UE Positioning Neural Network Triggering for Accuracy and Power Balance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently utilizing neural network functions for accurate positioning of user equipment (UE) due to the lack of dynamic and context-aware triggering mechanisms, leading to suboptimal performance in diverse environments and network conditions.
Innovation Solution
A method and system for dynamically generating and triggering neural network functions based on machine-learning algorithms, utilizing a set of triggering criteria to select appropriate neural network functions for UE positioning, including UE and base station features, and integrating these functions to determine precise location estimates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural network functions are continuously executed for positioning measurement processing, then positioning accuracy is improved, but energy consumption increases
Solution Approach 1:
The patent implements periodic triggering of neural network functions based on specific criteria rather than continuous execution. The network device or terminal device determines whether to trigger positioning measurement feature processing by evaluating triggering criteria (such as position change thresholds, time intervals, or event-based conditions), thereby executing neural network operations periodically or event-driven instead of continuously, which reduces energy consumption while maintaining positioning accuracy when needed
Solution Approach 2:
The patent dynamically adjusts triggering parameters such as position change thresholds, time interval thresholds, and measurement feature selection based on current conditions. By changing these parameters adaptively, the system optimizes the balance between positioning accuracy and energy consumption - using more aggressive triggering criteria when accuracy is prioritized and more conservative criteria when energy savings are needed
2Measurement precision
If multiple neural network functions are executed simultaneously for comprehensive positioning processing, then positioning accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent extracts and processes only the most relevant positioning measurement features based on triggering criteria and current conditions. Instead of executing all available neural network functions simultaneously, the system selectively triggers specific functions that are most appropriate for the current scenario, thereby reducing processing complexity while maintaining positioning accuracy through targeted feature processing
Solution Approach 2:
The patent segments the positioning processing into multiple independent neural network functions that can be selectively triggered. Each neural network function handles specific aspects of positioning measurement (such as different feature types or processing stages), allowing the system to activate only the necessary segments based on current conditions rather than running the entire processing pipeline, thus reducing overall complexity
3Measurement precision
If positioning measurement processing is performed frequently to maintain accurate location estimates, then positioning accuracy is improved, but time consumption increases
Solution Approach 1:
The patent implements periodic or event-driven triggering of positioning measurement processing based on time interval thresholds and specific conditions. Instead of continuous processing, the system evaluates whether triggering criteria are met (such as time elapsed since last measurement, position change detection, or specific events) before executing neural network functions, thereby reducing time consumption while maintaining positioning accuracy through strategically timed measurements
Solution Approach 2:
The patent performs preliminary evaluation of triggering criteria before executing positioning measurement processing. The system checks conditions such as time intervals, position change thresholds, and measurement feature availability in advance to determine whether full processing is needed, allowing it to skip unnecessary processing steps and reduce overall time consumption while ensuring accuracy when conditions warrant it
Data Source
AI summary
In an aspect, a UE obtains information (e.g., UE-specific information, etc.) associated with a set of triggering criteria 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 procedure, obtains positioning measurement data associated with a location of the UE, and determines a positioning estimate for the UE 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.