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

All projects

AI for customer perception network optimization

URN C24.0.673
Topics AI (Artificial Intelligence), Digital twin, IT & process automation

Anticipating customer pain points through AI-led digital twins

featured image
CSPs have historically taken a performance-centric approach to the optimization of their wireless networks, with an emphasis on addressing problems site by site. This Catalyst is exploring how CSPs can move to a perception-centric approach focused on optimizing crucial service areas, scenarios and solutions for key customers. By employing advanced AI, the Catalyst will seek to strengthen the effective transmission of customers’ real experiences such as video lag, resolution and first frame delay, to network operations. By better coordinating the perception layer, business layer and network layer, the goal is to create a quality optimization system centered on customer perception. This system could yield numerous business benefits. For example, it could help CSPs implement differentiated scheduling strategies for short video services, potentially leading to an increase of up to 13.4% in network traffic. To identify issues that affect customers’ perception before they complain, the solution will employ an algorithm that draws on big data modeling in both the operational and business domains. This will enable the CSP to build a precise user-level profile and anticipate when an individual customer might suffer a suboptimal experience. The Catalyst also plan to use digital twin technology to identify and address potential gaps in deep indoor coverage, and then enable closed-loop management of these problems. Using machine learning, the solution will employ a three-dimensional virtual grid to develop a ‘stereo coverage fingerprint library’ that will model customers’ perception of quality and provide alerts when high levels of demand could result in a poor experience. At the same time, the Catalyst will harness speech recognition and signaling big data technology to improve complaint handling. One of the objectives is to automatically locate the root cause of poor-quality speech bursts in small cells, and establish a relationship model between this root cause and the configuration of speech-related parameters. The solution will then be able to optimize the cell parameters accordingly.


We are pleased to present our achievements for our Catalyst. Please visit our Kiosk 'C3' for further details.


Catalyst Overview

Arena Presentation Outline

PoC Demo Videos

Catalyst Storyline Video

Contact team

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


Team members

China Mobile Communications Corporation logo
China Unicom logo
Huawei Technologies Co. Ltd logo
Inspur Communication Information Systems Co., Ltd logo
PT Telekomunikasi Selular logo
Saudi Telecom Company logo
ZTE Corporation logo

Related projects