Semantic Indoor Positioning Using Wi-Fi Signal Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing indoor positioning systems (IPS) face challenges with high deployment costs and low accuracy due to their reliance on sensor-based and distance-based approaches, which are either costly or inaccurate in noisy indoor environments.
Innovation Solution
The method employs a semantic indoor positioning system that uses reference areas as 'satellites' within a building, leveraging existing network assets by generating vectors of distance scores based on wireless radio signal strength indications (RSSI) and applying Bayesian models to determine the most probable location of a mobile device, thereby improving accuracy and reducing deployment costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based approaches (RFID, BLUETOOTH) are used for indoor positioning, then positioning accuracy is improved, but deployment cost increases
Solution Approach 1:
The patent creates a semantic map that copies the spatial relationships and signal characteristics of the physical environment. Instead of deploying physical sensors throughout the building, the system creates a digital representation (semantic map) that captures the essential positioning information, allowing accurate location determination through software processing of existing Wi-Fi signals.
Solution Approach 2:
The patent replaces the mechanical/sensor-based positioning system with an information-processing system. Instead of using RFID readers or BLUETOOTH sensors physically deployed throughout the building, the system uses semantic processing of Wi-Fi signal data to determine position, substituting physical sensing infrastructure with computational analysis.
2Device complexity
If distance-based approaches (triangulation, trilateration) are used for indoor positioning, then deployment cost is reduced by using existing network assets, but positioning accuracy deteriorates in noisy indoor environments
Solution Approach 1:
The patent transforms the raw Wi-Fi signal data into semantic features that capture the essential characteristics of the radio environment. By changing the parameters from simple signal strength measurements to semantic descriptors of spatial relationships and signal patterns, the system achieves both low deployment cost (using existing Wi-Fi infrastructure) and high positioning accuracy (through sophisticated semantic analysis).
Solution Approach 2:
The patent introduces a semantic map as an intermediary between the raw Wi-Fi signals and the positioning calculation. This semantic representation acts as a mediator that translates the noisy physical signals into meaningful spatial information, enabling accurate positioning without direct reliance on complex distance measurements.
3Device complexity
If simple Wi-Fi signal strength (RSSI) matching is used for positioning, then deployment cost is reduced, but positioning accuracy deteriorates due to signal noise and variability
Solution Approach 1:
The patent performs preliminary semantic processing of the Wi-Fi signal data before using it for positioning. By pre-processing the signals to extract semantic features and build a semantic map during a survey phase, the system prepares the data in advance to filter out noise and variability, enabling more accurate positioning when actual location determination is needed.
Solution Approach 2:
The patent replaces direct RSSI matching with semantic processing of signal characteristics. Instead of comparing raw signal strength values directly, the system uses semantic analysis to interpret the signals in terms of spatial relationships and environmental features, substituting simple threshold matching with intelligent pattern recognition.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances location accuracy and reduces deployment costs by using robust distance scores and existing network assets, providing a more stable and effective indoor positioning solution compared to traditional methods.
Implementation Method 1
A scan of a plurality of wireless radio signals is obtained by the mobile device of a user at an unknown location in the building. The plurality of wireless radio signals is generated by a plurality of wireless access points (WAPs).
Implementation Method 2
A plurality of distance scores for the plurality of reference areas is calculated, each distance score being calculated by applying a Bayesian model to the retrieved set of probabilities for the corresponding reference area.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for locating a mobile device inside a building by using a plurality of reference areas in the building as satellites. A scan is obtained by the mobile device at an unknown location in the building. The scan includes a plurality of detected WAPs with a corresponding RSSI for each detected WAP. The method to improve accuracy of a semantic indoor positioning system by generating a vector of distance scores based on the scan for comparison with vectors of survey distance scores corresponding to the reference areas. The method includes arranging the detected WAPs into an ordered list, extracting a set of WAP tuples from the ordered list, retrieving a set of probabilities for each reference area, calculating a distance score for each reference area, generating the vector of distance scores, and comparing the vector of distance scores with each of the vectors of survey distance scores.