Hierarchical region of interest clustering

A system, comprising:

• a processor;
• and
• a memory to store computer-executable instructions that, in response to execution by the processor, cause the system to at least:
• obtain search data indicating regions of interest;
• generate a first graph at a first resolution, the first graph comprising:
• a node for each region of interest of the regions of interest associated with the first resolution, and
• an edge between each node, wherein the edge is weighted based on a number of times that each region of interest was searched within a single session;
• cluster a first subset of nodes associated with the first resolution into a first cluster based on a clustering metric;
• and
• generate output comprising a recommendation relating to the search data based on the first cluster.

A computer-implemented method, comprising:

• obtaining search data indicating regions of interest;
• generating a first graph at a first resolution, the first graph comprising:
• a node for each region of interest of the regions of interest associated with the first resolution, and
• an edge between each node, wherein the edge is weighted based on a co-occurrence of each region of interest within the search data;
• clustering a first subset of nodes associated with the first resolution into a first cluster based on a clustering metric;
• and
• generating output comprising search data associated with the first cluster.

A non-transitory computer-readable medium storing computer-executable instructions that, when executed by a processor of a computing device, cause the computing device to at least:

• for a defined set of regions of interest, generate a first graph at a first resolution, the first graph comprising:
• a node for each region of interest associated with the first resolution, and
• an edge between each node, wherein the edge is weighted based on a co-occurrence of each region of interest within the defined set of regions of interest;
• and
• output a first subset of nodes associated with the first resolution, the first subset of nodes corresponding to a first cluster based on a clustering metric.