# Using AI to Manage Wireless Network Resources Smarter > Intel's 2025 patent on using a hierarchy of AI models to manage wireless network resources, making them more efficient by learning from network measurements and rewards. - **Patent:** US 12245052 - **Original title:** Reinforcement learning (RL) and graph neural network (GNN)-based resource management for wireless access networks - **Owner:** Intel - **Granted:** 2025 - **Status:** Active - **Times cited:** 3 - **Field:** telecommunications, ai_ml, software, consumer_electronics ## What it does This patent describes a computer system, called a 'computing node,' designed to help manage wireless networks like the 5G and beyond (Next Generation or NG). It uses a smart approach with multiple Artificial Intelligence (AI) models, specifically machine learning models, organized in layers like a pyramid. The system takes measurements from the network and uses these AI models to make decisions. A key part is how these models communicate: a model at a lower level gets instructions from a model at a higher level, and it also uses its own measurements to send signals. This allows the system to train the AI models using 'reward functions,' which are like scores that tell the AI if it's doing a good job. For example, a model might decide how to best allocate bandwidth based on traffic data and instructions from a higher-level model overseeing network stability. ## What it does NOT cover - Does not cover AI models that are not organized in a multi-level hierarchy. - Does not cover systems that do not generate reward functions for training AI models. - Does not cover wireless networks that are not 'Next Generation' (NG) networks. - Does not cover systems where control signaling only comes from a single AI model. - Does not cover network management that doesn't use network measurements. ## The clever bit The innovation lies in structuring the AI models in a hierarchy, allowing for more sophisticated and layered decision-making. This enables models at different levels to specialize in different aspects of network management, from real-time adjustments to longer-term strategic planning, all trained through a system of rewards. ## Real-world examples 1. 5G network resource management 2. Future wireless network optimization 3. Intelligent network controllers (RICs) ## Why it matters As wireless networks become more complex with 5G and future technologies, managing their resources efficiently is crucial. This patent offers a method for using AI to dynamically optimize network performance, potentially leading to better speeds, lower latency, and more reliable connections for users. ## Frequently asked questions ### What does Using AI to Manage Wireless Network Resources Smarter cover? Intel's 2025 patent on using a hierarchy of AI models to manage wireless network resources, making them more efficient by learning from network measurements and rewards. ### Who owns patent US 12245052? Intel owns this patent, granted in 2025. ### When does this patent expire? This patent is expected to expire on September 23, 2041, when the invention enters the public domain. ### What is patent US 12245052 cited by? This patent has been cited by 3 later patents that build on its ideas. ### What problem does this patent solve? As wireless networks become more complex with 5G and future technologies, managing their resources efficiently is crucial. This patent offers a method for using AI to dynamically optimize network performance, potentially leading to better speeds, lower latency, and more reliable connections for users. ### What does this patent NOT cover? Does not cover AI models that are not organized in a multi-level hierarchy. **Full plain-English explainer:** https://patentbrief.org/patent/us/12245052/reinforcement-learning-rl-and-graph-neural-network-gnn-based-resource-management **Original patent:** https://patents.google.com/patent/US12245052 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How 5G Networks Coordinate AI Models Across Different Devices](https://patentbrief.org/patent/us/20230412513/providing-distributed-ai-models-in-communication-networks-and-related-nodesdevic) — 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. - [How Phones and Towers Use AI to Improve Wireless Signal Quality](https://patentbrief.org/patent/us/12506552/method-and-apparatus-for-estimating-channel-in-wireless-communication-system) — This patent describes how a mobile phone and a base station work together, using machine learning, to accurately measure and predict the quality of the wireless connection, making communication more reliable. - [How AI Learns to Run Faster on Specific Computer Chips](https://patentbrief.org/patent/us/20250371349/methods-and-apparatus-for-hardware-aware-machine-learning-model-training) — This patent describes how a smart AI system, called a reinforcement learning agent, trains other AI models to run more efficiently on specific computer hardware by cleverly reducing their size without losing too much accuracy. - [How AI Learns to Manage Computer Applications Using Digital Simulators](https://patentbrief.org/patent/us/11238372/simulator-training-for-automated-reinforcement-learning-based-application-manage) — This patent describes a system that creates and trains digital simulators, which then teach other AI programs how to automatically manage and optimize complex computer applications in a controlled virtual environment. - [How AI Models Learn Complex Tasks by Breaking Them Down](https://patentbrief.org/patent/us/11120365/for-hierarchical-decomposition-deep-reinforcement-learning-for-an-artificial-int) — This patent describes a method for training artificial intelligence models to solve big problems by splitting them into smaller, manageable steps and learning each step separately before combining them.