Real-time personalized recommendation of location-related entities

• US 9,152,726 B2
• Filed: 12/01/2010
• Issued: 10/06/2015
• Est. Priority Date: 12/01/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Lymperopoulos, Dimitrios, Liu, Jie, Dunn, Melissa Wood, Varma, Ashwini K., Wang, Fang, Chien, Jen-Hsien Kenny
• Primary Examiner(s): Chbouki, Tarek
• Application Number:
  US12/958,320
• Publication Number:
  US 20120143859A1
• Time in Patent Office: 1,770 Days
• US Class Current: 1/1
• 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 within a certain geographic area in response to a search query, comprising:

receiving a query for a geographic location-related entity of a given type, a location within a certain geographic area and a current time;

using the received query, searching mobile search logs of a mobile computing device in a real-time window of time incorporating the current time for geographic location-related entities within the certain geographic area of the given type received that were selected by users near the received location in response to a same or similar query as the received query;

ranking the geographic location-related entities within the certain geographic area selected by users from the mobile search logs by the number of times each geographic location-related entity was selected by users from the mobile search logs in response to the same or similar query as the received query in the real-time window of time incorporating the current time; and

outputting the ranked list of the geographic location-related entities most frequently selected by users within the certain geographic area in the real-time window of time incorporating the current time 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 mobile search logs based on time-dependent group membership preferences before searching the mobile 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 mobile search log data to create a ranked list for the window of time, the time window associated with the current time is selected to be in the same period as the input time on a previous day.

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

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

receiving a query for a location-related entity type at a current time and geographic location within a certain geographic area;

receiving mobile search logs of a mobile computing device associated with the received query and limited to a window of time, determined based on query volume, proximate to the current time;

using the received query, searching the mobile search logs in the window of time proximate to the current time for location-related entities within the certain geographic area of the location-related entity type received that were selected by users from the mobile search logs near the input location in response to the same or similar query as the received query in the window of time proximate to the current time;

ranking the location-related entities within the certain geographic area selected by users by the number of times each location-related entity type was selected by users from the received mobile search logs in the window of time proximate to the current time; and

outputting a ranked list of the location-related entities most frequently selected by users within the certain geographic area in the window of time proximate to the current time.

11. The computer-implemented process of claim 10, further comprising re-ranking the ranked list of location-related entities 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 mobile 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 mobile search logs.

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

a user that input the query selecting a location-related entity from the ranked list; and

updating the mobile search logs to show the user selected the selected location-related entity 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-related entity from the ranked list of location-related entities; and

updating the user'"'"'s time-dependent user preferences to reflect the location-related entity 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 for determining popular location-related entities around a given location at a given time, comprising:

a computing device;

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

receive a query to search mobile search logs of a mobile computing device for a type of geographic location-related entity at a given location within a certain geographic area at a current time;

filter the mobile search logs based on group membership of a user that entered the query;

search the filtered mobile search logs for the type of geographic location-related entity at the given location selected by users from the filtered mobile search logs near the input location in response to the same or similar query as the received query in a window proximate to the current time;

rank each geographic location-related entity within the geographic area according to the number of times the geographic location-related entity was selected from the filtered mobile search logs in the window proximate to the current time in response to the same or similar query as the input query;

output a ranked list of geographic location-related entities most frequently selected by users within the geographic area in a window of time incorporating the current time.

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 mobile 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 mobile search log data comprising social network data.