US 12,443,926 B1
Machine learning based systems and methods for automatically classifying digital calendar events
Vijay D'Silva, Scarsdale, NY (US); and Tobias Bitzer, Stuttgart (DE)
Assigned to MCKINSEY & COMPANY, INC., New York, NY (US)
Filed by MCKINSEY & COMPANY, INC., New York, NY (US)
Filed on Feb. 2, 2022, as Appl. No. 17/591,124.
Int. Cl. G06Q 10/1093 (2023.01)
CPC G06Q 10/1095 (2013.01) 18 Claims
OG exemplary drawing
 
1. A machine learning based system configured to automatically classify digital calendar events, the machine learning based system comprising:
one or more processors;
a computer memory communicatively coupled to the one or more processors;
a calendar tracking application (app) stored in the computer memory and comprising computing instructions configured to execute on the one or more processors; and
a machine learning model stored on the computer memory and accessible to the calendar tracking app, the machine learning model trained with a set of training data comprising: (1) a plurality of predefined meeting categories as dependent variables, each dependent variable having a category label, and (2) a plurality of digital calendar events as independent variables, each independent variable having a digital calendar event description, wherein the machine learning model is further trained to classify each of the plurality digital calendar events into at least one of the predefined meeting categories based on a prediction that a given digital calendar event of the plurality digital calendar events corresponds to a given category label of the plurality of predefined meeting categories,
wherein the computing instructions of the calendar tracking app, when executed by the one or more processors, cause the one or more processors to:
receive a first set of digital calendar data of a first period, the first set of digital calendar data comprising a first set of calendar events of a user, each calendar event having a digital calendar event description,
generate, with the machine learning model by inputting the first set of calendar events of the user, classification data, wherein the classification data comprises the first set of calendar events of the user classified according to one or more of the predefined meeting categories,
generate a data view based on the classification data, wherein the data view is generated as a lightweight data object transferable across a computer network and renderable by the calendar tracking app executing locally on a computing device, and
provide, over the computer network, the data view to the computing device for rendering a graphic user interface (GUI) on a display of the computing device.