Changing the 5G experience landscape – Meet us at DTW 2022

|---Module:text|Size:small---|

Let’s meet at the arena!

Curious about our last developments on Autonomous Customer Experience, 5G networks, and automated network processes?

Celfocus is one of 27 teams that are part of the Catalysts’ list – a set of innovative proof of concept projects – and contributing to one of these cutting-edge prototypes with the topic Autonomous customer experience index for zero-touch 5G network – Phase II, nominee for the categories “Outstanding Catalyst – Business Impact”, “Outstanding Catalyst – Innovation” and for the recently introduced category “Future Techco”.

In close-knit collaboration with our strategic client Telefónica, Celfocus is co-creating a leading-edge solution to deliver higher quality and enhanced customer experience, based on the Customer Experience Index (CEI) that combines real-time network and customer data within increasingly complex, high-performance networks.

Disclosing a seamless, predictive, and empowered customer-centric approach

The goal is to anticipate customer pain points and proactively implement autonomous solutions to avoid service degradation that may negatively impact on Customer Experience. Celfocus contributes to specific use cases by using AI/ML techniques to 1) detect anomalies and produce an initial root cause insight by indicating which service is more likely to be causing the anomaly; 2) manage the admission control of new network slice requests according to an objective function.

Building on the first phase (Part I), it provides a faster, more efficient deployment of automated processes that aim to detect service anomalies at the antenna level within the whole network for an optimized, high-level customer experience with zero-touch and zero interruptions.

Moreover, in the context of the foresight of 5G technology and the highly dynamic context to be imprinted in network management and configuration, cutting-edge machine learning algorithms implement an Admission Control layer that can be applied to accept or reject slice requests conditional to objective functions, like revenue maximization of energetic efficiency. These algorithms can be extended to determine the optimal asking price for slice requests.