Use of electronic shopping carts to generate personal recommendations

• US 6,317,722 B1
• Filed: 09/18/1998
• Issued: 11/13/2001
• Est. Priority Date: 09/18/1998
• Status: Expired due to Term

• 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): Hafiz, Tariq R.
• Assistant Examiner(s): HARLE, JENNIFER I
• Application Number:
  US09/156,237
• Time in Patent Office: 1,152 Days
• Field of Search: 235/383, 380/24, 455/5.1, 455/480, 705/14, 705/27, 707/3, 707/102, 709/227
• US Class Current: 705/14.51
• 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 recommends products or other items to a user based on a set of items known to be of interest to the user, such as a set of items currently in the user'"'"'s electronic shopping cart. In one embodiment, the service identifies items that are currently in the user'"'"'s shopping cart, and uses these items to generate a list of additional items that are predicted to be of interest to the user, wherein an additional item is selected to include in the list based in-part upon whether that item is related to more than one of the items in the user'"'"'s shopping cart. The item relationships are preferably determined by an off-line process that analyzes user purchase histories to identify correlations between item purchases. The additional items are preferably displayed to the user when the user views the contents of the shopping cart.

Claims

1. In a computer system that provides user access to a database of items, and provides electronic shopping carts for allowing users to interactively select and hold items from the database for prospective purchase, a system for recommending items to users, comprising:

a computer-readable medium embodying a non-user-specific data structure which maps items from the database to sets of similar items from the database; and

a computer system embodying a recommendation process which generates personal recommendations for a user that has an electronic shopping cart by at least;

(a) identifying a plurality of items, including multiple items that are currently in the user'"'"'s shopping cart;

(b) for each item identified in step (a), accessing the non-user-specific data structure to identify a corresponding set of similar items, to thereby identify a plurality of sets of similar items;

(c) combining the sets of similar items identified in step (b) to generate a ranked set of similar items in which a similar item'"'"'s ranking reflects whether that similar item appears within more than one of said sets; and

(d) presenting at least some of the items of the ranked set of similar items to the user as recommendations.

2. The system of claim 1, wherein step (a) consists of identifying items that are currently in the user'"'"'s shopping cart.

3. The system of claim 1, wherein the shopping cart used in step (a) is a designated one of a plurality of shopping carts defined by the user within an account of the user, the system thereby generating recommendations that correspond to a shopping role of the designated shopping cart.

4. The system of claim 3, wherein the shopping cart used in step (a) is a shopping cart selected by the user for display.

5. The system of claim 1, wherein the computer system allows a user to create multiple shopping carts within a single account, and the recommendation process generates shopping cart specific recommendations to allow a user with multiple shopping carts to obtain recommendations specific to a role of a particular shopping cart.

6. The system of claim 1, wherein the data structure maps items to similar items based at least upon correlations between purchases of items by users.

7. The system of claim 1, wherein the data structure maps items to similar items based at least upon a content-based similarity analysis of items.

8. The system of claim 1, wherein the sets of similar items in the data structure include similarity index values, each index value indicating a degree of similarity between a reference item and a similar item, and wherein step (c) comprises combining similarity index values of like items.

9. The system of claim 1, further comprising filtering out similar items identified in step (b) to remove items already purchased by the user.

10. The system of claim 1, wherein step (d) comprises displaying the recommendations to the user when the user displays the contents of the shopping cart.

34. The system of claim 1, wherein the recommendation process performs (b)-(d) when the user views contents of the shopping cart.

11. In a computer system that provides user access to a database of items, and provides electronic shopping carts for allowing users to collect and hold items for prospective purchase, a method of predicting items that are of current interest to a user, comprising the computer-implemented steps of:

(a) identifying a plurality of items that are currently in the user'"'"'s shopping cart;

(b) for each item identified in step (a), accessing a non-user-specific data structure which maps items to similar items to identify a corresponding set of similar items, to thereby identify multiple sets of similar items;

(c) combining the multiple sets of similar items to form a ranked set of similar items in which an item'"'"'s ranking reflects whether that item appears within more than one of the multiple sets; and

(d) recommending at least some of the items of the ranked set of similar items to the user.

12. The method of claim 11, wherein step (d) comprises presenting recommended items to the user when the user views the shopping cart contents.

13. The method of claim 11, wherein step (b) comprises accessing a data structure that maps items to similar items based at least upon correlations between purchases of items by users.

14. The method of claim 11, wherein step (b) comprises accessing a data structure that maps items to similar items based at least upon a content-based similarity analysis of items.

15. The method of claim 11, wherein step (a) further comprises identifying at least one additional item for which the user has recently indicated an interest.

35. The method of claim 11, wherein steps (b)-(d) are performed when the user views contents of the shopping cart.

16. In a computer system that provides user access to a database of items, and provides electronic shopping carts for allowing users to collect and hold items for prospective purchase, a computer-implemented method of recommending items to a user, comprising:

(a) providing a non-user-specific data structure which indicates similarities between items of the database;

(b) identifying a first plurality of items that are of current interest to the user, the first plurality of items including at least two items that are currently in an electronic shopping cart of the user;

(c) using the data structure to identify a second plurality of items that are similar to one or more of the first plurality of items and

(d) selecting, from the second plurality of items, a subset of items to recommend to the user, wherein an item is selected based in part on whether it is similar to more than one of the first plurality of items.

