Automatic extraction of user mobility behaviors and interaction preferences using spatio-temporal data

A computer readable storage medium storing a program of instructions executable by a machine to perform a method to automatically determine user mobility behaviors and interaction preferences using spatio-temporal data and engage users, the method comprising:

• receiving spatio temporal data comprising location data as a function of time, app interaction data as a function of time, and geographic map data comprising geographic coordinates;
• constructing a user trajectory graph based on the spatio temporal data;
• determining mobility pattern based on the user trajectory graph;
• deriving features from the mobility patterns;
• clustering users into groups, wherein the users in a same group have similar feature values associated with the features, and the users in different groups have different feature values, whether a feature value is similar or different determined based on meeting a similarity threshold;
• identifying personas and location sets based on the clustering;
• constructing a distribution model, wherein an outcome indicates a preference for a particular time bin on a particular day for a particular location;
• and
• monitoring user device's location and responsive to detecting that the user device is at the particular location at a particular time estimated as a preferred time and location, pushing content to the user device.

A system to automatically determine user mobility behaviors and interaction preferences using spatio-temporal data and engage users, comprising:

• one or more processor communicatively couple to one or more storage devices,
• one or more of the processors operable to receive spatio temporal data comprising location data as a function of time, app interaction data as a function of time, and geographic map data comprising geographic coordinates from one or more of the storage devices,
• one or more of the processors further operable to construct a user trajectory graph based on the spatio temporal data,
• one or more of the processors further operable to determine mobility pattern based on the user trajectory graph,
• one or more of the processors further operable to derive features from the mobility patterns,
• one or more of the processors further operable to cluster users into groups, wherein the users in a same group have similar feature values associated with the features, and the users in different groups have different feature values, whether a feature value is similar or different determined based on meeting a similarity threshold,
• one or more of the processors further operable to identify personas and location sets based on the clustering,
• one or more of the processors further operable to construct a distribution model, wherein an outcome indicates a preference for a particular time bin on a particular day for a particular location,
• one or more of the processors further operable to monitor user device's location and responsive to detecting that the user device is at the particular location at a particular time estimated as a preferred time and location, one or more of the processors further operable to push content via a network to the user device.