The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 19, 2023

Filed:

Dec. 30, 2020
Applicant:

Psj International Ltd., Tortola, VG;

Inventors:

Chung-Yuan Chen, Tainan, TW;

Alexander I Chi Lai, Taipei, TW;

Ruey-Beei Wu, Taipei, TW;

Assignee:

PSJ INTERNATIONAL LTD., Tortola, VG;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G05D 1/02 (2020.01); H04W 84/18 (2009.01); G06F 16/906 (2019.01); G06N 20/00 (2019.01); G06F 16/907 (2019.01); H04W 4/024 (2018.01); G01C 21/00 (2006.01); G01C 21/20 (2006.01); G01S 13/02 (2006.01); H04W 4/02 (2018.01); H04W 64/00 (2009.01); H04W 84/12 (2009.01); G06F 18/214 (2023.01); H04W 72/00 (2023.01); G06V 20/70 (2022.01); G06V 20/10 (2022.01); H04W 72/29 (2023.01);
U.S. Cl.
CPC ...
G05D 1/0285 (2013.01); G01C 21/005 (2013.01); G01C 21/206 (2013.01); G01S 13/0209 (2013.01); G05D 1/0248 (2013.01); G05D 1/0257 (2013.01); G05D 1/0282 (2013.01); G06F 16/906 (2019.01); G06F 16/907 (2019.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06V 20/10 (2022.01); G06V 20/70 (2022.01); H04W 4/023 (2013.01); H04W 4/024 (2018.02); H04W 4/025 (2013.01); H04W 64/003 (2013.01); H04W 72/29 (2023.01); H04W 84/12 (2013.01); H04W 84/18 (2013.01);
Abstract

A positioning system and a positioning method based on WI-FI® fingerprints are provided. The method includes obtaining positioning map data; performing a clustering processing process to allocate collected data into reference groups in a target area according to collection coordinates; calculating metadata of WI-FI® access points; serving the metadata as a filtering condition related to an identification rate, and extracting WI-FI® fingerprint data with relatively high identification rate; establishing a machine learning model for estimating a relevant position based on the fingerprint data of the WI-FI® access points, and training the machine learning model with extracted WI-FI® fingerprint data and corresponding spatial coordinates to generate a trained machine learning model; configuring a communication module to receive WI-FI® fingerprint data collected by a wireless device; and configuring the trained machine learning model to estimate, according to the WI-FI® fingerprint data collected, the relevant position.


Find Patent Forward Citations

Loading…