Uplink Resource Mapping for Priority-Based AI UCI Bits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current communication standards do not adequately support the interpretation and transmission of bits generated by AI/ML models in uplink control information (UCI) for UEs, leading to undefined bit meanings and lack of differentiated priority handling for AI/ML model outputs and parameters.
Innovation Solution
Implement new resource element mapping rules for multiplexing AI/ML model-generated bits as new UCI types on physical uplink shared channels (PUSCH) based on priority orders, enabling separate handling and transmission of AI/ML model outputs and parameters alongside legacy UCI types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If new resource element mapping rules are implemented for AI/ML model-generated bits, then differentiated priority handling and reliable transmission are achieved, but device complexity and standardization complexity increase
Solution Approach 1:
The patent segments UCI transmission into multiple priority levels (first priority and second priority), allowing AI/ML model-generated bits to be differentiated from legacy UCI types. This segmentation enables reliable transmission by assigning appropriate resource elements and mapping rules to each priority level, resolving the contradiction between reliability and complexity through structured organization.
Solution Approach 2:
The patent introduces dynamic priority handling where the network can configure different priority levels for AI/ML model outputs and parameters. This dynamic approach allows the system to adapt resource allocation based on the importance of the data being transmitted, achieving reliable transmission while managing complexity through flexible configuration rather than rigid fixed rules.
2Productivity
If AI/ML model-generated bits are multiplexed with legacy UCI types, then radio resource utilization improves, but interpretation ambiguity and standardization challenges increase
Solution Approach 1:
The patent applies local quality by assigning different properties (priority levels) to different portions of the UCI transmission. AI/ML model-generated bits are assigned specific priority levels (first or second priority) distinct from legacy UCI types, allowing the receiver to correctly interpret the meaning and importance of each bit based on its assigned priority, thus preventing information loss while enabling efficient multiplexing.
Solution Approach 2:
The patent introduces priority levels as an intermediary mechanism between the transmitter and receiver. This intermediary (priority indication) resolves the interpretation ambiguity by providing explicit information about the nature and importance of each bit, allowing the receiver to correctly process AI/ML model-generated bits alongside legacy UCI types without confusion.
3Reliability
If separate handling of AI/ML model outputs and parameters is implemented, then transmission reliability improves, but signaling overhead and processing complexity increase
Solution Approach 1:
The patent merges the handling of AI/ML model-generated bits with the existing UCI transmission framework by integrating them into the same physical uplink shared channel (PUSCH) resources. Instead of creating separate transmission channels, the patent combines AI/ML bits with legacy UCI types in the same resources but applies different priority-based mapping rules, reducing signaling overhead while maintaining reliable transmission through differentiated handling.
Data Source
AI summary
According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises applying a resource element mapping rule to one of the one or more fields based on the obtained priority and transmitting the uplink transmission based on the applied resource element mapping.