US 12,314,978 B2
Targeted advertisement ranking using machine learning
Alexandre Miguel Cachapuz Santos Fontoura, Dublin (IE); Arshiya Tripathy, Dublin (IE); and Fiachra M. O'Donoghue, Cork (IE)
Assigned to VIASAT INC., Carlsbad, CA (US)
Filed by VIASAT, INC., Carlsbad, CA (US)
Filed on Feb. 23, 2023, as Appl. No. 18/113,323.
Prior Publication US 2024/0289839 A1, Aug. 29, 2024
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0251 (2023.01)
CPC G06Q 30/0251 (2013.01) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
executing a learn-to-rank algorithm to train at least one machine learning model on a training dataset that includes electronic advertisements, the electronic advertisements having associated scores and the associated scores characterizing a relevancy between the electronic advertisements and a defined query, wherein the executing includes training the at least one machine learning model including:
inputting the training dataset to the at least one machine learning model, the training data set generated from input data from one or more data pipelines communicatively coupled to one or more advertisement analysis devices that query the one or more data pipelines for a defined duration;
comparing, to the training data set, one or more output datasets from the at least one machine learning model; and
based on the comparing, adjusting one or more weights of the at least one machine learning model to obtain a trained machine learning model; and
applying the trained machine learning model to rank a set of electronic advertisements based on at least one feature vector, the at least one feature vector characterizing input data that includes flight details of an aircraft, wherein the trained machine learning model is applied while the aircraft is in transit, and wherein the feature vector is defined or re-defined while the aircraft is in transit.