AI ML Positioning Receiver for Flexible Carrier Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current positioning systems in communication networks face challenges in accurately determining the position of terminal devices using signals with varying carrier frequencies and durations, as well as those received with different resource elements, due to the complexity of aggregating and processing these diverse signals effectively.
Innovation Solution
An apparatus equipped with a processor and memory that converts and ranks signal samples into a common data format, accounting for missing entries and channel selectivity, and uses a machine learning model to generate positioning measurements, ensuring that the AI/ML positioning receiver can handle signals with variable bandwidth, duration, and carrier configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If signal samples with varying carrier frequencies and durations are aggregated for positioning, then positioning versatility and adaptability improve, but processing complexity and difficulty of measurement increase
Solution Approach 1:
The patent segments the complex positioning task into distinct processing stages: receiving signal samples with different parameters, converting them to a common data format, ranking the converted samples, and finally generating positioning measurements. This segmentation allows each stage to handle specific aspects independently, reducing overall processing complexity while maintaining versatility in handling diverse signal configurations
Solution Approach 2:
The patent introduces a common data format as an intermediary representation between the diverse input signal samples and the positioning measurement process. This intermediate format standardizes different carrier frequencies, durations, and resource elements into a unified structure that the machine learning model can process efficiently, thereby reducing processing complexity without sacrificing adaptability
2Reliability
If diverse signal samples with different resource elements are processed, then positioning reliability improves, but measurement precision and ease of operation deteriorate
Solution Approach 1:
The patent performs preliminary conversion of diverse signal samples into a common data format before the actual positioning measurement is taken. By pre-processing and standardizing the signals in advance, the system ensures that all subsequent measurements operate on uniformly formatted data, which maintains measurement precision while improving reliability through comprehensive use of diverse signal samples
Solution Approach 2:
The patent implements a ranking mechanism that provides feedback on the quality and relevance of converted signal samples. This feedback loop allows the system to selectively weight or prioritize certain samples over others based on their characteristics, thereby maintaining measurement precision while still leveraging the reliability benefits of diverse signal inputs
3Measurement precision
If machine learning models are used to generate positioning measurements from converted signal samples, then positioning accuracy improves, but computational requirements and device complexity increase
Solution Approach 1:
The patent segments the complex machine learning process into distinct phases: signal conversion to common format, ranking of samples based on quality metrics, and finally positioning measurement generation. This segmentation allows the system to use sophisticated machine learning models for accuracy while keeping each individual processing stage manageable and well-defined
Solution Approach 2:
The patent performs preliminary conversion and ranking of signal samples before feeding them to the machine learning model. By pre-processing the data into a standardized and ranked format, the system reduces the computational burden on the machine learning model itself, thereby improving positioning accuracy through better data quality while limiting the increase in device complexity
Data Source
AI summary
An apparatus comprising circuitry configured to: receive a plurality of signal samples, wherein at least two of the signal samples are received on different carrier frequencies or over different durations; convert the plurality of signal samples to a common data format that stores as entries the samples, a stored entry corresponding to a sample measured with a carrier frequency, a time, and a receive antenna; generate entries of the common data format that are missing due to a sample not being measured with a carrier frequency, time, and receive antenna; wherein the entries of the common data format are ranked, wherein a higher ranking entry is considered more relevant than a relatively lower ranking entry; and generate at least one positioning measurement with a machine learning model, based on the entries of the common data format and the ranking of the entries of the common data format.