System for detecting associations between items

• US 9,311,046 B1
• Filed: 08/16/2010
• Issued: 04/12/2016
• Est. Priority Date: 09/27/2007
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hicks, Cory
• Primary Examiner(s): Mahmoudi, Tony
• Assistant Examiner(s): Pham, Tuan A
• Application Number:
  US12/857,384
• Time in Patent Office: 2,066 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 7/00 Methods or arrangements for processing data by operating upon the order or content of the data handled logic circuits H03K19/00
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A method of detecting associations between items can include identifying a plurality of items represented in a data repository from which to select items to recommend to a target user, each item including one or more attributes. A degree of fit between an item'"'"'s attributes and other items is calculated. The degree of fit can indicate the relevance of the attributes of one item to the other item. A degree of association between the two items is calculated based at least in part on the calculated degree of fit. The degree of association between the two items can indicate the relatedness of the two items. Based on this degree of association, an association between the items can be stored in a data repository.

Claims

1. A method of associating media works having related media contributors, the method comprising:

by a computer system comprising computer hardware;

identifying a first media work having a first contributor;

identifying a second media work having a second contributor, the second contributor not being a contributor to the first media work, and the first contributor not being a contributor to the second media work; and

calculating a degree of association between the first media work and the second media work based, at least in part, on an extent to which the first and second contributors co-contribute to one or more other media works, wherein calculating said degree of association between the first and second media works comprises calculating an association value that is dependent upon respective contribution roles of the first and second contributors in contributing to a third media work.

2. The method of claim 1, further comprising recommending one or more items to a user based at least partly on the calculated degree of association between the first media work and the second media work.

3. The method of claim 1, wherein calculating the degree of association comprises taking into consideration acting roles of the first and second contributors in said one or more other media works.

4. The method of claim 1, wherein the first and second media works are movies and the first and second contributors are actors in the movies.

5. The method of claim 1, wherein the media works comprise musical works.

6. The method of claim 1, wherein the computer system comprises a plurality of physical computers.

7. The method of claim 1, wherein calculating said degree of association between the first and second media works comprises identifying a third media work to which the first and second contributors co-contributed, and determining respective contribution roles of the first and second contributors in contributing to the third media work.

8. The method of claim 1, wherein calculating said degree of association between the first and second media works comprises calculating an association value that is dependent upon types of contributions made by the first and second contributors to each of a plurality of other media works to which the first and second contributors co-contributed.

9. A method of associating media works having related media contributors, the method comprising:

by a computer system comprising computer hardware;

identifying a first media work having a first contributor;

identifying a second media work having a second contributor, the second contributor not being a contributor to the first media work, and the first contributor not being a contributor to the second media work; and

calculating a degree of association between the first media work and the second media work based, at least in part, on an extent to which the first and second contributors co-contribute to one or more other media works, wherein calculating said degree of association comprises (a) calculating a first degree of fit between the first contributor and the second media work, (b) calculating a second degree of fit between the second contributor and the first media work, and (c) calculating an association value that is dependent upon the first and second calculated degrees of fit, said association value representing said degree of association between the first and second media works.

10. A system capable of detecting associations between works, the system comprising:

a computer data repository that stores attribute data for each of a plurality of works, said attribute data specifying contributors to the works; and

an association mining system comprising one or more processors, said association mining system configured to use the attribute data to determine degrees of association between particular works by a process that comprises;

identifying a first work having a first contributor;

identifying a second work having a second contributor; and

calculating an association value representing a degree of association between the first work and the second work, said association value being dependent upon an extent to which the first and second contributors have co-contributed to one or more other works, as determined from said attribute data said association value additionally dependent upon respective contribution roles of the first and second contributors in contributing to a third work.

11. The system of claim 10, wherein the first contributor is not a contributor to the second work, and the second contributor is not a contributor to the first work.

12. The system of claim 10, further comprising a recommendation system that uses association values calculated according to said process to select works to recommend to users.

13. The system of claim 10, wherein the first contributor is an actor in the first work, and the second contributor is an actor in the second work.

14. The system of claim 10, wherein the works are movies.

15. The system of claim 10, wherein the association value is dependent upon types of contributions made by the first and second contributors to each of a plurality of works to which the first and second contributors co-contributed.

16. The system of claim 10, wherein the association value is additionally dependent upon an extent to which other contributors to the first and second works have co-contributed to works other than the first and second works.

17. A system capable of detecting associations between works, the system comprising:

a computer data repository that stores attribute data for each of a plurality of works, said attribute data specifying contributors to the works; and

an association mining system comprising one or more processors, said association mining system configured to use the attribute data to determine degrees of association between particular works by a process that comprises;

identifying a first work having a first contributor;

identifying a second work having a second contributor; and

calculating an association value representing a degree of association between the first work and the second media, said association value being dependent upon an extent to which the first and second contributors have co-contributed to one or more other works, as determined from said attribute data;

wherein the association mining system, in calculating the association value, is configured to (a) calculate a first degree of fit between the first contributor and the second work, (b) calculate a second degree of fit between the second contributor and the first work, and (c) calculate the association value such that the association value is dependent upon the first and second calculated degrees of fit.

18. Non-transitory computer storage that stores executable code that directs a computer system to determine a degree of association between movies by a process that comprises:

identifying a first movie having a first actor;

identifying a second movie having a second actor;

determining, based on a data repository of movie attribute data, an extent to which the first actor and second actor co-contributed as actors to one or more other movies; and

calculating an association value that is dependent upon said extent to which the first actor and second actor have co-contributed as actors to one or more other movies, and that is additionally dependent upon acting roles of the first and second actors in co-contributing to the one or more other movies, said association value representing a degree of association between the first and second movies.

19. The non-transitory computer storage of claim 18, wherein the association value is additionally dependent upon an extent to which other contributors to the first and second movies have co-contributed to other movies.

20. The non-transitory computer storage of claim 18, wherein the first actor is not a contributor to the second movie, and the second actor is not a contributor to the first movie.

21. The non-transitory computer storage of claim 18, in combination with said computer system, wherein the computer system is programmed with said executable code to implement said process.