REAL-TIME PERSONALIZED RECOMMENDATION OF LOCATION-RELATED ENTITIES

• US 20120143859A1
• Filed: 12/01/2010
• Published: 06/07/2012
• Est. Priority Date: 12/01/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Lymperopoulos, Dimitrios, Liu, Jie, Dunn, Melissa Wood, Wang, Fang, Varma, Ashwini K., Chien, Jen-Hsien Kenny
• Granted Patent: US 9,152,726 B2
• Time in Patent Office: Days
• US Class Current: 707/724
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

A location-related entity ranking technique is described that allows a user see the ranking of location-related entities near a desired location in response to a query. The technique can leverage the searches performed by a community of mobile device users at a given location and at a given time to infer the location-related entities that are popular at this specific location and time window. The technique can also filter out or re-rank these location-related entities based on the personal preferences of the person that submits the query and group preferences of a group to which the user belongs. The personal preferences can also be context specific (i.e. different restaurant preferences for lunch and dinner times).

Claims

1. A computer-implemented process for ranking location-related entities in response to a search query, comprising:

inputting a query for a location-related entity of a given type, a location and a time;

searching search logs in a window of time associated with the input time for location-related entities of type input that were selected by users from the search logs near the input location in response to the same or similar query;

ranking the location-related entities selected by users by the number of times each location-related entity was selected by users from the search logs in response to the same or similar query; and

outputting the ranked list of the location-related entities to a user.

2. The computer-implemented process of claim 1, further comprising re-ranking the ranked list of location-related entities based on time-dependent user preferences of a user that input the query before outputting the ranked list of location-related entities.

3. The computer-implemented process of claim 2, wherein the user preferences vary based on the user'"'"'s location.

4. The computer-implemented process of claim 1, further comprising determining time-dependent group memberships by grouping users by time, location, query and query results.

5. The computer-implemented process of claim 4, further comprising filtering the search logs based on time-dependent group membership preferences before searching the search logs.

6. The computer-implemented process of claim 5, wherein the groups a user belongs to can change over different periods of time and location.

7. The computer-implemented process of claim 1, wherein the time window is selected based on the time the query was entered.

8. The computer-implemented process of claim 7, wherein if there is not sufficient search log data to create a ranked list for the window of time, the time window associated with the input time is selected to be in the same period as the input time on a different day.

9. The computer-implemented process of claim 1, wherein the ranking of location-related entities occurs in real-time.

10. A computer-implemented process for ranking location-related entities, comprising:

inputting a query for a location type at a given time and location into a search engine;

inputting search logs associated with the input query;

searching the search logs in a window of time associated with the input given time for locations of the location type input that were selected by users from the search logs near the input location in response to the same or similar query;

ranking the locations selected by users by the number of times each location was selected by users to determine a ranked list.

11. The computer-implemented process of claim 10, further comprising re-ranking the ranked list of locations based on time-dependent user preferences of a user that input the query.

12. The computer-implemented process of claim 10, further comprising filtering the search logs based on time and location dependent group preferences of a group to which the user that input query belongs prior to searching the search logs.

13. The computer-implemented process of claim 10 further comprising the actions of:

a user that input the query selecting a location from the ranked list of locations; and

updating the search logs to show the user selected the selected location in response to the query.

14. The computer-implemented process of claim 10, further comprising the actions of:

a user that input the query selecting a location from the ranked list of locations; and

updating the user'"'"'s time-dependent user preferences to reflect the location selected by the user.

15. The computer-implemented process of claim 14, wherein the updated time-dependent user preferences further comprise:

locations the user usually visits;

types of locations the user visits; and

a distance the user is willing to go to visit a location.

16. A system computer-implemented process determining popular location-related entities around a given location, comprising:

a general purpose computing device;

a computer program comprising program modules executable by the general purpose computing device, wherein the computing device is directed by the program modules of the computer program to,

input a query to search for a type of location-related entity at a given location;

search search logs for the type of location-related entity at the given location selected by users from the search logs near the input location in response to the same or similar query;

rank each location-related entity according to the number of times the location-related entity was selected in response to the same or similar query to determine a ranked list of location-related entities.

17. The system of claim 16, further comprising a module to re-rank the ranked list by preferences of the user that entered the query that vary with time of day.

18. The system of claim 16, further comprising a module to re-rank the ranked list based on group preferences that vary with the time of day.

19. The system of claim 16, further comprising a module to use additional data sources to augment the search log data comprising phone log data.

20. The system of claim 16, further comprising a module to use additional data sources to augment the search log data comprising social network data.