18257115. ENHANCED FINGERPRINT POSITIONING simplified abstract (Nokia Technologies Oy)
Contents
ENHANCED FINGERPRINT POSITIONING
Organization Name
Inventor(s)
ENHANCED FINGERPRINT POSITIONING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18257115 titled 'ENHANCED FINGERPRINT POSITIONING
Simplified Explanation
The patent application relates to improving fingerprint positioning in a wireless communication network. The method involves training a positioning model using historical measurements and regions. The model uses the measurements as input and the regions as output to obtain parameter sets of Gaussian distributions. These distributions indicate the probabilities of a device being positioned in certain regions, corresponding to different non-line of sight levels. This improves the accuracy of the fingerprint positioning method.
- The method involves obtaining a set of training data comprising historical measurements and regions.
- The historical measurements are associated with a device within a region when the measurement is obtained.
- The positioning model is trained using the historical measurements as input and the regions as output.
- The model obtains parameter sets of Gaussian distributions, indicating probabilities of a device being positioned in the regions.
- The parameter sets correspond to different non-line of sight levels of the regions.
Potential Applications
- Wireless communication networks
- Location-based services
- Indoor positioning systems
Problems Solved
- Inaccurate fingerprint positioning in wireless communication networks
- Difficulty in determining the position of devices in non-line of sight scenarios
Benefits
- Improved accuracy of fingerprint positioning method
- Enhanced performance of location-based services
- Better positioning of devices in indoor environments
Original Abstract Submitted
Embodiments of the present disclosure relate to fingerprint positioning in a wireless communication network. A method for establishing a positioning model comprises: obtaining, at a first device, a set of training data comprising historical measurements and historical regions, a historical measurement being associated with a second device, the second device being within one of the historical regions when the historical measurement is obtained; and training the positioning model by using the historical measurements as input of the positioning model and the historical regions as output of the positioning model to obtain parameter sets of Gaussian distributions of the positioning model, the Gaussian distributions indicating probabilities that a third device is positioned in the historical regions, and the parameter sets corresponding to respective non-light of sight levels of the historical regions. In this way, the positioning accuracy of fingerprint positioning method can be greatly improved.
