Adaptive recommendation system

• US 9,208,155 B2
• Filed: 09/09/2011
• Issued: 12/08/2015
• Est. Priority Date: 09/09/2011
• Status: Active Grant

• Current Assignee: Rovi Technologies Corporation (Adeia Inc.)
• Original Assignee: Rovi Technologies Corporation (Adeia Inc.)
• Inventors: Nice, Nir, Kremer, Dror, Sitton, Daniel, Feldman, Michael, Shlevich, Shimon, Folger, Ori
• Primary Examiner(s): Wong, Lut
• Application Number:
  US13/229,482
• Publication Number:
  US 20130066819A1
• Time in Patent Office: 1,551 Days
• Field of Search: 706/14
• US Class Current: 1/1
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A recommendation system for optimizing content recommendation lists is disclosed. The system dynamically tracks a list interaction history of a user, which details that user'"'"'s interactions with a plurality of different lists presenting different recommended items to that user. The system automatically correlates one or more list preferences with that user based on the list interaction history, and builds a recommendation list with a plurality of candidate items having different recommendation confidences. The recommendation list is built such that each candidate item with a higher recommendation confidence is prioritized over each candidate item with a lower recommendation confidence according to the one or more list preferences correlated to that user.

Claims

1. A recommendation system, comprising:

a logic subsystem comprising a processor; and

a data-holding subsystem holding instructions executable by the processor to;

generate for display a list of recommended items to a user, each recommended item having a different position in the list relative to each other recommended item of the list;

dynamically track a list interaction history of a user, the list interaction history detailing list attributes of recommended items with which that user interacts, wherein the list attributes are independent of content attributes of such recommended items and wherein a list attribute of the list attributes describes a position in the list corresponding to a recommended item;

for each position in the list, calculate a frequency with which the user interacts with an item in said position based on the list attribute of the list interaction history;

identify a position which the user has previously demonstrated a greatest frequency of interaction based on the frequency calculated for each respective position in the list; and

build a recommendation list with a plurality of candidate items having different recommendation confidences such that a candidate item having a highest recommendation confidence is presented in the identified position.

2. The system of claim 1, wherein the list attributes for each recommended item comprise one or more of a size of that item on a user interface, a color of that item on the user interface, a position of that item on the user interface, and a font of that item on the user interface.

3. The system of claim 1, wherein the list attributes for each recommended item comprise a number of columns of a list in which that item is presented.

4. The system of claim 1, wherein the list attributes for each recommended item comprise a number of subheadings on a list in which that item is presented.

5. The system of claim 1, wherein the list attributes for each recommended item comprise whether that item includes one or more of a picture and an animation.

6. The system of claim 1, wherein the list attributes for each recommended item comprise an amount of textual information displayed on the user interface along with that item.

7. The system of claim 1, wherein the list attributes for each recommended item comprise a length of a list in which that item is presented.

8. The system of claim 1, wherein the list attributes for each recommended item comprise whether that item is from a “

recommended for you”

subgroup, from a “

social”

subgroup, or from a “

popular”

subgroup.

9. The system of claim 1, wherein the recommendation confidences are determined by a collaborative filter.

10. The system of claim 1, wherein the recommendation confidences are determined by a features filter.

11. A method of providing recommendations, comprising:

generating for display a list of recommended items to a user, each recommended item having a different position in the list relative to each other recommended item of the list;

dynamically tracking a list interaction history of a user, the list interaction history detailing list attributes of recommended items with which that user interacts, wherein the list attributes are independent of content attributes of such recommended items and wherein a list attribute of the list attributes describes a position in the list corresponding to a recommended item;

for each position in the list, calculating a frequency with which the user interacts with an item in said position based on the list attribute of the list interaction history;

identifying a position which the user has previously demonstrated a greatest frequency of interaction based on the frequency calculated for each respective position in the list; and

building a recommendation list with a plurality of candidate items having different recommendation confidences such that a candidate item having a highest recommendation confidence is presented in the identified position.

12. The method of claim 11, wherein the list attributes for each recommended item comprise one or more of a size of that item on a user interface, a position of that item on the user interface, a color of that item on the user interface, and a font of that item on the user interface.

13. The method of claim 11, wherein the list attributes for each recommended item comprise a number of columns of a list in which that item is presented.

14. The method of claim 11, wherein the list attributes for each recommended item comprise a number of subheadings on a list in which that item is presented.

15. The method of claim 11, wherein the list attributes for each recommended item comprise whether that item includes one or more of a picture and an animation.

16. The method of claim 11, wherein the list attributes for each recommended item comprise an amount of textual information displayed on the user interface along with that item.

17. The method of claim 11, wherein the list attributes for each recommended item comprise a length of a list in which that item is presented.

18. The method of claim 11, wherein the list attributes for each recommended item comprise whether that item is from a “

recommended for you”

subgroup, from a “

social”

subgroup, or from a “

popular”

subgroup.

19. The method of claim 11, wherein the recommendation confidences are determined by a collaborative filter.

20. The method of claim 11, wherein the recommendation confidences are determined by a features filter.