CPC G06F 3/0483 (2013.01) [G06F 3/04842 (2013.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01)] | 13 Claims |
1. A method for application navigation recommendations using machine learning, comprising:
determining one or more pages accessed by a user within an application via a user interface;
generating an input vector comprising one or more numerical values quantifying an amount of data the user entered into the one or more pages;
providing the input vector to a trained machine learning model based on the one or more pages accessed by the user, wherein the trained machine learning model was trained using a training data set comprising two or more training data instances that relate to a single set of pages accessed by a respective user, wherein each of the two or more training data instances comprises a vector having a same number of elements, and wherein a given page of the single set of pages is indicated in a label of a first training data instance of the two or more training data instances and indicated in input features of a second training data instance of the two or more training data instances;
receiving, as an output from the trained machine learning model based on the input vector, one or more predicted pages, wherein the one or more predicted pages are within the application and different from the one or more pages accessed by the user;
displaying, in the user interface, within or adjacent to a currently displayed page of the one or more pages accessed by the user, one or more user interface elements recommending the one or more predicted pages to the user;
receiving a selection of a given user interface element of the one or more user interface elements; and
navigating within the user interface, based on the selection, to a given page of the one or more predicted pages that corresponds to the given user interface element.
|