Hybrid automatic repeat request buffer memory and logical channel buffer memory optimization employing generative artificial intelligence foundation models
Generative AI models dynamically manage HARQ and logical channel buffer memory in wireless communication systems, addressing inefficiencies by predicting memory needs, leading to optimized memory usage and improved system performance.
WO2026128078A1PCT designated stage Publication Date: 2026-06-18QUALCOMM INC
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- QUALCOMM INC
- Filing Date
- 2025-10-13
- Publication Date
- 2026-06-18
AI Technical Summary
⚠Technical Problem
Existing wireless communication systems inefficiently allocate memory for HARQ and logical channel data buffers, reserving excessive amounts based on worst-case scenarios, leading to suboptimal memory usage and inefficiency.
⚗Method used
Employing generative artificial intelligence foundation models to dynamically manage HARQ and logical channel buffer memory by predicting memory requirements based on real-time traffic patterns and network conditions, using pretrained and fine-tuned models to adapt memory allocation and release.
🎯Benefits of technology
Optimizes memory usage by accurately predicting memory needs, enhancing efficiency and reducing unnecessary reservations, thereby improving overall system performance.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure US2025050711_18062026_PF_FP_ABST
Abstract
An apparatus is configured to operate one of a pretrained or a pretrained and fine-tuned generative artificial intelligence (AI) foundation model (the generative AI foundation model), pretrained or pretrained and fine-tuned using at least a wireless language that models a wireless protocol, to receive a wireless input according to the wireless protocol, convert the wireless input into the wireless language, convert the wireless language into tokens, map each of the tokens to the generative AI foundation model as embeddings, capture patterns and relationships between the embeddings, expressed implicitly in statistics, using the generative AI foundation model, and apply the statistics, an output of the generative AI foundation model, or both to a dynamic memory management controller. The dynamic memory management controller adapts an amount of hybrid automatic repeat request (HARQ) buffer memory and / or logical channel buffer memory to allocate or release in the one or more memories.
Need to check novelty before this filing date? Find Prior Art