US 12,035,166 B2
Unsupervised WiFi-enabled device-user association for personalized location-based service
Han Zou, Berkeley, CA (US); Costas Spanos, Lafayette, CA (US); Yuxun Zhou, Chicago, IL (US); and Jianfei Yang, Singapore (SG)
Assigned to THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, Oakland, CA (US); and NANYANG TECHNOLOGICAL UNIVERSITY, Singapore (SG)
Appl. No. 17/056,940
Filed by THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, Oakland, CA (US); and NANYANG TECHNOLOGICAL UNIVERSITY, Singapore (SG)
PCT Filed May 23, 2019, PCT No. PCT/US2019/033782
§ 371(c)(1), (2) Date Nov. 19, 2020,
PCT Pub. No. WO2019/226910, PCT Pub. Date Nov. 28, 2019.
Claims priority of provisional application 62/675,485, filed on May 23, 2018.
Prior Publication US 2021/0136617 A1, May 6, 2021
Int. Cl. H04W 28/02 (2009.01); G16Y 10/75 (2020.01); H04L 67/50 (2022.01)
CPC H04W 28/0226 (2013.01) [H04L 67/535 (2022.05); H04W 28/0215 (2013.01); H04W 28/0236 (2013.01); G16Y 10/75 (2020.01)] 17 Claims
OG exemplary drawing
 
1. A mobile device and user association system, comprising:
a plurality of wireless routers each configured to execute software to enable it to capture data including a received signal strength (RSS) value and a media access controller (MAC) address for each of a plurality of mobile devices (MDs) from existing wireless fidelity (WiFi) traffic;
a SQL database configured to create a table for each MD and use the MAC address corresponding to each MD as the ID of the corresponding table, wherein each table includes historical location estimations in time-series; and
at least one server configured to receive the data including the RSS values and MAC addresses of the plurality of MDs from the plurality of wireless routers and the MD tables from the SQL database to estimate a location of each MD and generate historical location data of each MD, identify and filter out temporary MDs, classify each non-temporary MD as either a static device (SD) or a mobile phone (MP), and associate each of a plurality of users with each SD and MP,
wherein each of the plurality of wireless routers is further configured to provide wireless Internet access service to the plurality of MDs by constructing a WiFi LAN network within the indoor environment, and overhear data packets transmitted between the plurality of MDs and other wireless routers from the existing WiFi traffic,
wherein the data packets are generated by applications running on the plurality of MDs,
wherein the applications running on the plurality of MDs include at least one of the following: push notifications and email fetches,
wherein the at least one server is configured to classify non-temporary MDs as either an SD or an MP based at least in part on location variations and overnight presences of each MD, and
wherein the classifying includes calculating a location standard deviation threshold using the following equation:

OG Complex Work Unit Math
where (x, y) represents the mean of the location estimation.