Adaptive spatial density based clustering

A system comprising:

• one or more processors;
• and
• a memory storing instructions that, when executed by the one or more processors, configure the system to perform operations comprising:
• accessing historical location information of a user;
• identifying, using the one or more processors, a plurality of visit points based on the historical location information;
• clustering, using the one or more processors, the plurality of visit points into a plurality of clusters, the clustering being performed based on a density threshold;
• based on determining that one of the clusters includes a number of visit points exceeding a maximum cluster size, repeating the clustering with an increased density threshold;
• and
• based on determining that none of the clusters includes a number of visit points exceeding the maximum cluster size, identifying, using the one or more processors, at least one of the clusters as a habitual place of the user;
• receiving from a client device associated with the user, via a wireless communication, an electronic communication containing current location information of the user;
• identifying a current location of the user based on the current location information;
• and
• based on determining that the current location of the user is in a neighborhood of the cluster identified as the habitual place of the user, determining that the user is at the habitual place of the user,
• wherein the habitual place is defined by a bounding box including all the visit points included in the cluster associate with the habitual place, and
• wherein determining that the current location of the user is in a neighborhood of the cluster comprises:
• computing a probability of the user being at the habitual place based on a joint probability of a latitude and a longitude of the current location of the user being included in the bounding box, and
• determining that the computed probability exceeds a preset threshold.

A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations comprising:

• accessing historical location information of a user;
• identifying a plurality of visit points based on the historical location information;
• clustering the plurality of visit points into a plurality of clusters, the clustering being performed based on a density threshold;
• based on determining that one of the clusters includes a number of visit points exceeding a maximum cluster size, repeating the clustering with an increased density threshold;
• and
• based on determining that none of the clusters includes a number of visit points exceeding the maximum cluster size, identifying at least one of the clusters as a habitual place of the user;
• receiving from a client device associated with the user, via a wireless communication, an electronic communication containing current location information of the user;
• identifying a current location of the user based on the current location information;
• and
• based on determining that the current location of the user is in a neighborhood of the cluster identified as the habitual place of the user, determining that the user is at the habitual place of the user,
• wherein the habitual place is defined by a bounding box including all the visit points included in the cluster associate with the habitual place, and
• wherein determining that the current location of the user is in a neighborhood of the cluster comprises:
• computing a probability of the user being at the habitual place based on a joint probability of a latitude and a longitude of the current location of the user being included in the bounding box, and
• determining that the computed probability exceeds a preset threshold.