AI-Based CSI Reporting with Input Pre-Processing Constraints

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing wireless communication systems face challenges in accurately and efficiently performing wireless signal transmission and reception processes.

Innovation Solution

A method and apparatus for channel state information (CSI) reporting in wireless communication systems using artificial intelligence/machine learning (AI/ML) models, involving input restriction configurations, pre-processing of datasets, and CSI reports that include information on pre-processing performed by user equipment (UE).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If AI/ML models are used to enhance CSI reporting accuracy, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
ImproveCSI reporting accuracyVSAvoidUE processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by performing pre-processing on the input dataset before feeding it to the AI/ML model. The network configures input restriction parameters that define which data elements should be pre-processed or excluded. This pre-processing step prepares the data in advance, reducing the computational burden during actual CSI reporting while maintaining high accuracy through the AI/ML model's predictive capabilities.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If input restriction configuration is applied to AI/ML model, then productivity is improved, but loss of information increases

Engineering Contradiction:
ImproveCSI reporting efficiencyVSAvoidinput dataset information
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent applies local quality by implementing input restriction at specific locations in the data processing pipeline rather than applying uniform restrictions throughout. The network configures restriction parameters that selectively apply to certain input data elements (such as specific resource indicators or channel measurement data) while preserving other important information. This selective pre-processing maintains productivity by filtering out redundant data while preserving essential information needed for accurate CSI reporting.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4694008A1Method and apparatus for transmitting and receiving signal in wireless communication system
Publication Date: 2026.02.11 LG ELECTRONICS INC
  • EP4694008A1 patent drawingFigure 1~2
  • EP4694008A1 patent drawingFigure 3
  • EP4694008A1 patent drawingFigure 4~5

AI summary

A method for reporting channel state information (CSI) by a terminal in a wireless communication system according to at least one of embodiments disclosed in the present specification comprises: receiving, from a network, a setting for a limitation on an input to an artificial intelligence/machine learning (AI/ML) model related to CSI; performing a pre-processing process for an input data set of the AI/ML model on the basis of the setting for the limitation on the input; acquiring an output related to the CSI from the AI/ML model on the basis of the input data set that has passed through the pre-processing process; and transmitting a CSI report on the basis of the output related to the CSI, wherein the CSI report may comprise information about the pre-processing process performed by the terminal.