Assigning social networking system users to households

Patent metadata

Field	Value
Publication number	US-9679044-B2
Application number	US-201213677885-A
Country	US
Kind code	B2
Filing date	Nov 15, 2012
Priority date	Nov 15, 2011
Publication date	Jun 13, 2017
Grant date	Jun 13, 2017

Abstract

Users of a social networking system are assigned to households using prediction models that rely, in part, on user profile information and social graph data. Information about users may be received by a social networking system through various channels (e.g., declared/profile information, user history, IP addresses, Global Positioning System (GPS) data from check-in events and/or continuously provided by mobile devices, external household information, and/or social information). Scoring models may use statistical analysis of the received user information to predict household membership for users. User attributes, such as previous names, date of birth, social graph data, locations, life events, and check-ins, may be factors in generating confidence scores of predicted household memberships. Weighted scoring models may use machine learning methods for measuring the accuracy of the household membership prediction. The social networking system may use a machine learning algorithm to analyze user information to determine confidence scores for matching potential households.

First claim

What is claimed is:

1. A method comprising:
receiving a plurality of information items about a user of a social networking system;
generating a household object associated with the user in the social networking system based on the plurality of information items about the user;
determining one or more members of a household represented by the household object in the social networking system based on the received plurality of information items about the user, where the user is a member of the household; and
storing the household object in association with the determined one or members of the household in the social networking system.

2. The method of claim 1 , wherein receiving a plurality of information items about a user of a social networking system comprises:
retrieving household data about the user from external resources based on a name of the user and an address of the user extracted from a user profile for the user stored in the social networking system.

3. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a department of motor vehicles.

4. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a tax agency.

5. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a magazine publisher.

6. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a postal service agency.

7. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a voter registration agency.

8. The method of claim 2 , wherein household data about the user retrieved from external resources further comprises one or more records from a credit agency.

9. The method of claim 1 , wherein determining one or more members of a household comprises:
determining a spouse of the user to be a member of the household, where the spouse comprises another user of the social networking system married to the user based on relationship information included in a user profile of the user and the spouse.

10. The method of claim 1 , wherein determining one or more members of a household comprises:
determining a child of the user to be a member of the household, where the child comprises another user of the social networking system connected to the user based on relationship information included in a user profile of the user and the child.

11. The method of claim 1 , wherein determining one or more members of a household comprises:
determining a roommate of the user to be a member of the household, where the roommate comprises another user of the social networking system having an equivalent address as the user based on an address of the user extracted from a user profile for the user stored in the social networking system.

12. The method of claim 1 , wherein determining one or more members of a household comprises:
determining a particular user connected to the user in the social networking system to be a member of the household, where the social networking system has determined a social graph correlation between the particular user and the user based on a plurality of affinity scores between the particular user and the user exceeding a predetermined threshold.

13. A method comprising:
retrieving a plurality of information items about a user of a social networking system;
determining one or more membership scores for the user for one or more households in the social networking system using a scoring model based on the plurality of information items about the user;
selecting a household from the one or more households in the social networking system based on the one or more memberships scores for the user; and
storing an association of the selected household with the user in the social networking system.

14. The method of claim 13 , wherein determining one or more membership scores for the user for one or more households in the social networking system using a scoring model based on the plurality of information items about the user comprises:
retrieving a relationship status of the user as an information item of the retrieved plurality of information items;
retrieving a scoring model for the user based on the retrieved relationship status of the user; and
determining a membership score for the user for one or more households in the social networking system using the retrieved scoring model based on the plurality of information items.

15. The method of claim 13 , wherein determining one or more membership scores for the user for one or more households in the social networking system using a scoring model based on the plurality of information items about the user comprises:
retrieving a life event of the user as an information item of the retrieved plurality of information items;
retrieving a scoring model for the user based on the retrieved life event of the user; and
determining a membership score for the user for one or more households in the social networking system using the retrieved scoring model based on the plurality of information items.

16. The method of claim 13 , where a household comprises one or more household properties.

17. The method of claim 16 , where a household property comprises a single household type.

18. The method of claim 16 , where a household property comprises a married household type.

19. The method of claim 16 , where a household property comprises a roommate household type.

20. The method of claim 16 , where a household property comprises a family household type.

21. The method of claim 16 , where a household property comprises an extended family household type.

22. The method of claim 16 , where a household property comprises one or more interests associated with one or more members of the household.

23. The method of claim 16 , where a household property comprises a geographical location.

24. The method of claim 16 , where a household property comprises one or more genders associated with one or members of the household.

25. The method of claim 16 , where a household property comprises one or more ages associated with one or members of the household.

26. A non-transitory computer-readable storage medium storing executable computer program instructions, the instructions executable to perform steps comprising:
receiving a plurality of information items about a user of a social networking system;
generating a household object associated with the user in the social networking system based on the plurality of information items about the user;
determining one or more members of a household represented by the household object in the social networking system based on the received plurality of information items about the user, where the user is a member of the household; and
storing the household object in association with the determined one or members of the household in the social networking system.

27. The non-transitory computer-readable storage medium of claim 26 , wherein receiving a plurality of information items about a user of a social networking system comprises:
retrieving household data about the user from external resources based on a name of the us

Assignees

• Facebook Inc

Inventors

• Bruich Sean Michael
• Smallwood Bradley Hopkins

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q30/0269 Primary

  based on user profile or attribute · CPC title

• G06F17/30867

  Physics · mapped topic

• G06F17/30598 Primary

  Physics · mapped topic

• H04L67/52

  specially adapted for the location of the user terminal · CPC title