Automating network operations and maintenance through large language models
Based on the TM Forum GenAI report published in 2023 and the challenges collected from champions in this project, our project target to address 4 major challenges when CSPs tried to integrate O&M knowledge into different business scenarios and drive adoption at scale: 1. Which network O&M scenarios to start with? 2. How to integrate LLM into specific business scenarios? 3. What changes need to happen to organization, talent and culture? 4. What is the sustainability impact? [Resource and Read Instructions] We have prepared a presentation and some demos (kindly note that it will be frequently updated before DTW) for pre-reading. Please refer to the below read instructions. * Page 2 & 3: Challenges and Solution Overview If you are interested in the exploring how LLM can create value in different network O&M scenarios, you might go to: * Page 4: Core Network IoT Service Compliant Analysis AI Agent * Page 5: Home Broadband Installation & Maintenance Copilot * Page 6: Fiber O&M AI Agent We have also prepared two demo videos for the first two scenarios. Integrating O&M Knowledge into applications and processes requires quite a number of efforts to make sure LLM can truly understand user intent and provide accurate and timely replies in the user-friendly way. Understand the technology details we used in: * Page 7: Key Technology: LLM Knowledge Integration-- how to use techniques like prompt engineering, chain-of-thoughts, RAG, function call, NL2API for LLM Integration * Page 8: Key Technology: Digital Twin Network (DTN) --LLM needs a graphic view of real-time network and service status to support precise decision making. DTN is designed to provide that complimentary capability We have also prepared a DTN demo based on IOH & Huawei joint innovation. There is no doubt that Organization, Talent and Culture are key to making sure LLMs can be adopted at scale and responsibly. Understand how HKT, China Mobile and MTN each has developed solutions to address organizational challenges using TM Forum GB1047 Digital Talent Maturity Model (DTMM): * Page 9: Organization, Talent and Culture solution overview based on DTMM gaps * Page 10: HKT Organization Structure Design Case * Page 11: CMCC Strategic Workforce Planning Case * Page 12 & 13: MTN Diversity & Inclusion Case In this project, we do not only see value delivered in operational excellence and customer experience. More importantly, we found that the use of LLM will also support “Tech for Good”. The quantified value can be found in: * Page 14: Quantified Solution Value This project also used assets from 5 different TM Forum collaboration projects, find the mapping details and how to use in: * Page 15: TM Forum Assets Used In the end, we have prepared some lesson leant and hope they can provide additional help and insights to other industry practitioners. * Page 16: Lesson learnt
IG1291 MAMA defined CSP Value Streams for Autonomous Operations v2.0.0
IG1293 Using the Value Operations Framework v1.0.0
IG1345 Embracing Generative AI in Telecom: Amplifying Autonomous Network Evolution v1.0.0
IG1274 AIOps Lifecycle v3.0.0
IG1307 Digital Twin for Decision Intelligence (DT4DI) Whitepaper v1.0.0
GB1047 Digital Talent Maturity Model v2.0.0
Email the members of the Catalyst team to request more details.
Growing revenue by bringing AI-enabled network service quality assurance into autonomous transportation in the open-pit mining industry
Showcasing high-value autonomous network Level 4 scenarios, unifying the vision across TM Forum members for a smarter future
Creating the future of mobile network optimization.