| CPC G06N 5/04 (2013.01) [G06F 16/285 (2019.01); G06F 16/29 (2019.01); G06N 20/00 (2019.01); H04L 67/01 (2022.05); H04L 67/52 (2022.05); G06N 3/044 (2023.01); G06N 3/08 (2013.01); G06N 20/20 (2019.01)] | 20 Claims |
|
1. A method comprising:
accessing, from a database, historical geolocation data of one or more client devices of a first user, the historical geolocation data comprising a plurality of location points;
extracting an attendance record of the first user at a labeled place for each location point of the plurality of location points;
determining, that the first user is at the labeled place, based on current geolocation data of the first user;
determining a predicted departure time of the first user from the labeled place using a trained machine learning model trained on the attendance record of the labeled place, the trained machine learning model trained to generate a departure threshold value, wherein the predicted departure time is a future time at which a probability that the first user is at the labeled place falls below the departure threshold value;
in response to determining the predicted departure time of the first user from the labeled place, causing display on a second client device of a second user, a graphical user interface comprising a map depicting a selectable user interface element indicating the labeled place and the predicted departure time of the first user from the labeled place; and
in response to a selection of the selectable user interface element, initiating or resuming a communication session between the first user and the second user via a messaging system.
|