Expanding Attribute Profiles

• US 20080228703A1
• Filed: 08/08/2007
• Published: 09/18/2008
• Est. Priority Date: 03/16/2007
• Status: Active Grant

• Current Assignee: 23andme Incorporated (23andMe Holding Co.)
• Original Assignee: Expanse Networks, Inc.
• Inventors: Eldering, Charles Anthony, Kenedy, Andrew Alexander
• Granted Patent: US 8,024,348 B2
• Time in Patent Office: Days
• US Class Current: 707/2
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/2282 Tablespace storage structures; Management thereof
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 20/40 Population genetics; Linkage disequilibrium
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/20 : relating to practices or guidelines
• CPC Class Codes: H04L 67/306 : User profiles

Abstract

A method and system for expanding attribute profiles are presented in which primary attributes from one or more attribute profiles are used to derive secondary attributes which are added to the respective attribute profiles to generate expanded attribute profiles. The expanded attribute profiles are generated to increase the strength of association of a query attribute with one or more attribute profiles associated with query-attribute-positive individuals.

Claims

1. A computer based method for expanding attribute profiles to increase the strength of association between a query attribute and a set of attribute profiles associated with query-attribute-positive individuals, comprising:

a) receiving a query attribute;

b) accessing a set of attribute profiles associated with a group of query-attribute-positive individuals;

c) accessing a set of attribute profiles associated with a group of query-attribute-negative individuals;

d) determining a first statistical result indicating strength of association of the query attribute with an attribute combination having a higher frequency of occurrence in the set of attribute profiles associated with the group of query-attribute-positive individuals than in the set of attribute profiles associated with the group of query-attribute-negative individuals;

e) expanding one or more attributes in the set of attribute profiles associated with the group of query-attribute-positive individuals and one or more attributes in the set of attribute profiles associated with the query-attribute-negative individuals to create a set of expanded attribute profiles associated with the group of query-attribute-positive individuals and a set of expanded attribute profiles associated with the group of query-attribute-negative individuals;

f) determining a second statistical result indicating strength of association of the query attribute with an attribute combination having a higher frequency of occurrence in the set of expanded attribute profiles associated with the group of query-attribute-positive individuals than in the set of expanded attribute profiles associated with the group of query-attribute-negative individuals; and

g) storing, when the second statistical result is higher than the first statistical result, the expanded attribute profiles associated with the group of query-attribute-positive individuals and the expanded attribute profiles associated with the group of query-attribute-negative individuals.

2. The computer based method of claim 1, wherein the one or more attributes are primary attributes, wherein expanding one or more attributes comprises deriving secondary attributes from the primary attributes, and wherein the secondary attributes have a lower resolution than the primary attributes.

3. The computer based method of claim 1, wherein a secondary attribute encompasses a primary attribute.

4. The computer based method of claim 1, wherein at least one secondary attribute is derived by compounding the values of two or more primary attributes.

5. The computer based method of claim 1, wherein at least one secondary attribute is derived through a heuristic rule applied to one or more primary attributes.

6. The computer based method of claim 1, wherein at least one secondary attribute comprises an inequality statement containing a quantitative value, wherein the quantitative value is either larger or smaller than that of the primary attribute from which it was derived.

7. The computer based method of claim 1, wherein the identity of one or more individuals is masked or anonymized.

8. A computer based method for expanding an attribute profile to increase the strength of association between a query attribute and the attribute profile, comprising:

a) accessing an attribute profile containing a set of primary attributes;

b) expanding the set of primary attributes to produce a set of secondary attributes, wherein the set of secondary attributes results in a higher strength of association between a query attribute and an attribute profile containing the set of secondary attributes than between the query attribute and an attribute profile containing only the set of primary attributes; and

c) storing the set of secondary attributes in association with the attribute profile to create an expanded attribute profile.

9. The computer based method of claim 8, further comprising:

d) determining the strength of association of the expanded attribute profile with a query attribute by comparing the expanded attribute profile to a set of attribute combinations that are statistically associated with the query attribute.

10. The computer based method of claim 8, further comprising:

d) determining attribute combinations that are associated with a query attribute by identifying attribute combinations from the expanded attribute profile that have higher frequencies of occurrence in a set of attribute profiles associated with query-attribute-positive individuals than in a set of attribute profiles associated with query-attribute-negative individuals.

11. The computer based method of claim 8, wherein the set of secondary attributes has lower resolution than the set of primary attributes.

12. The computer based method of claim 8, wherein a secondary attribute encompasses a primary attribute.

13. The computer based method of claim 8, wherein at least one secondary attribute in the set of secondary attributes is a categorical attribute that encompasses at least one primary attribute in the set of primary attributes that is a numerical attribute.

14. The computer based method of claim 8, wherein at least one secondary attribute is derived by compounding the values of two or more primary attributes.

15. The computer based method of claim 8, wherein at least one primary attribute has a continuous value and at least one secondary attribute derived from that primary attribute has a discrete value.

16. The computer based method of claim 8, wherein at least one secondary attribute is derived through a heuristic rule applied to one or more primary attributes.

17. The computer based method of claim 8, wherein at least one secondary attribute comprises an inequality statement containing a quantitative value, wherein the quantitative value is either larger or smaller than that of the primary attribute from which it was derived.

18. The computer based method of claim 8, wherein two or more of the secondary attributes comprise a sequence of inequality statements containing progressively larger quantitative values.

19. The computer based method of claim 8, wherein two or more of the secondary attributes comprise a sequence of inequality statements containing progressively smaller quantitative values.

20. A computer based system for expanding attribute profiles to increase the strength of association between a query attribute and a set of attribute profiles associated with query-attribute-positive individuals, comprising:

a) a data receiving subsystem for receiving a query attribute;

b) a data accessing subsystem for accessing;

i) a set of attribute profiles associated with a group of query-attribute-positive individuals;

ii) a set of attribute profiles associated with a group of query-attribute-negative individuals;

c) a data processing subsystem comprising a data conversion subsystem for expanding one or more attributes in the set of attribute profiles associated with the group of query-attribute-positive individuals and one or more attributes in the set of attribute profiles associated with the query-attribute-negative individuals to create a set of expanded attribute profiles associated with the group of query-attribute-positive individuals and a set of expanded attribute profiles associated with the group of query-attribute-negative individuals;

d) a statistical computation subsystem for;

i) calculating a first statistical result indicating strength of association of the query attribute with an attribute combination having a higher frequency of occurrence in the set of attribute profiles associated with the group of query-attribute-positive individuals than in the set of attribute profiles associated with the group of query-attribute-negative individuals;

ii) calculating a second statistical result indicating strength of association of the query attribute with an attribute combination having a higher frequency of occurrence in the set of expanded attribute profiles associated with the group of query-attribute-positive individuals than in the set of expanded attribute profiles associated with the group of query-attribute-negative individuals; and

e) a data storage subsystem for storing, when the second statistical result is higher than the first statistical result, the expanded attribute profiles associated with the group of query-attribute-positive individuals and the expanded attribute profiles associated with the group of query-attribute-negative individuals.