Method And System For Generating Item Recommendation

• US 20150170038A1
• Filed: 12/17/2013
• Published: 06/18/2015
• Est. Priority Date: 12/17/2013
• Status: Abandoned Application

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Lin, Shun-Chieh, Tsai, Huan-Wen, Cheng, Kuang-Hung, Lin, Chien-Kuo
• Application Number:
  US14/109,383
• Publication Number:
  US 20150170038A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

A method for a system to generate an item recommendation. The method includes determining, for each of a plurality of roles, a plurality of reference utility values each for one of a plurality of items, and performing a normalization on the plurality of reference utility values determined for each of the plurality of roles. The method further includes determining a plurality of aggregate utility values each for one of the plurality of items, based on a plurality of normalized reference utility values determined for each of the plurality of roles, and determining one or more combinations of items for recommendation based on the plurality of aggregate utility values.

Claims

1. A method for a system to generate an item recommendation, comprising:

determining, for each of a plurality of roles, a plurality of reference utility values each for one of a plurality of items;

performing a normalization on the plurality of reference utility values determined for each of the plurality of roles;

determining a plurality of aggregate utility values each for one of the plurality of items, based on a plurality of normalized reference utility values determined for each of the plurality of roles; and

determining one or more combinations of items for recommendation based on the plurality of aggregate utility values.

2. The method of claim 1, wherein the determining, for each of a plurality of roles, of a plurality of reference utility values comprises:

determining, for a consumer, a first plurality of reference utility values each for one of the plurality of items based on one or more consumer utility models;

determining, for a supplier, a second plurality of reference utility values each for one of the plurality of items based on one or more supplier utility models; and

determining, for an intermediary, a third plurality of reference utility values each for one of the plurality of items based on one or more intermediary utility models.

3. The method of claim 2, wherein the determining of the first plurality of reference utility values comprises:

determining the first plurality of reference utility values based on at least one of a first utility model for determining a probability of a consumer need for an item or a second utility model based on an item review.

4. The method of claim 2, wherein the determining of the second plurality of reference utility values comprises:

determining the second plurality of reference utility values based on at least one of a first utility model for determining a profit for the supplier or a second utility model based on a sale status of an item.

5. The method of claim 2, wherein the determining of the third plurality of reference utility values comprises:

determining, for an online retailer, the third plurality of reference utility values.

6. The method of claim 5, wherein the determining, for the online retailer, of the third plurality of reference utility values comprises:

determining the third plurality of reference utility values based on at least one of a first utility model based on a commission fee or a second utility model based on advertisement income.

7. The method of claim 1, wherein the determining of the plurality of aggregate utility values comprises:

applying a weighted method to the plurality of reference utility values determined for each of the plurality of roles, to calculate the plurality of aggregate utility values.

8. The method of claim 1, wherein the determining of the one or more combinations of items comprises:

determining the one or more combinations of items using a high utility pattern mining algorithm.

9. The method of claim 1, further comprising:

generating an item recommendation including one or more items in the determined one or more combinations.

10. The method of claim 9, wherein the generating of the item recommendation comprises:

sorting the one or more items.

11. The method of claim 9, wherein the generating of the item recommendation comprises:

determining a plurality of candidate items based on a request from a consumer;

determining a plurality of representative items for the consumer based on information regarding the consumer; and

identifying one or more items from the plurality of candidate items that are in a same determined combination with a first one of the representative items, as the one or more items included in the generated item recommendation.

12. The method of claim 11, wherein the determining of a plurality of representative items comprises:

determining a plurality of items that have been reviewed or purchased by the consumer as the plurality of representative items.

13. A system for generating an item recommendation, comprising:

a processor; and

a memory for storing instructions executable by the processor,

wherein the processor is configured to;

determine, for each of a plurality of roles, a plurality of reference utility values each for one of a plurality of items;

perform a normalization on the plurality of reference utility values determined for each of the plurality of roles;

determine a plurality of aggregate utility values each for one of the plurality of items, based on a plurality of normalized reference utility values determined for each of the plurality of roles; and

determine one or more combinations of items for recommendation based on the plurality of aggregate utility values.

14. The system of claim 13, wherein the processor is further configured to:

determine, for a consumer, a first plurality of reference utility values each for one of the plurality of items based on one or more consumer utility models;

determine, for a supplier, a second plurality of reference utility values each for one of the plurality of items based on one or more supplier utility models; and

determine, for an intermediary, a third plurality of reference utility values each for one of the plurality of items based on one or more intermediary utility models.

15. The system of claim 14, wherein the processor is further configured to:

determine the first plurality of reference utility values based on at least one of a first utility model for determining a probability of a consumer need for an item or a second utility model based on an item review.

16. The system of claim 14, wherein the processor is further configured to:

determine the second plurality of reference utility values based on at least one of a first utility model for determining a profit for the supplier or a second utility model based on a sale status of an item.

17. The system of claim 14, wherein the processor further configured to:

determine, for an online retailer, the third plurality of reference utility values.

18. The system of claim 17, wherein the processor is further configured to:

determine the third plurality of reference utility values based on at least one of a first utility model based on a commission fee or a second utility model based on advertisement income.

