| CPC G06Q 30/0631 (2013.01) [G01C 21/3679 (2013.01); G06N 20/00 (2019.01); G16H 20/60 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/70 (2018.01); H04L 67/306 (2013.01); H04W 4/023 (2013.01); H04W 4/029 (2018.02)] | 20 Claims |

|
1. An apparatus for geographically tracking nourishment selection, the apparatus comprising:
at least a computing device; and
a memory communicatively connected to the at least a computing device, the memory containing instructions configuring the at least a computing device to:
receive a location associated with a user's commute from a user device;
determine a nourishment provider within the location, wherein the nourishment provider is associated with a plurality of nourishment possibilities;
locate a performance character associated with the user, wherein the performance character contains a nourishment score and at least a behavior relating to the plurality of nourishment possibilities, wherein the nourishment score is calculated using a nourishment machine-learning process as a function of a nourishment behavioral target and a logged nourishment entry, wherein training the nourishment machine-learning process comprises:
using a first training set correlating at least a logged nourishment entry as an input and at least a nourishment score as an output;
generate a user profile wherein the user profile comprises the location, the nourishment provider, and the performance character;
generate a selector machine-learning model, wherein the selector machine-learning model is trained using a second training set configured to correlate at least a user profile input to a nourishment possibility index output, wherein the nourishment possibility index comprises an indication identifying an impact of a nourishment possibility on the calculated nourishment score;
grade, using the selector machine-learning model, the plurality of nourishment possibilities associated with the nourishment provider using a plurality of corresponding nourishment possibility indexes;
receiving a user selection comprising at least a selection of one or more nourishment possibilities of the plurality of nourishment possibilities;
logging a user entry comprising a user preference for the user selection;
retraining the selector machine-learning model with subsequent training data comprising the user selection correlator to the user preference, wherein the user preference comprises data indicating a tolerability of the user selection;
generating the nourishment possibility index output; and
a graphical user interface configured to display the plurality of graded nourishment possibilities.
|