers:
What did we achieve?
5,000+
Order progress requests per
hour

SRIMS performs service
design and provisioning for
various products.
17
Measurable Gains: 65% reduction in OSS Apps, reduced time
to deploy new capabilities, modernised processes and
improved innovation culture.
BT Group |

18. Future Innovations
The future is positive for SRIMS both within BT Group and in
the wider Telco Industry.
BT Group are now supplying the SRIMS platform via a partner
to other Telecom Service Providers.
We are now exploring the use of Enterprise Knowledge
Graphs + LLMs in a RAG architecture to provide intelligent
searching of information to enable faster business decisions.

18BT Group PowerPoint |

19. BT’s Asset
Knowledge Graph
Neo4j Inc. All rights reserved 202419
https://go.neo4j.com/rs/710-RRC-3
35/images/BT_SRIMS_Whitepaper.pdf

20. Are graphs for me?
Neo4j Inc. All rights reserved 202420

21. The Fastest Growing Database Category For 10 Years
Neo4j Inc. All rights reserved 202421

22. ISO SQL, meet ISO GQL
Neo4j Inc. All rights reserved 202422

23. The future is graph

24. The future is graph
Rethink what’s possible. Start building

25. Thank you for listening
Sreenath Gopalakrishna
Director of Software Engineering, BT
Dr. Jim Webber
Chief Scientist, Neo4j
Come talk to us at Neo4j Booth #324