Wireless Positioning Settings Selected From Performance Statistics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for improvements in 5G NR technology to optimize wireless positioning systems, particularly in selecting and applying positioning model settings to enhance accuracy and efficiency in determining user equipment location.
Innovation Solution
A method and apparatus that involve receiving recommended positioning model statistics, selecting appropriate settings, measuring positioning signals, and calculating outputs using a positioning model to determine the location of user equipment, while also enabling the transmission of positioning reports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple positioning model settings are evaluated and selected based on performance statistics, then positioning accuracy is improved, but system complexity and processing time increase
Solution Approach 1:
The system performs preliminary evaluation of multiple positioning model settings offline to generate performance statistics and recommendations before actual positioning operations. This pre-computation stores optimal settings based on historical data, allowing the system to quickly select pre-vetted configurations during runtime without re-evaluating all options, thus improving accuracy while reducing real-time complexity
Solution Approach 2:
The system automatically generates performance statistics, evaluates different positioning models, and creates recommendations without manual intervention. The automated evaluation process compares multiple settings against ground truth data and generates optimal configuration recommendations, reducing the need for manual system configuration and expertise while maintaining high positioning accuracy
2Measurement precision
If multiple positioning model settings are evaluated and selected based on performance statistics, then positioning accuracy is improved, but processing time increases
Solution Approach 1:
The system performs comprehensive evaluation of positioning model settings in advance to generate performance statistics and recommendations. By pre-computing the optimal settings based on historical positioning data and ground truth comparisons, the system eliminates the need for time-consuming real-time evaluation, thus improving positioning accuracy without increasing processing time during actual operations
Solution Approach 2:
The system uses performance statistics and ground truth comparisons to provide feedback on positioning model effectiveness. This feedback mechanism identifies which settings perform best under different conditions and feeds this information back into the recommendation system, enabling continuous improvement of positioning accuracy while maintaining efficient processing through data-driven optimization
3Productivity
If AI/ML models are used to select optimal positioning settings, then positioning efficiency is improved, but computational requirements and system complexity increase
Solution Approach 1:
The system introduces an intermediary recommendation layer that sits between the complex AI/ML evaluation process and the actual positioning operations. This intermediary component translates complex model evaluations into simple, actionable recommendations that can be easily implemented, allowing the system to leverage powerful AI/ML capabilities while maintaining operational simplicity and reducing the burden on end systems
Solution Approach 2:
The system creates simplified copies or representations of complex positioning models in the form of performance statistics and recommendation rules. Instead of deploying full AI/ML models at every positioning point, the system generates condensed recommendation sets that capture the essential decision logic, enabling efficient positioning operations without the computational overhead of running complex models everywhere
Data Source
AI summary
A first wireless device, for example a user equipment (UE), a base station, a transmission reception point (TRP), or a location management function (LMF), may transmit a first set of recommended positioning statistics. A second wireless device, for example a UE, a base station, or a TRP, may receive the first set of recommended positioning model statistics. The second wireless device may select a second set of positioning model settings based on the received first set of recommended positioning model statistics. The second wireless device may receive a third set of positioning signals. The second wireless device may measure the third set of positioning signals based on the selected second set of positioning model settings. The second wireless device may calculate a fourth set of positioning outputs using a positioning model based on the measured third set of positioning signals and the selected second set of positioning model settings.