Computer processes for identifying related items and generating personalized item recommendations

• US 7,921,042 B2
• Filed: 08/20/2007
• Issued: 04/05/2011
• Est. Priority Date: 09/18/1998
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon.com, Inc.
• Inventors: Jacobi, Jennifer A., Benson, Eric A., Linden, Gregory D.
• Primary Examiner(s): Champagne; Donald L
• Application Number:
  US11/841,926
• Publication Number:
  US 20080033821A1
• Time in Patent Office: 1,324 Days
• Field of Search: 705/26.7, 705/14.53
• US Class Current: 705/26.7
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0253 During e-commerce, i.e. online transactions
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A computer-implemented service analyzes purchase histories and/or other types of behavioral data of users on an aggregated basis to detect and quantify associations between particular items represented in an electronic catalog. The detected associations are stored in a mapping structure that maps items to related items, and is used to recommend items to users of the electronic catalog.

Claims

1. A computer-implemented method, comprising:

storing transaction histories of each of a plurality of users in computer storage, said transaction histories identifying specific items for which transactions were conducted by the users;

generating data values that represent degrees to which specific items are related to each other, each data value corresponding to only a certain single pair of items, and being dependent upon how frequently the items of said pair co-occur in the transaction histories of the plurality of users;

using the data values to select, for each of a plurality of items, a corresponding set of related items;

generating, in computer storage, a mapping that maps each of said plurality of items to the respective set of related items; and

using the mapping, in combination with corresponding ones of said data values, to generate personalized item recommendations for each of a plurality of users.

2. The method of claim 1, wherein the transaction histories include item purchase histories.

3. The method of claim 1, wherein the method comprises generating personalized item recommendations for a target user, at least in part, by selecting a first plurality of items that are known to be of interest to the target user, and using the mapping and associated data values to map the first plurality of items to a second plurality of items to recommend to the target user.

4. The method of claim 3, wherein selecting the first plurality of items comprises selecting items from a purchase history of the user.

5. The method of claim 4, wherein generating the personalized item recommendations further comprises giving different amounts of weights to different items in the purchase history of the target user such that more weight is given to recently purchased items than to less recently purchased items.

6. The method of claim 4, wherein selecting the first plurality of items additionally comprises selecting items from an item ratings profile of the target user, said items ratings profile based on explicit ratings of items by the target user.

7. The method of claim 3, wherein selecting the first plurality of items comprises selecting items from an item ratings profile of the target user, said items ratings profile based on explicit ratings of items by the target user.

8. The method of claim 7, wherein generating the personalized item recommendations further comprises giving different amounts of weight to different items in the items ratings profile of the target user, said amounts of weight being dependent upon the explicit ratings of the corresponding items.

9. The method of claim 3, wherein selecting the first plurality of items comprises selecting items currently represented in an electronic shopping cart of the target user.

10. The method of claim 9, further comprising communicating the personalized item recommendations to the target user via a shopping cart page that identifies the items currently represented in the electronic shopping cart.

11. The method of claim 1, wherein the method comprises generating the data values and mapping in an off-line processing mode.

12. The method of claim 11, wherein the method comprises generating the personalized item recommendations substantially in real time in response to requests from the users.

13. The method of claim 1, wherein generating the personalized item recommendations comprises replicating the mapping across a plurality of physical servers, each of which runs code for using the mapping to the generate personalized item recommendations for users.

14. The method of claim 1, wherein the method is performed in its entirety by a computer system that comprises a plurality of physical servers.

15. Non-transitory computer storage that stores executable code that directs a computer system to perform a method that comprises:

storing transaction histories of each of a plurality of users, said transaction histories identifying specific items for which transactions were conducted by the users;

generating data values that represent degrees to which specific items are related to each other, each data value corresponding to only a certain single pair of items, and being dependent upon how frequently the items of said pair co-occur in the transaction histories of the plurality of users;

using the data values to select, for each of a plurality of items, a corresponding set of related items;

generating a mapping that maps each of said plurality of items to the respective set of related items; and

using the mapping, in combination with corresponding ones of said data values, to generate personalized item recommendations for each of a plurality of users.

16. The non-transitory computer storage of claim 15, wherein the transaction histories include purchase histories.

17. The non-transitory computer storage of claim 15, wherein the executable code directs the computer system to generate personalized item recommendations for a target user, at least in part, by selecting a first plurality of items that are known to be of interest to the target user, and by using the mapping and associated data values to map the first plurality of items to a second plurality of items to recommend to the target user.

18. The non-transitory computer storage of claim 17, wherein the executable code directs the computer system to select the first plurality of items at least partly from a purchase history of the user.

19. The non-transitory computer storage of claim 18, wherein the executable code directs the computer system to give different amounts of weight to different items in the purchase history of the target user such that more weight is given to recently purchased items than to less recently purchased items.

20. The non-transitory computer storage of claim 17, wherein the executable code directs the computer system to select the first plurality of items at least partly from an item ratings profile of the target user, said items ratings profile based on explicit ratings of items by the target user.

21. The non-transitory computer storage of claim 20, wherein the executable code directs the computer system to give different amounts of weight to different items in the items ratings profile of the target user, said amounts of weight being dependent upon the target user'"'"'s explicit ratings of the corresponding items.

22. The non-transitory computer storage of claim 17, wherein the executable code directs the computer system to select the first plurality of items from a set of items currently selected for purchase by the target user.

23. The non-transitory computer storage of claim 15, wherein the executable code directs the computer system to generate the personalized item recommendations substantially in real time in response to requests from the users.

24. The non-transitory computer storage of claim 15, in combination with said computer system, wherein the computer system is configured, via said executable code, to perform said method.

25. The non-transitory computer storage and computer system of claim 24, wherein the computer system comprises a plurality of physical servers.

26. A computer-implemented method of providing item recommendations, comprising:

receiving a request over a network from a user computing device associated with a user;

responding to the request by obtaining personalized item recommendation from a recommendations service, said recommendations service operative to generate the item recommendations according to a method that comprises;

storing transaction histories of each of a plurality of users, said transaction histories identifying specific items for which transactions were conducted by the users;

generating data values that represent degrees to which specific items are related to each other, each data value corresponding to only a certain single pair of items, and being dependent upon how frequently the items of said pair co-occur in the transaction histories of the plurality of users;

using the data values to select, for each of a plurality of items, a corresponding set of related items;

generating a mapping that maps each of said plurality of items to the respective set of related items; and

using the mapping, in combination with corresponding ones of said data values, to generate the personalized item recommendations; and

incorporating the personalized item recommendations into a page for transmission to the user computing device in response to the request.

27. The method of claim 26, wherein incorporating the item recommendations into a page comprises incorporating the item recommendations into a shopping cart page that indicates contents of an electronic shopping cart of the user.

28. The method of claim 27, wherein the item recommendations are based on said contents of the electronic shopping cart.

29. The method of claim 26, wherein the method is performed in its entirety by a server that communicates with the recommendations service.

30. The method of claim 29, wherein the recommendation service is external to the server, and the method comprises the server communicating with the recommendation service to obtain the item recommendations.

31. The method of claim 26, wherein the method is performed in its entirety by a web server system that is separate from the recommendation service.

32. The method of claim 26, further comprising generating the item recommendations with the recommendation service.

33. The method of claim 26, wherein the item recommendations are personalized for the user based at least partly on an item ratings profile of the user.

34. The method of claim 26, wherein the item recommendations are personalized for the user based at least partly on past item purchases of the user.

35. The method of claim 26, wherein the item recommendations are personalized for the user based at least partly on recorded item viewing activities of the user.