SYSTEMS AND METHODS FOR REAL-TIME LOCATION-AWARE RECOMMENDATIONS

• US 20130024471A1
• Filed: 07/20/2012
• Published: 01/24/2013
• Est. Priority Date: 07/20/2011
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Mitrovic, Ivan
• Granted Patent: US 10,114,901 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

Systems and methods for real-time location-aware recommendations are discussed herein. In an example, a method for generating location-aware recommendations can include receiving a current location of a user, calculating a place graph for the user, traversing the place graph, selecting a recommendation, and communicating the recommendation. In this example, the place graph is calculated based on the current location. Traversing the place graph can identify one or more potential recommendations within a pre-defined distance of the current location,

Claims

1. A method for generating location-aware recommendations, the method comprising:

receiving information specifying a current location of a user;

calculating, on-the-fly, a place graph for the user based on the current location;

traversing the place graph, using one or more processors, to identify one or more potential place recommendations within a pre-defined distance of the current location;

selecting a local place recommendation for the user from the one or more potential place recommendations; and

communicating the local place recommendation to the user.

2. The method of claim 1, wherein the calculating the place graph includes:

accessing user profile data for a user, the user profile data including a first plurality of places, with each place of the first plurality of places including interaction history recorded within the user profile data;

extracting a feature matrix from the first plurality of places;

accessing place data for a second plurality of places within the current location; and

projecting the feature matrix from the first plurality of places onto the second plurality of places within the current location.

3. The method claim 2, wherein the extracting the feature matrix from the first plurality of places includes scoring features within the feature matrix based on the user profile data associated with the first plurality of places.

4. The method of claim 3, wherein the scoring the features includes scoring the features based on explicit user input regarding one or more of the first plurality of places.

5. The method of claim 4, wherein the scoring the features based on explicit user input includes scoring the features based on one or more of the following explicit inputs:

a user supplied rating;

a review;

a related check-in; and

a user saving a place into an address book.

6. The method of claim 4, wherein the scoring the features includes scoring the features based on implicit user input regarding the one or more of the first plurality of places.

7. The method of claim 6, wherein the scoring the features includes applying a first weighting factor to the explicit user input regarding the one or more of the first plurality of places and a second weighting factor to the implicit user input regarding the one or more of the first plurality of places.

8. The method of claim 2, wherein the traversing the place graph includes analyzing the second plurality of places to identify the one or more potential place recommendations.

9. The method of claim 1, wherein the selecting the local place recommendation includes filtering the one or more potential place recommendations based on time of day.

10. A system comprising:

a server coupled to a network, the server including,

a location module configured to determine a current location associated with a user accessing the server over the network;

a place graph module configured to calculate, on-the-fly, a place graph for the user based on the current location;

a recommendation engine configured to,

traverse the place graph to identify one or more potential place recommendations within a pre-defined distance of the current location, and

select a local place recommendation for the user from the one or more potential place recommendations; and

a processor-executed publication application configured to communicate the local place recommendation to the user over the network.

11. The system of claim 10, wherein the place graph module is further configured to:

access user profile data for a user, the user profile data including a first plurality of places, with each place of the first plurality of places including interaction history recorded within the user profile data;

extract a feature matrix from the first plurality of places;

access place data for a second plurality of places within the current location; and

project the feature matrix from the first plurality of places onto the second plurality of places within the current location.

12. The system of claim 11, wherein the place graph module is further configured to score features within the feature matrix based on the user profile data associated with the first plurality of places.

13. The system of claim 12, wherein the place graph module is further configured to score the features based on explicit user input regarding one or snore of the first plurality of places.

14. The system of claim 13, wherein the place graph module is further configured to score the features based on implicit user input regarding the one or more of the first plurality of places.

15. The system of claim 14, wherein the place graph module is further configured to apply a first weighting factor to the explicit user input regarding the one or more of the first plurality of places and a second weighting factor to the implicit user input regarding the one or more of the first plurality of places.

16. The system of claim 11, wherein the recommendation engine is further configured to analyze the second plurality of places to identify the one or more potential place recommendations.

17. A machine-readable storage medium containing instructions that, when executed by a networked system, cause the networked system to:

receive information specifying a current location of a user;

calculate, on-the-fly, a place graph for the user based on the current location;

traverse the place graph to identify one or more potential place recommendations within a pre-defined distance of the current location;

select a local place recommendation for the user from the one or more potential place recommendations; and

communicate the local place recommendation to the user.

18. The machine-readable storage medium of claim 17, wherein the instructions that cause the networked system to calculate the place graph include instructions that cause the networked system to:

access user profile data for a user, the user profile data including a first plurality of places, with each place of the first plurality of places including interaction history recorded within the user profile data;

extract a feature matrix from the first plurality of places;

access place data for a second plurality of places within the current location; and

project the feature matrix from the first plurality of places onto the second plurality of places within the current location.

19. The machine-readable storage medium of claim 18, wherein the instructions that cause the networked system to extract the feature matrix from the first plurality of places include instructions that cause the networked system to score features within the feature matrix based on the user profile data associated with the first plurality of places.

20. The machine-readable storage medium of claim 19, wherein the instructions that cause the networked system to score the features include instructions that cause the networked system to score the features based on explicit user input regarding one or more of the first plurality of places and to score the features based on implicit user input regarding the one or more of the first plurality of places.