NEF Charging Reporting for AI/ML Operations in 5G Core

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current 5G core network technologies lack charging aspects for artificial intelligence (AI)/machine learning (ML) operations, specifically in network exposure function (NEF) initiated charging reporting.

Innovation Solution

Introduce new triggers and parameters in the 5G core network to support AI/ML charging reporting, including Consolidated Data Rate monitoring and list of UEs, enabling the Network Exposure Function (NEF) to transmit charging data requests to the Charging Function (CHF) and trigger appropriate reporting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If charging aspects for AI/ML operations are introduced in 5G core network, then billing and credit control capability is improved, but system complexity increases

Engineering Contradiction:

Improvecharging capability for AI/ML operationsVSAvoid5G core network structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The Network Exposure Function (NEF) is enhanced to perform multiple functions: it continues to provide network exposure services while also handling charging data collection and reporting for AI/ML operations. The charging data request message integrates both traditional charging parameters and AI/ML-specific parameters (consolidated data rate, list of UEs, triggers), allowing the NEF to serve both conventional and AI/ML charging needs through a unified mechanism.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The NEF acts as an intermediary between the Application Function (AF) and the Charging Function (CHF). It receives charging data requests from AFs, processes AI/ML operation parameters, and forwards appropriately formatted charging data to the CHF. This intermediary role allows the CHF to remain relatively simple while still supporting complex AI/ML charging scenarios.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If new triggers and parameters are added for AI/ML charging reporting, then charging accuracy is improved, but message complexity increases

Engineering Contradiction:

Improvecharging reporting accuracyVSAvoidcharging data message structure

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The charging data request message is segmented into distinct information elements, each serving a specific purpose: session identifier, subscriber identifier, charging identifier, consolidated data rate, list of UEs, and triggers. This segmentation allows for clear organization of complex AI/ML charging parameters while maintaining message readability and processing efficiency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces new parameters (consolidated data rate, list of UEs, triggers) to existing charging data messages while maintaining backward compatibility with traditional charging parameters. The message structure evolves to accommodate AI/ML-specific requirements without completely redesigning the charging communication protocol.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260067175A1Apparatuses and communication methods for ai/ ML operation

Publication Date: 2026.03.05 GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

AI summary

A communication method for artificial intelligence (AI)/machine learning (ML) operation includes transmitting, by a network exposure function (NEF) to a charging function (CHF), a charging data request message comprising at least one information element associated with a charging reporting for AI/ML operation and allowing and/or triggering the CHF to identify the at least one information element associated with the charging reporting for AI/ML operation based on the charging data request message.