Wow, not only is the article title completely fake, but they even linked to the wrong patent.<p>Real patent is here: <a href="http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=/netahtml/PTO/srchnum.html&r=1&f=G&l=50&s1=20180157984.PGNR.inpu" rel="nofollow">http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=...</a><p>It looks like the main data points the system uses are time and location occurrence with previous outings, and characteristics of how they interact with the app, specifically text input.