AI CSI Processing Unit Occupancy for Efficient Wireless Reporting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing wireless communication systems lack efficient methods for determining and managing CSI processing capabilities, particularly when both legacy and AI/ML-based CPUs are used for calculating CSI reports, leading to inefficiencies in resource allocation and reporting.

Innovation Solution

The introduction of AI/ML-based CSI processing units (CPUs) that determine and manage CSI processing capabilities, including occupancy periods and resource allocation, enabling efficient handling of CSI reports.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If both legacy and AI/ML-based CPUs are used for calculating CSI reports, then processing capability and reporting efficiency are improved, but device complexity and resource management difficulty increase

Engineering Contradiction:

ImproveCSI reporting efficiencyVSAvoidCPU type management complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments CPU functionality into distinct types (legacy CPU and AI/ML-based CPU) with separate management mechanisms. Each CPU type has its own occupancy tracking and resource allocation rules, allowing the system to manage complexity through structured classification while benefiting from the enhanced capabilities of both CPU types for improved CSI reporting efficiency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces dynamic occupancy period tracking for each CPU type, where the system adapts resource allocation based on real-time CPU usage patterns. The network node dynamically adjusts which CPU types are allocated resources based on current CSI reporting requirements, enabling flexible management of both legacy and AI/ML-based processing capabilities.

Inventive Principle:

Principle #15Dynamics

2Productivity

If CPU occupancy periods are tracked and managed for both legacy and AI/ML-based CPUs, then resource allocation efficiency is improved, but measurement and monitoring complexity increases

Engineering Contradiction:

Improveresource allocation efficiencyVSAvoidCPU occupancy monitoring complexity

Core Design Contradiction:

ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements feedback mechanisms where the wireless device reports CPU occupancy status to the network node, which then uses this information to adjust future resource allocations. This closed-loop feedback system enables efficient resource allocation while managing monitoring complexity through structured information exchange between devices.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent uses the network node as an intermediary that centralizes the monitoring and coordination of CPU occupancy for both legacy and AI/ML-based CPUs. This intermediary approach allows the complex monitoring task to be managed at a higher level, with the network node orchestrating resource allocation based on occupancy information from wireless devices.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20260113654A1Channel state information processing unit for artificial intelligence based report generation

Publication Date: 2026.04.23 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

A method, system and apparatus are disclosed. A wireless device (WD) configured to communicate with a network node is described. The WD is configured to determine a first channel state information (CSI) processing unit (CPU) of a first CPU type based on a first characteristic of a first CSI report, where the first CPU type is an artificial intelligence CPU type, and generate the first CSI report using the first CPU and an artificial intelligence process, where the first CSI report has a first CPU occupancy. One or more actions are performed based on the first CSI report.