19. The system of claim 13, wherein the processor is further configured to:

apply a weighted method to the plurality of reference utility values determined for each of the plurality of roles, to calculate the plurality of aggregate utility values.

20. The system of claim 13, wherein the processor is further configured to:

determine the one or more combinations of items using a high utility pattern mining algorithm.

21. The system of claim 13, wherein the processor is further configured to:

generate an item recommendation including one or more items in the determined one or more combinations.

22. The system of claim 21, wherein the processor is further configured to:

sort the one or more items before generating the item recommendation.

23. The system of claim 21, wherein the processor is further configured to:

determine a plurality of candidate items based on a request from a consumer;

determine a plurality of representative items for the consumer based on information regarding the consumer; and

identify one or more items from the plurality of candidate items that are in a same determined combination with a first one of the representative items, as the one or more items included in the generated item recommendation.

24. The system of claim 23, wherein the processor is further configured to:

determine a plurality of items that have been reviewed or purchased by the consumer as the plurality of representative items.

25. A non-transitory medium including instructions, executable by a processor, for performing an item recommendation method, the method comprising:

determining, for each of a plurality of roles, a plurality of reference utility values each for one of a plurality of items;

performing a normalization on the plurality of reference utility values determined for each of the plurality of roles;

determining a plurality of aggregate utility values each for one of the plurality of items, based on a plurality of normalized reference utility values determined for each of the plurality of roles; and

determining one or more combinations of items for recommendation based on the plurality of aggregate utility values.

26. The non-transitory medium of claim 25, wherein the determining, for each of a plurality of roles, of a plurality of reference utility values comprises:

determining, for a consumer, a first plurality of reference utility values each for one of the plurality of items based on one or more consumer utility models;

determining, for a supplier, a second plurality of reference utility values each for one of the plurality of items based on one or more supplier utility models; and

determining, for an intermediary, a third plurality of reference utility values each for one of the plurality of items based on one or more intermediary utility models.

27. The non-transitory medium of claim 26, wherein the determining of the first plurality of reference utility values comprises:

determining the first plurality of reference utility values based on at least one of a first utility model for determining a probability of a consumer need for an item or a second utility model based on an item review.

28. The non-transitory medium of claim 26, wherein the determining of the second plurality of reference utility values comprises:

determining the second plurality of reference utility values based on at least one of a first utility model for determining a profit for the supplier or a second utility model based on a sale status of an item.

29. The non-transitory medium of claim 26, wherein the determining of the third plurality of reference utility values comprises:

determining, for an online retailer, the third plurality of reference utility values.

30. The non-transitory medium of claim 29, wherein the determining, for the online retailer, of the third plurality of reference utility values comprises:

determining the third plurality of reference utility values based on at least one of a first utility model based on a commission fee or a second utility model based on advertisement income.

31. The non-transitory medium of claim 25, wherein the determining of the plurality of aggregate utility values comprises:

applying a weighted method to the plurality of reference utility values determined for each of the plurality of roles, to calculate the plurality of aggregate utility values.

32. The non-transitory medium of claim 31, wherein the determining of the one or more combinations of items comprises:

determining the one or more combinations of items using a high utility pattern mining algorithm.

33. The non-transitory medium of claim 25, wherein the method further comprises:

generating an item recommendation including one or more items in the determined one or more combinations.

34. The non-transitory medium of claim 33, wherein the generating of the item recommendation comprises:

sorting the one or more items.

35. The non-transitory medium of claim 33, wherein the generating of the item recommendation comprises:

determining a plurality of candidate items based on a request from a consumer;

determining a plurality of representative items for the consumer based on information regarding the consumer; and

identifying one or more items from the plurality of candidate items that are in a same determined combination with a first one of the representative items, as the one or more items included in the generated item recommendation.

36. The non-transitory medium of claim 35, wherein the determining of a plurality of representative items comprises:

determining a plurality of items that have been reviewed or purchased by the consumer as the plurality of representative items.

37. A system to generate an item recommendation, comprising:

a database configured to store a plurality of utility models and consumer information;

a utility model management module configured to determine, for each of a plurality of roles, a plurality of reference utility values each for one of a plurality of items, based on the plurality of utility models;

a utility aggregating module configured to perform a normalization on the plurality of reference utility values determined for each of the plurality of roles, and to determine a plurality of aggregate utility values each for one of the plurality of items, based on a plurality of normalized reference utility values determined for each of the plurality of roles; and

a high utility pattern mining module configured to determine one or more combinations of items for recommendation based on the plurality of aggregate utility values.

38. The system of claim 37, further comprising:

a matching and filtering module configured to determine a plurality of candidate items based on a request from a consumer, and to determine a plurality of representative items for the consumer based on the consumer information stored in the database.

39. The system of claim 38, further comprising:

a recommendation module configured to identify one or more items from the plurality of candidate items that are in a same determined combination with a first one of the representative items, and generate an item recommendation including the one or more items.

40. The system of claim 38, wherein the matching and filtering module receives the request from a client terminal.