Method and apparatus for spatial aggregation for location-based services

An apparatus comprising:

• at least one processor;
• and
• at least one memory including computer program code for one or more programs,
• the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
• determine a plurality of partitions of a geographic area;
• determine a set of destinations that is common to a first partition and a second partition of the plurality of partitions, wherein the set of destinations are associated with a plurality of trips originating from the first partition, the second partition, or a combination thereof;
• determine a statistical property of the plurality of trips to any of the set of destinations from the first partition, the second partition, or a combination thereof;
• determine a number of inter-partition trips between the first partition and the second partition;
• merge the first partition with the second partition into the traffic analysis zone based on the statistical property and based on determining that the number of inter-partition trips is below a threshold value, wherein the traffic analysis zone represents a reduced-dimensionality feature for training a machine learning model;
• train the machine learning model using the traffic analysis zone as a training input to generate a trained machine learning model, wherein training using the traffic analysis zone reduces memory and processing resources used by one or more processors compared to training the machine learning model using the first partition and the second partition;
• generate, by the trained machine learning model, an estimated time of arrival (ETA) for a query trip;
• and
• transmit a control command based on the generated ETA to a user device, the control command configured to cause a modification of a user interface on the user device.

A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:

• determining a plurality of partitions of a geographic area;
• determining a set of destinations that is common to a first partition and a second partition of the plurality of partitions, wherein the set of destinations are associated with a plurality of trips originating from the first partition, the second partition, or a combination thereof;
• determining a statistical property of the plurality of trips to any of the set of destinations from the first partition, the second partition, or a combination thereof;
• determining a number of inter-partition trips between the first partition and the second partition;
• merging the first partition with the second partition into the traffic analysis zone based on the statistical property and based on determining that the number of inter-partition trips is below a threshold value, wherein the traffic analysis zone represents a reduced-dimensionality feature for training a machine learning model;
• training the machine learning model using the traffic analysis zone as a training input to generate a trained machine learning model, wherein training using the traffic analysis zone reduces memory and processing resources used by one or more processors compared to training the machine learning model using the first partition and the second partition;
• generating, by the trained machine learning model, an estimated time of arrival (ETA) for a query trip;
• and
• transmitting a control command based on the generated ETA to a user device, the control command configured to cause a modification of a user interface on the user device.