Gain access to resources and project updates

Register or log in to save your details for future use
First name
Last name
Business email
Company name
Job title

TM Forum will be processing the above information, with the assistance of our service providers located within and outside the European Union, to manage your registration to this event or report download, as well as to keep you informed about our services and products, future events and special offers, the organization of events, providing training and certification, and facilitating collaboration programs. Privacy policy

I wish to receive further information from the Catalyst Team about their products and service by electronic means. Check the "Team Members" section of this Catalyst Project to review the companies that will receive your information. Companies may join the project in the future, so please check back periodically for any updates

logologo
All projects

LOKI - LLM O&M Knowledge Integrator

URN C24.0.628
Topics AI (Artificial Intelligence), Digital twin, Open Digital Architecture (ODA)
Finalist

Automating network operations and maintenance through large language models

Hi there, welcome to LOKI - LLM O&M Knowledge Integrator ! We will be showcasing at Catalyst booth C20! CSPs have traditionally relied heavily on the knowledge and expertise of engineers to solve network issues – as a result, multiple rounds of human interactions may be required to tackle a problem. This manual approach can however no longer cope with CSPs’ increasingly complex operations and maintenance (O&M) requirements. This Catalyst aims to harness data patterns and best practice to build large language models (LLMs) enabled Copilots and AI Agents across the “Monitor and Handle Anomaly” value stream. The project team will focus on developing LLMs to address several specific use cases, such as summarizing work order information, demarcating network faults with the support of digital twins, and recommending next best actions for O&M tasks. Other priority applications will be identifying the root causes of network faults and issues and generating operational reports based on intent. In each case, the objective is to enable engineers to simply ‘ask’ an AI agent, underpinned by an LLM, to complete necessary tasks. Besides the scenario-based innovation with LLMs, the project team also agree that organization, culture and talent challenges need to properly addressed in order to adopt LLM at scale. The overarching goal of the Catalyst is to help CSPs greatly simplify their O&M processes and tasking handling, thereby improving the customer & employee experience and realizing operational excellence. This project will also deliver sustainability impact in terms of decent workplace, inclusion & diversity, reduced carbon emission, etc.

Resources

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

TM Forum Assets Used

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

Contact team

Email the members of the Catalyst team to request more details.

Name
Email

Team members

Beijing ZZNode Technologies Co.,Ltd. logo
BroadTech Technology Co., Ltd logo
China Academy of Information and Communications Technology(CAICT) logo
Champion
China Mobile Communications Corporation logo
Champion
Hong Kong Telecommunications (HKT) Limited logo
Champion
Huawei Technologies Co. Ltd logo
Indosat Ooredoo Hutchison logo
Champion
MTN South Africa logo
Champion
Saudi Telecom Company logo
Champion

Related projects