Pangenetic web user behavior prediction system

• US 9,031,870 B2
• Filed: 01/30/2012
• Issued: 05/12/2015
• Est. Priority Date: 12/30/2008
• Status: Active Grant

• Current Assignee: 23andme Incorporated (23andMe Holding Co.)
• Original Assignee: Expanse Bioinformatics, Inc.
• Inventors: Kenedy, Andrew Alexander, Eldering, Charles Anthony
• Primary Examiner(s): TRUONG, CAM Y T
• Application Number:
  US13/361,533
• Publication Number:
  US 20120131034A1
• Time in Patent Office: 1,198 Days
• Field of Search: 707/749, 705/26.7
• US Class Current: 705/26.7
• CPC Class Codes: G06F 16/2237 Vectors, bitmaps or matrices
• 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

Abstract

Computer based systems, methods, software and databases are presented in which correlations between web item preferences, behaviors and pangenetic (genetic and epigenetic) attributes of individuals are used for pangenetic based user behavior prediction in which predictions of a user'"'"'s online behavior can be generated based on the user'"'"'s pangenetic makeup. Data masking can be used to maintain privacy of sensitive portions of the pangenetic data.

Claims

1. A computer based method for pangenetic recommendation of consumer purchasable items for a user, comprising:

a) receiving a signal indicative of user interest in a consumer purchasable item or a consumer purchasable item category;

b) accessing a pangenetic profile associated with the user, the pangenetic profile comprising at least one genetic or epigenetic attribute;

c) correlating prior purchases of consumer purchases items of a set individuals with pangenetic profiles of the set of individuals to create statistical correlations between the consumer purchasable items and pangenetic attributes of the set of individuals;

d) determining, based on the correlations of the step c), consumer purchasable items preferred by a subset of individuals with pangenetic attributes correlated to pangenetic attributes of the user; and

e) transmitting as output a listing of at least a portion of the consumer purchasable items preferred by the subset of individuals with pangenetic attributes correlated to pangenetic attributes of the user to indicate recommended consumer purchasable items for the user, wherein the listing is a rank listing, and wherein the rank of each consumer purchasable item in the rank listing is based on strength of the correlations of the pangenetic attributes of the subset of individuals with the pangenetic attributes of the user, wherein the portion of the list transmitted as output consists of the consumer purchasable items having a rank within a range defined by at least one predetermined threshold applied to rank.

2. The computer based method of claim 1, wherein the signal is a web search query.

3. The computer based method of claim 1, wherein the prior purchases include ratings that indicate levels of satisfaction with the purchased consumer purchasable items.

4. The computer based method of claim 1, further comprising the steps of i) transmitting an authorization request for access to the pangenetic profile associated with the user, and ii) receiving an authorization granting access to the pangenetic profile associated with the user.

5. The computer based method of claim 1, wherein a data mask is applied to the pangenetic profile of the set of individuals and the pangenetic profile of the user.

6. The computer based method of claim 1, wherein the dataset is a consumer purchasable item feedback matrix.

7. A database system for pangenetic online recommendation of consumer purchasable items for a user, comprising:

a) a memory containing;

i. a first data structure containing a pangenetic profile associated with the user, the pangenetic profile comprising at least one of genetic or epigenetic attribute;

ii. a second data structure containing correlations of preferences for consumer purchasable items by a set individuals with the pangenetic profile of the set of individuals, wherein the correlations in dataset are determined based on statistical associations between preferences for particular consumer purchasable items and pangenetic attributes associated with the set of individuals;

b) a processor for;

i. receiving a signal indicative of user interest in a consumer purchasable item or a consumer purchasable item category;

ii. accessing the first data structure containing the pangenetic profile associated with the user,

iii. accessing the second data structure containing the correlations of the preferences for the consumer purchasable items by set individuals with pangenetic profiles of the set of individuals, wherein the correlations in the dataset are determined based on the statistical associations between the preferences for the particular consumer purchasable items and pangenetic attributes associated with the set of individuals;

iv. determining, based on the correlations in the step of accessing (iii), consumer purchasable items preferred by a subset set of individuals with pangenetic attributes correlated to the user; and

v. transmitting as output a listing of at least a portion of the consumer purchasable items preferred by the subset of individuals with pangenetic attributes correlated to pangenetic attributes of the user to indicate recommended consumer purchasable items for the user, wherein the listing is a rank listing, and wherein the rank of each consumer purchasable item in the rank listing is based on strength of the correlations of the pangenetic attributes of the subset of individuals with the pangenetic attributes of the user, wherein the portion of the list transmitted as output consists of the consumer purchasable items having a rank within a range defined by at least one predetermined threshold applied to rank.

8. The database system of claim 7, wherein the signal is a web search query.

9. The database system of claim 7, wherein prior purchases include ratings that indicate levels of satisfaction with the purchased consumer purchasable items.

10. The database system of claim 7, further comprising the steps of i) transmitting an authorization request for access to the pangenetic profile associated with the user, and ii) receiving an authorization granting access to the pangenetic profile associated with the user.

11. The database system of claim 7, wherein a data mask is applied to the pangenetic profile of the set of individuals and the pangenetic profile of the user.

12. The database system of claim 7, wherein the dataset is a consumer purchasable item feedback matrix.