Recommendations based upon explicit user similarity

Patent metadata

Field	Value
Publication number	US-10769702-B2
Application number	US-201815980396-A
Country	US
Kind code	B2
Filing date	May 15, 2018
Priority date	Mar 15, 2013
Publication date	Sep 8, 2020
Grant date	Sep 8, 2020

Abstract

A system and method for providing recommendations to individuals on a social network, in which the recommendations include information indicating the similarity of the individuals to one another, to aid the individuals in judging the degree to which the opinions of the others are applicable to the themselves.

First claim

What is claimed is:

1. A method, comprising:
characterizing a first user and a second user based on interaction information for the first user and the second user via a network;
calculating a level of similarity of the first user and the second user based on the interaction information;
providing, to the first user, a recommendation of a product or a service based on the interaction information for the first user and the second user and the similarity level;
providing, to the first user, information relating to the second user so that reasons for the similarity can be reviewed by the first user;
causing, via a selection of one or more graphical elements of a graphical user interface when the information relating to the second user is presented, a list of categories and their respective similarity levels to be presented; and
causing, via a selection of one or more graphical elements of the graphical user interface, to be presented how one or more of the similarity levels are calculated.

2. The method according to claim 1 , wherein the network comprises an e-commerce system.

3. The method according to claim 1 , wherein the interaction information is based on online social network activities of the first user and the second user via the network.

4. The method according to claim 1 , wherein the interaction information is based on implicit interactions.

5. The method according to claim 1 , wherein calculating the level of similarity of the first user and the second user comprises calculating an aggregated similarity level based on user interests and product preferences.

6. The method according to claim 1 , wherein providing the recommendation to the first user comprises providing a level of similarity of a first attribute weight vector and a second attribute weight vector.

7. The method according to claim 1 , wherein the interaction information is based on one or more of a vote on an online survey, an addition of an item to an online shopping cart, a purchase of one or more items, and an addition of an item to a catalog.

8. The method according to claim 1 , wherein calculating the level of similarity of the first user and the second user comprises calculating an aggregated similarity level based on user interests and product preferences.

9. The method according to claim 1 , wherein calculating the level of similarity of the first user and the second user comprises calculating the aggregated similarity level using answers to online surveys.

10. The method according to claim 1 , wherein characterizing the first user and the second user is with respect to attributes.

11. The method according to claim 10 , wherein calculating the level of similarity of the first user and the second user comprises adjusting a plurality of weights for each of the first user and the second user based upon a number of distinct users associated with each attribute.

12. The method according to claim 1 , wherein the list of categories and their respective similarity levels are used to determine whether opinions of the second user are useful to the first user.

13. The method according to claim 1 , comprising normalizing the calculated similarity levels for corresponding categories into different level categories.

14. The method according to claim 13 , wherein the normalized similarity levels comprise two or more different level categories.

15. The method according to claim 13 , wherein the normalized similarity levels comprise three or more different level categories.

16. The method according to claim 1 , wherein, although how one or more of the similarity levels are calculated is presented, the privacy of the second user is maintained.

17. The method according to claim 16 , wherein particular purchases of the second user are not revealed.

18. The method according to claim 1 , comprising:
expressing a strength of a relationship between the first user and each of a plurality of attributes as a plurality of weights; and
expressing a strength of a relationship between the second user and each of a plurality of attributes as a plurality of weights.

19. The method according to claim 18 , comprising calculating a metric of similarity of the first user and the second user based on the weights of the first user and the weights of the second user.

20. The method according to claim 19 , comprising expressing a graphical indication representing the similarity metric.

Assignees

• Transf Sr Brands Llc

Inventors

• Egozi Ofer
• Moran Amit
• Shamir Oren

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q10/42

  Determination of affinities or common interests between users · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title