SoftBank Corp. has introduced a new Large Telecom Model (LTM), an artificial intelligence (AI) system designed for the telecom industry.
The LTM is trained on various datasets, including network data and operational knowledge accumulated by SoftBank over the years. This model allows for advanced decision-making in the design, management, and operation of cellular networks.
SoftBank plans to integrate the LTM into its operations and has also created specialized AI models by fine-tuning the LTM to optimize base station configurations for improved network operations. By using the LTM-led approach, changes that used to take days can now be made in minutes with over 90% accuracy, reducing operational time and costs while minimizing errors.
The main features of the LTM include leveraging large-scale data for advanced inference capabilities and natural language processing (NLP) for flexible responsiveness. It provides insights from SoftBank's mobile network specialists and allows for the development of specialized AI models for specific use cases in mobile network operations. SoftBank has collaborated with NVIDIA to train and optimize the LTM and plans to continue exploring the use of AI to enhance network efficiency and deliver high-quality services to customers.
Latest: A Single Word Can Change Lives
AI for RAN
This demonstrates the potential for developing dedicated AI models tailored to different operational scenarios in cellular networks. The LTM also serves as the foundation for the “AI for RAN” initiative, which aims to enhance radio access network (RAN) performance through AI. The LTM model has been optimized using NVIDIA NIM, resulting in significant performance improvements for specialized use cases.
Human AI
SoftBank's Research Institute of Advanced Technology (RIAT) envisions the implementation of “Human AI,” which combines human expertise with AI capabilities. SoftBank aims to integrate various AI models developed based on the LTM with AITRAS, an AI-RAN integrated solution under development.
Redefining Network Operations
Ryuji Wakikawa, Vice President, Head of the Research Institute of Advanced Technology at SoftBank, said, “By fine-tuning LTM, it’s possible to build AI models specialized for various processes and deploy them as agents. This not only optimizes and automates operational tasks but also enhances network performance through the tuning of wireless devices. SoftBank will continue to leverage cutting-edge AI technologies, aiming to deliver unprecedented levels of high-quality communication services to customers.”
Chris Penrose, Vice President of Telecoms at NVIDIA, praised SoftBank's innovation, adding that, “Large Telecom Models are the foundation for simplifying and speeding up network operations by enabling the creation of network AI agents for specialized tasks such as network planning, network configuration, and network optimization. SoftBank’s rapid innovation in developing its new LTM, leveraging NVIDIA AI technologies, sets a powerful example for telecom operators globally to redefine their network operations processes with AI.”
Interesting Reads:
Globe Business: Building a Stronger, More Connected Philippines
Saleem Alblooshi Explores How du is Developing the UAE’s 5G Advanced and Sustainable Future
Onoe on ITU’s Vision: Connecting the World through Standards and Partnerships
