18467707. AI-ML MODEL STORAGE IN OTT SERVER AND TRANSFER THROUGH UP TRAFFIC simplified abstract (MEDIATEK INC.)

AI-ML MODEL STORAGE IN OTT SERVER AND TRANSFER THROUGH UP TRAFFIC

Organization Name

MEDIATEK INC.

Inventor(s)

Ta-Yuan Liu of Hsinchu City (TW)

Hao Bi of San Jose CA (US)

CHIA-CHUN Hsu of Hsinchu City (TW)

AI-ML MODEL STORAGE IN OTT SERVER AND TRANSFER THROUGH UP TRAFFIC - A simplified explanation of the abstract

This abstract first appeared for US patent application 18467707 titled 'AI-ML MODEL STORAGE IN OTT SERVER AND TRANSFER THROUGH UP TRAFFIC

Simplified Explanation

The patent application describes a method and apparatus for storing and transferring AI-ML models in a wireless network. The AI-ML model can be stored at the AI server and transferred through the user plane (UP) connection. The UE can download the AI-ML model from the AI server, and the model can be updated at the RAN node or the UE itself.

• AI-ML model storage and transfer in wireless networks:

 - AI-ML model stored at AI server
 - Transfer through user plane (UP)
 - UE downloads model from AI server
 - Model can be updated at RAN node or UE

• Shared AI dataset among entities:

 - Transfer through UP connection or new AI plane

---

1. 1. 1. Potential Applications

This technology can be applied in various industries such as healthcare, finance, and manufacturing for improving AI-ML model management and deployment in wireless networks.

1. 1. 1. Problems Solved

1. Efficient storage and transfer of AI-ML models in wireless networks. 2. Seamless updating of AI-ML models at different network nodes and user equipment.

1. 1. 1. Benefits

1. Enhanced performance of AI applications in wireless networks. 2. Simplified management of AI-ML models for network operators and users.

1. 1. 1. Potential Commercial Applications

Optimizing AI-ML model storage and transfer in 5G networks for industries such as telecommunication, IoT, and autonomous vehicles.

1. 1. 1. Possible Prior Art

Prior art may include patents related to AI model management and transfer in wired networks, as well as research papers on AI dataset sharing among entities.

---

1. 1. 1. 1. Unanswered Questions

1. 1. 1. 1. How does this technology impact network latency in real-time AI applications?

The patent application does not specifically address the impact of this technology on network latency in real-time AI applications.

1. 1. 1. 1. What are the security measures in place to protect the AI-ML models during transfer?

The patent application does not detail the security measures implemented to protect AI-ML models during transfer in wireless networks.

Original Abstract Submitted

Apparatus and methods are provided for AI-ML model storage and transfer in the wireless network. In one novel aspect, the AI-ML model is stored at the AI server and transferred through the user plane (UP). In one embodiment, UE downloads the AI-ML model from the AI server through the UP connection. In one embodiment, the AI-ML model is updated at the RAN node, and the UE downloads the AI-ML model through the AI server. In another embodiment, the AI-ML model is updated at the UE, and the UE uploads the AI-ML model to the AI server through the UP connection. In another embodiment, the UE uploads the AI-ML model to the RAN through the AI server. In one embodiment, the UE mobility triggers the AI-ML model transfer. In one novel aspect, the AI dataset is shared and transferred among different entities through the UP connection or a new AI plane.