17. The method of claim 16, wherein step (a) comprises generating the data structure, the step of generating the data structure comprising analyzing purchase history data of a community of users to identify correlations between purchases of items.

18. The method of claim 16, wherein step (a) comprises generating the data structure, the step of generating the data structure comprising performing a content-based analysis of items within the database.

19. The method of claim 16, further comprising presenting the subset of items to the user as recommendations when the user views contents of the shopping cart.

36. The method of claim 16, wherein (b) and (c) are performed when the user views contents of the shopping cart, to thereby identify items to display to the user in conjunction with the contents of the shopping cart.

39. The method of claim 16, wherein the first plurality of items consists of items currently in the user'"'"'s shopping cart.

20. In a computer system that provides user access to a database of items that are available for purchase, and which allows users to create and use multiple shopping carts within a common account with a merchant to hold items for prospective purchase, a method of recommending items that correspond to a particular shopping cart of a user that has multiple shopping carts, comprising:

(a) providing a non-user-specific data structure which indicates similarities between items of the database;

(b) identifying a shopping cart of the plurality of shopping carts of the user;

(c) identifying a first plurality of items that have been placed by the user into the shopping cart identified in step (b);

(d) using the data structure to identify a second plurality of items that are similar to one or more of the first plurality of items; and

(e) selecting, from the second plurality of items, a subset of items to recommend to the user, wherein an item is selected based in part on whether that item is similar to more than one of the first plurality of items.

21. The method of claim 20, wherein step (b) comprises prompting the user to select a shopping cart from the plurality of shopping carts.

22. The method of claim 20, wherein step (b) comprises identifying a shopping cart currently selected by the user for display.

23. The method of claim 22, further comprising presenting the subset of items to the user as recommendations when the user views contents of the selected shopping cart.

24. The method of claim 20, wherein step (c) comprises identifying at least one item that was purchased by the user from the shopping cart identified in step (b).

25. The method of claim 20, wherein step (c) comprises identifying at least one item that is currently in the shopping cart identified in step (b).

26. The method of claim 20, wherein step (a) comprises generating the data structure, the step of generating the data structure comprising analyzing purchase history data of a community of users to identify correlations between purchases of items.

27. The method of claim 20, wherein step (a) comprises generating the data structure, the step of generating the data structure comprising performing a content-based analysis of items within the database.

28. A computer-implemented method of recommending items to a user, comprising:

identifying a plurality of items that are currently in the user'"'"'s shopping cart;

using the plurality of items in the user'"'"'s shopping cart to generate a list of additional items that are predicted to be of interest to the user, wherein an additional item is selected for inclusion in the list based in-part upon whether that additional item is similar to more than one of the plurality of items in the user'"'"'s shopping cart; and

displaying the list of additional items to the user when the user views contents of the shopping cart.

29. The method as in claim 28, wherein using the plurality of items to generate a list comprises:

(a) for each of the plurality of items, accessing a data structure which maps items to sets of similar items to identify a corresponding set of similar items; and

(b) combining the sets of similar items identified in (a) to generate a ranked set of items in which items are ranked according to similarity to the plurality of items in the shopping cart.

30. The method as in claim 29, wherein (b) comprises increasing a ranking of an item that is similar to more than one of the plurality of items in the shopping cart.

31. The method as in claim 28, wherein using the plurality of items to generate a list comprises determining whether an item is similar to more than one of the plurality of items in the shopping cart.

32. The method as in claim 28, wherein using the plurality of items to generate a list comprises filtering out items that have been purchased by the user.

33. The method as in claim 28, wherein the shopping cart is one of multiple shopping carts within an account of the user, and the method is performed separately for each of the multiple shopping carts to provide shopping cart specific recommendations.

37. The method of claim 28, wherein the list of additional items is generated when the user selects the shopping cart for viewing.

38. The method of claim 29, wherein (a) and (b) are performed when the user views contents of the shopping cart.

40. A method of recommending products to a user, comprising:

generating a data structure which maps individual products to sets of related products in which product relatedness is determined based at least in-part on an automated analysis of user purchase histories of products;

identifying a plurality of products that are currently in a shopping cart of a user;

for each of the plurality of products, accessing the data structure to identify a corresponding set of related products, to thereby identify a plurality of sets of related products; and

selecting related products from the plurality of sets to recommend to the user based in part on whether a related product falls within more than one of said sets, such that products that are related to more than one of the products in the user'"'"'s shopping cart tend to be recommended to the user over products related to only a single product in the shopping cart.

41. The method of claim 40, wherein the data structure is generated in an off-line mode.

42. The method of claim 40, further comprising displaying the related products selected for recommendation within a web page that displays current contents of the shopping cart.