Creation of Attribute Combination Databases
A method and system are presented in which the attributes associated with individuals having a query attribute of interest (query-attribute-positive individuals) are compared against attributes associated with individuals not having the query attribute of interest (query-attribute-negative individuals) to create to create a compilation of attribute combinations that co-occur with the query attribute.
1 . A computer based method for compiling attribute combinations, comprising:
a) accessing a query attribute;
b) accessing attributes associated with query-attribute-positive individuals and attributes associated with query-attribute-negative individuals;
c) selecting a query-attribute-positive individual;
d) storing attributes associated with the query-attribute-positive individual that are not associated with a portion of the query-attribute-negative individuals, to create a set of candidate attributes; and
e) storing combinations of the candidate attributes and frequencies of occurrence of those combinations for the query-attribute-positive individuals and the query-attribute-negative individuals, to create a compilation of attribute combinations that co-occur with the query attribute.
2 . The computer based method of claim 1 , further comprising:
f) storing statistical results that are based on the frequencies of occurrence and indicate strength of association of each combination with the query attribute.
3 . The computer based method of claim 1 , further comprising:
f) repeating steps (c)-(e) for successive query-attribute-positive individuals.
4 . The computer based method of claim 1 , further comprising:
f) repeating steps (a)-(e) for a succession of query attributes.
5 . The computer based method of claim 1 , further comprising:
f) eliminating attribute combinations from the compilation based on the frequencies of occurrence.
6 . The computer based method of claim 1 , further comprising:
f) ranking the attribute combinations based on the frequencies of occurrence.
7 . The computer based method of claim 2 , further comprising:
g) ranking the attribute combinations based on the statistical results.
8 . The computer based method of claim 2 , further comprising:
g) eliminating attribute combinations from the compilation that do not meet one or more statistical requirements.
9 . The computer based method of claim 1 , further comprising:
f) transmitting one or more attributes, attribute combinations, frequencies of occurrence as output.
10 . The computer based method of claim 1 , further comprising:
f) repeating steps (c)-(e) for successive query-attribute-positive individuals;
g) storing statistical results that are based on the frequencies of occurrence and indicate strength of association of each combination with the query attribute;
h) eliminating attribute combinations from the compilation that do not meet one or more statistical requirements;
i) ranking the attribute combinations based on the statistical results;
j) repeating steps (a)-(i) for a succession of query attributes; and
k) transmitting one or more attributes, attribute combinations, frequencies of occurrence and statistical results as output.
11 . The computer based method of claim 8 , wherein the one or more statistical requirements are selected from the group consisting of: greater than a minimum statistical value, less than a maximum statistical value, and statistical significance.
12 . The computer based method of claim 10 , wherein the one or more statistical requirements are selected from the group consisting of: greater than a minimum statistical value, less than a maximum statistical value, and statistical significance.
13 . The computer based method of claim 1 , wherein the query attribute can be a query attribute combination consisting of two or more attributes.
14 . The computer based method of claim 1 , wherein the query-attribute-positive individuals and the query-attribute-negative individuals constitute a population or subpopulation that is preselected based on having an association with one or more attributes.
15 . The computer based method of claim 1 , wherein the identity of one or more individuals is masked or anonymized.
16 . A computer based system for compiling attribute combinations, comprising:
a) a first data accessing subsystem for accessing a query attribute;
b) a second data accessing subsystem for accessing databases containing attributes associated with query-attribute-positive and attributes associated with query-attribute-negative individuals;
c) a data processing subsystem comprising:
i) a data comparison subsystem for identifying attributes associated with the query-attribute-positive individual that are not associated with a portion of the query-attribute-negative individuals;
ii) a statistical computing subsystem for calculating frequencies of occurrence of attribute combinations and statistical results indicating their strength of association with query attributes; and
d) a data storage subsystem for storing one or more attributes, attribute combinations, frequencies of occurrence, statistical results and individual identifiers, to create a compilation of attribute combinations that co-occur with the query attribute.
17 . The computer based system of claim 16 , wherein the data processing subsystem further comprises:
iii) an attribute elimination subsystem for eliminating attribute combinations from the compilation based on their frequencies of occurrence or the statistical results.
18 . The computer based system of claim 16 , wherein the data processing subsystem further comprises:
iii) a data ranking subsystem for ranking the attribute combinations based on the statistical results.
19 . The computer based system of claim 16 , further comprising a communications subsystem for:
i) a receiving subsystem for receiving at least some attributes from at least one external database; and
ii) a transmission subsystem for transmitting one or more attributes, attribute combinations, frequencies of occurrence and statistical results as output.