Selective Neural Network Triggering for UE Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems, particularly in 5G networks, face challenges in efficiently processing positioning measurement data due to the need for precise and dynamic handling of neural network functions for user equipment (UE) positioning, which is hindered by the lack of adaptive and efficient mechanisms for triggering and aggregating neural network functions based on real-time environmental and operational conditions.
Innovation Solution
A method is introduced where user equipment (UE) dynamically obtains and processes positioning measurement data using neural network functions generated through machine learning, based on historical procedures, and selectively triggers these functions based on specific criteria such as geographic region, indoor/outdoor status, and base station/carrier network information, enabling efficient feature processing and reporting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural network functions are continuously triggered for positioning measurement data processing, then positioning accuracy is improved, but signaling overhead and processing complexity increase
Solution Approach 1:
The patent implements dynamic triggering of neural network functions based on real-time evaluation of triggering criteria. The system selectively activates NN functions only when specific conditions are met (e.g., measurement quality thresholds, environmental changes), rather than continuously processing. This dynamic approach maintains positioning accuracy by triggering processing only when necessary, while reducing overall processing complexity and signaling overhead during normal operation.
Solution Approach 2:
The system changes the operational parameters of the positioning system by introducing triggering criteria that evaluate multiple factors (measurement quality, environmental context, UE mobility state). These parameter changes enable intelligent decision-making about when to activate neural network processing, optimizing the balance between positioning accuracy and system resource consumption.
2Measurement precision
If multiple neural network functions are aggregated and processed, then positioning accuracy is improved, but signaling overhead increases
Solution Approach 1:
The patent extracts and processes only the essential triggering criteria and measurement data needed for positioning, rather than transmitting all raw data. By selectively extracting relevant information based on triggering criteria evaluation, the system reduces signaling overhead while maintaining the accuracy benefits of multiple neural network functions.
Solution Approach 2:
The system segments the positioning processing into discrete triggering events based on specific criteria. Instead of continuous aggregation of all neural network functions, processing is divided into separate triggered instances, each handling only the necessary functions based on current conditions. This segmentation reduces redundant signaling while preserving positioning accuracy.
3Adaptability or versatility
If neural network functions are triggered based on real-time conditions, then adaptability is improved, but processing time and complexity increase
Solution Approach 1:
The system performs preliminary evaluation of triggering criteria before activating neural network functions. By pre-defining triggering conditions and evaluating them in advance, the system prepares for selective processing without unnecessary delays. This preliminary action enables rapid response to changing conditions while avoiding the time cost of continuous processing.
Solution Approach 2:
The patent implements periodic evaluation of triggering criteria at defined intervals or events rather than continuous monitoring. This periodic approach maintains adaptability to operational conditions while reducing processing time and complexity by limiting evaluations to necessary moments, such as measurement updates or environmental changes.
Data Source
AI summary
In an aspect, a UE obtains information (e.g., UE-specific information) associated with a set of triggering criteria (e.g., from a server, a serving network, e.g., in conjunction with or separate from a set of neural network functions) for a set of neural network functions, the set of neural network functions configured to facilitate positioning measurement feature processing at the UE, the set of neural network functions being generated dynamically based on machine-learning associated with one or more historical measurement procedures. The UE obtains positioning measurement data associated with a location of the UE, and processes the positioning measurement data into a respective set of positioning measurement features based at least in part upon the positioning measurement data and at least one neural network function from the set of neural network functions that is triggered by at least one triggering criterion from the set of triggering criteria.