Indoor Outdoor Wireless Terminal Location Probability Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location determination systems in wireless networks struggle to accurately differentiate between indoor and outdoor locations of a wireless terminal, particularly when multiple candidate locations are identified, leading to inefficiencies in emergency response and tracking scenarios.
Innovation Solution
The system employs pattern matching techniques using tell-tale indicators such as signal strength patterns, neighbor cells, and speed classification to estimate the probability of a wireless terminal being indoors or outdoors, applying machine learning to weight these factors and eliminate inappropriate candidate locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pattern matching techniques are used to analyze signal strengths from multiple antennas, then location estimation can be performed, but the system cannot accurately differentiate between indoor and outdoor locations when multiple candidate locations are identified
Solution Approach 1:
The patent segments the location estimation process into two distinct phases: first identifying candidate locations based on signal strength patterns, then classifying each candidate as indoor or outdoor using separate classification techniques. This segmentation allows the system to maintain multiple candidate locations while adding differentiation capability without compromising the initial location estimation accuracy.
Solution Approach 2:
The patent introduces an intermediary classification step that acts as a mediator between signal strength analysis and final location determination. This classification layer uses additional indicators (signal strength variability, neighbor cell patterns, speed classifications) to differentiate indoor from outdoor environments, thereby recovering the lost indoor/outdoor information without discarding the candidate locations generated by pattern matching.
2Measurement precision
If all candidate locations are evaluated to ensure accurate location determination, then location accuracy is maintained, but computational resources and time are excessively consumed
Solution Approach 1:
The patent performs preliminary classification of candidate locations as indoor or outdoor before final location determination. By evaluating indoor/outdoor probability early in the process, the system can eliminate unlikely candidates and focus computational resources on the most probable locations, thereby maintaining accuracy while improving productivity.
Solution Approach 2:
Instead of evaluating all candidate locations with equal depth, the patent applies partial evaluation based on indoor/outdoor classification. Locations with high probability of being in the correct environment type receive more thorough evaluation, while low-probability locations are discarded with minimal processing, achieving accurate results with reduced computational effort.
3Measurement precision
If additional factors such as signal strength variability, neighbor cells, and speed classifications are incorporated, then indoor/outdoor differentiation improves, but system complexity increases
Solution Approach 1:
The patent makes the classification system universal by using multiple indicators (signal strength variability, neighbor cell patterns, speed classifications) that serve the same function of differentiating indoor from outdoor environments. These multi-functional indicators can be applied across different wireless network configurations and location scenarios, improving classification accuracy without proportionally increasing system complexity through modular design.
Solution Approach 2:
The patent changes parameters such as signal strength thresholds, neighbor cell counts, and speed classification boundaries to optimize the balance between classification accuracy and system complexity. By adjusting these parameters based on network conditions and requirements, the system achieves high indoor/outdoor differentiation accuracy while maintaining manageable complexity through parameter optimization rather than structural complexity.
Data Source
AI summary
Methods for generating more accurate location estimates are based on indicative factors. The factors are gleaned from wireless signals that were received by a wireless terminal and from other network-specific data. Each factor is probative of whether the wireless signals were received by the wireless terminal: (i) indoors versus outdoors, and/or (ii) “above-the-clutter” versus “below-the-clutter” of ambient wireless signals, and/or (iii) while moving at a certain speed classification, e.g., stationary/pedestrian versus vehicular speeds. Each factor tends to prove or disprove the particular characteristic. The result is an estimated probability, such as the probability that the wireless terminal received the signals indoors. The estimated probability is applied to the analysis of candidate locations, eliminating some candidates from further consideration. This enables computational resources to focus on the remaining higher-likelihood candidate locations and provides improved accuracy in the location estimate.