Recommendation system
First Claim
Patent Images
1. A computer system, comprising:
- a first component configured to generate, for each of a plurality of item pairs, a respective data value representing a degree to which only the items of the that particular pair are related to each other, said data value being dependent upon how frequently the items of the pair have co-occurred in purchase histories of a plurality of users;
a data repository which stores at least some of the data values in association with the items to which they correspond; and
a second component configured to receive an input list of items selected by a user, and to use the associated data values stored in the data repository to generate an output list of items that are predicted to be of interest to the user, said input and output lists each including multiple items.
1 Assignment
0 Petitions
Accused Products
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. The items may include products and/or categories of products.
-
Citations
27 Claims
-
1. A computer system, comprising:
-
a first component configured to generate, for each of a plurality of item pairs, a respective data value representing a degree to which only the items of the that particular pair are related to each other, said data value being dependent upon how frequently the items of the pair have co-occurred in purchase histories of a plurality of users; a data repository which stores at least some of the data values in association with the items to which they correspond; and a second component configured to receive an input list of items selected by a user, and to use the associated data values stored in the data repository to generate an output list of items that are predicted to be of interest to the user, said input and output lists each including multiple items.
-
-
2. The computer system of claim 1, wherein the data repository comprises a mapping structure that associates related items.
-
3. The computer system of claim 2, wherein the first component uses the data values to select item pairs to include in the mapping structure.
-
4. The computer system of claim 1, wherein the first component is configured to exclude, from the data repository, data values that do not satisfy a selected condition.
-
5. The computer system of claim 1, wherein the input list includes at least one purchased item that was purchased by the user on a purchase date, and the second component is configured to take the purchase date into consideration in determining how much weight to give to the purchased item in generating the output list of items.
-
6. The computer system of claim 1, wherein the input list includes at least one item to which the user has explicitly assigned a rating, and the second component is configured to take the rating into consideration in generating the output list of items.
-
7. The computer system of claim 1, wherein the first component is configured to additionally take item viewing histories of users into consideration in generating the data values.
-
8. The computer system of claim 1, wherein the second component generates the input list of items, at least in part, by identifying items viewed by the user during browsing of an electronic catalog.
-
9. The computer system of claim 1, wherein the items are products represented in an electronic catalog.
-
10. The computer system of claim 1, wherein the items are categories of products represented in the electronic catalog.
-
11. The computer system of claim 1, wherein the input list is a list of items represented in an electronic shopping cart of the user.
-
12. The computer system of claim 1, wherein the first component is configured to generate the data values in an off-line processing mode, and the second component is configured to generate the output list substantially in real time in response to an action by said user.
-
13. The computer system of claim 1, wherein the second component comprises a physical server that is configured to generate personalized item recommendations substantially in real time in response to requests for recommendations.
-
14. The computer system of claim 13, wherein the physical server uses an item-to-item mapping structure generated by the first component to generate the personalized recommendations, said mapping structure having said data values stored therein.
-
15. The computer system of claim 1, wherein the second component comprises a plurality of physical servers, each of which stores (1) a replicated copy of an item-to-item mapping structure that includes said data values, and (2) executable code that uses the item-to-item mapping structure to generate item recommendations.
-
16. The computer system of claim 1, wherein the second component is configured to generate the output list by a process that comprises (a) for each of a plurality of items on the input list, looking up a respective set of related items, and (b) merging the sets of related items while combining data values associated with like items.
-
17. The computer system of claim 1, wherein the second component is configured to give different amounts of weight to different items on the input list, said amounts of weight being dependent upon user actions performed in connection with the items on the input list.
-
18. 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 item recommendation from a recommendations service, said recommendation service comprising; a first component configured to generate, for each of a plurality of item pairs, a respective data value representing a degree to which only the items of that particular pair are related to each other, said data value being dependent upon how frequently the items of the pair have co-occurred in purchase histories of a plurality of users; a data repository which stores at least some of the data values in association with the items to which they correspond; and a second component configured to receive an input list of items selected by the user, and to use the associated data values stored in the data repository to generate an output list of items that are predicted to be of interest to the user, said input and output lists each including multiple items; and incorporating the item recommendations into a page, and transmitting the page to the user computing device for presentation to the user.
-
-
19. The method of claim 18, wherein incorporating the item recommendations into a page comprises incorporating the item recommendations into a shopping cart page that displays contents of an electronic shopping cart of the user.
-
20. The method of claim 19, wherein the item recommendations are based on said contents of the electronic shopping cart.
-
21. The method of claim 18, wherein the method is performed in its entirety by a web server.
-
22. The method of claim 21, wherein the recommendation service is external to the web server, and the method comprises the web server communicating with the recommendation service to obtain the item recommendations.
-
23. The method of claim 18, wherein the method is performed in its entirety by a web server system that is separate from the recommendation service.
-
24. The method of claim 18, further comprising generating the item recommendations with the recommendation service.
-
25. The method of claim 18, wherein the item recommendations are personalized for the user based at least partly on an item ratings profile of the user.
-
26. The method of claim 18, wherein the item recommendations are personalized for the user based at least partly on past item purchases of the user.
-
27. The method of claim 18, wherein the item recommendations are personalized for the user based at least partly on recorded item viewing activities of the user.
Specification