# How 5G Networks Coordinate AI Models Across Different Devices

> A method for 5G networks to translate AI requirements into network performance settings so that AI models can run efficiently across cloud, edge, and local devices.

- **Patent:** US 20230412513
- **Original title:** Providing distributed ai models in communication networks and related nodes/devices
- **Owner:** Telefonaktiebolaget LM Ericsson AB
- **Status:** Active
- **Times cited:** 17
- **Field:** telecommunications, ai_ml, consumer_electronics

## What it does

This patent describes a 'translation node' that acts as a bridge between an AI application and the underlying cellular network. It takes information about how an AI model is structured—specifically, its Model Deployment Map (MDM)—and converts that into concrete Quality of Service (QoS) parameters like required bandwidth or latency. By providing these parameters alongside the AI model, the network can intelligently decide where to run specific parts of the model, such as on a local device, an edge server, or a centralized cloud. For example, if an AI model for a self-driving car needs a specific inference time to be safe, this system ensures the network allocates the necessary resources to meet that target.

## What it does NOT cover

- Does not cover the internal architecture or training methods of the AI models themselves.
- Does not cover hardware-specific AI acceleration techniques like custom NPU or GPU chip designs.
- Does not cover general network routing protocols that do not involve AI model distribution.
- Does not cover user-level application interfaces or how the AI results are presented to the end user.

## The clever bit

The innovation lies in treating the 'Model Deployment Map' as a network-aware object, allowing the network to proactively adjust its QoS parameters based on the specific needs of the AI model's distributed components.

## Real-world examples

1. 5G network slicing for industrial IoT applications
2. Autonomous vehicle sensor fusion processing
3. Cloud-based augmented reality headsets
4. Real-time remote surgery telepresence

## Why it matters

As AI moves from centralized data centers to the 'edge' (closer to users), managing the network becomes a bottleneck. This patent addresses the friction between AI software requirements and cellular network capabilities, which is essential for low-latency applications like autonomous vehicles, remote robotics, and real-time augmented reality.

## Frequently asked questions

### What does How 5G Networks Coordinate AI Models Across Different Devices cover?

A method for 5G networks to translate AI requirements into network performance settings so that AI models can run efficiently across cloud, edge, and local devices.

### Who owns patent US 20230412513?

This patent is owned by Telefonaktiebolaget LM Ericsson AB.

### When does this patent expire?

This patent is expected to expire on November 26, 2040, when the invention enters the public domain.

### What is patent US 20230412513 cited by?

This patent has been cited by 17 later patents that build on its ideas.

### What problem does this patent solve?

As AI moves from centralized data centers to the 'edge' (closer to users), managing the network becomes a bottleneck. This patent addresses the friction between AI software requirements and cellular network capabilities, which is essential for low-latency applications like autonomous vehicles, remote robotics, and real-time augmented reality.

### What does this patent NOT cover?

Does not cover the internal architecture or training methods of the AI models themselves.

**Full plain-English explainer:** https://patentbrief.org/patent/us/20230412513/providing-distributed-ai-models-in-communication-networks-and-related-nodesdevic

**Original patent:** https://patents.google.com/patent/US20230412513

---

_Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._