Mining generalized spatial association rule

A system for mining a rule including spatial information and non-spatial information by using a SAR (Spatial Association Rule) mining tool, the system comprising:

• a computing system including at least one memory device and at least one processor connected to the memory device,
• wherein the computing system is configured to:
• construct an expanded spatial predicate transaction table for reference spatial objects and a generalized taxonomy for task-relevant spatial objects, the expanded spatial predicate transaction table including both spatial predicates of the reference spatial objects and non-spatial information associated with the reference spatial objects, the generalized taxonomy including:
• non-spatial information associated with the task-relevant spatial objects, a concept classification of the task-relevant spatial objects, and a mapping between the task-relevant spatial objects and non-spatial attributes representing the non-spatial information associated with the task-relevant spatial objects, the construct the generalized taxonomy including:
• create or read a table that that corresponds the task-relevant spatial objects to the non-spatial attributes associated with the task-relevant objects, the table further including values of the non-spatial attributes of the corresponding task-relevant spatial objects;
• and
• create the concept classification of the task-relevant spatial objects as a data structure, the create the concept classification including:
• create at least one concept node from the table, a concept node representing a combination of a non-spatial attribute and a corresponding value;
• create at least one object node that corresponds to the task-relevant spatial objects;
• and
• connect the at least one concept node to the at least one object node by making a concept node a parent node of an object node;
• run the SAR mining tool with the constructed expanded spatial predicate transaction table and the generalized taxonomy;
• generate, by the SAR mining tool, one or more generalized spatial association rules for the reference spatial objects, the one or more generalized spatial association rules having a support value above a first threshold, the one or more generalized spatial association rules having a confidence value above a second threshold, the support value indicating a percentage of occurrences of the individual reference spatial objects, the confidence value indicating a minimum percentage of transactions that involve the individual reference spatial objects, the one or more generalized spatial association rules including the spatial information and non-spatial information, associated with both the reference spatial objects and the task-relevant spatial objects.

A computer program product for mining a rule including spatial information and non-spatial information by using a SAR (Spatial Association Rule) mining tool, the computer program product comprising a non-transitory storage device readable by a processing circuit and storing instructions run by the processing circuit for performing a method, the method comprising:

• constructing, by using the processing circuit, an expanded spatial predicate transaction table for reference spatial objects and a generalized taxonomy for task-relevant spatial objects, the expanded spatial predicate transaction table including both spatial predicates of the reference spatial objects and non-spatial information associated with the reference spatial objects, the generalized taxonomy including non-spatial information associated with the task-relevant spatial objects, a concept classification of the task-relevant spatial objects, and a mapping between the task-relevant spatial objects and non-spatial attributes representing the non-spatial information associated with the task-relevant spatial objects, the constructing the generalized taxonomy including:
• creating or reading a table that corresponds the task-relevant spatial objects to the non-spatial attributes associated with the task-relevant objects, the table further including values of the non-spatial attributes of the corresponding task-relevant spatial objects;
• and
• creating the concept classification of the task-relevant spatial objects as a data structure, the creating the concept classification including:
• creating at least one concept node from the table, a concept node representing a combination of a non-spatial attribute and a corresponding value;
• creating at least one object node that corresponds to the task-relevant spatial objects;
• and
• connecting the at least one concept node to the at least one object node by making a concept node a parent node of an object node;
• running, by using the processing circuit, the SAR mining tool with the constructed expanded spatial predicate transaction table and the generalized taxonomy;
• generating, by the SAR mining tool, one or more generalized spatial association rules for the reference spatial objects, the one or more generalized spatial association rules having a support value above a first threshold, the one or more generalized spatial association rules having a confidence value above a second threshold, the support value indicating a percentage of occurrences of the reference spatial objects, the confidence value indicating a minimum percentage of transactions that involve the reference spatial objects, the one or more generalized spatial association rules including the spatial information and non-spatial information, associated with both the reference spatial objects and the task-relevant spatial objects.