INFERRING USER-SPECIFIC LOCATION SEMANTICS FROM USER DATA

• US 20110029474A1
• Filed: 07/31/2009
• Published: 02/03/2011
• Est. Priority Date: 07/31/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Lin, Jyh-Han
• Granted Patent: US 8,521,680 B2
• Time in Patent Office: Days
• US Class Current: 706/50
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

Determining semantics for locations based on user data such as user activities and/or user communications. The user data is captured and analyzed to identify keywords including locations. Location data describing the locations is obtained and associated with the user and keywords. The associations represent user context for the locations. The associations are used to deliver services and/or products to the user at various times such as when user approaches or enters a particular location.

Claims

1. A system for inferring location-specific user context, said system comprising:

a memory area for storing user data for a user, said user data describing one or more of the following;

user activities and user communications; and

a processor programmed to;

perform a textual analysis of the user data stored in the memory area to identify one or more location keywords, said location keywords corresponding to one or more locations;

obtain location data for the locations corresponding to the identified location keywords;

creating one or more tags based on the obtained location data;

defining one or more associations among the user, the identified location keywords, and the created tags; and

storing, in the memory area, the defined associations as user context for the locations.

2. The system of claim 1, wherein the location keywords comprise one or more of the following:

names of places and names of people.

3. The system of claim 1, wherein the user activities comprise one or more of the following:

calendar entries, task entries, to-do lists, and shopping lists.

4. The system of claim 1, wherein the user communications comprise one or more of the following:

electronic mail messages, instant messages, text messages, blog postings, microblog postings, web site postings, voice telephone calls, and video telephone calls.

5. The system of claim 1, further comprising means for mining data associated with the user and the locations.

6. The system of claim 1, further comprising means for obtaining the location data.

7. A method comprising:

receiving user data for a user from one or more computing devices, said received user data describing one or more of the following;

user activities and user communications;

analyzing, by a processor, the received user data to identify one or more location keywords associated with the received user data, said location keywords corresponding to one or more locations;

obtaining location data for the locations corresponding to the identified location keywords;

defining, by the processor, one or more associations among the user, the identified location keywords, and the obtained location data; and

storing, by the processor in a memory area, the defined associations as user context for the locations.

8. The method of claim 7, further comprising:

selecting at least one service based on the stored associations; and

providing the selected service to the user at one or more of the locations.

9. The method of claim 7, further comprising:

creating one or more tags based on the obtained location data; and

storing the created tags with the stored associations in the memory area.

10. The method of claim 9, further comprising:

determining a present location of the user;

selecting at least one of the created tags based on the determined present location; and

presenting a user interface to the user based on the selected tags.

11. The method of claim 7, further comprising:

detecting a present location of the user;

comparing the detected location with the location keywords;

selecting at least one of the associations based on said comparing; and

presenting to the user at least a portion of the location data corresponding to the selected association.

12. The method of claim 7, further comprising generating metrics based on the received user data.

13. The method of claim 12, further comprising defining a point of interest based on the obtained location data and the generated metrics.

14. The method of claim 13, further comprising modifying a defined point of interest based on the generated metrics.

15. The method of claim 12, wherein the generated metrics comprise one or more of the following:

time spent at the locations, a wait time for an attraction, a wait time for a restaurant, and a frequency of visits to the locations.

16. One or more computer-readable media having computer-executable components, said components comprising:

a collection component that when executed by at least one processor causes the at least one processor to receive user data for a plurality of users from one or more computing devices, said received user data describing one or more of the following;

user activities and user communications;

a parser component that when executed by at least one processor causes the at least one processor to identify one or more location keywords associated with the user data received by the collection component, said location keywords corresponding to one or more locations;

a mining component that when executed by at least one processor causes the at least one processor to obtain location data for the locations corresponding to the location keywords identified by the parser component;

a memory component that when executed by at least one processor causes the at least one processor to associate the location data obtained by the mining component and the location keywords identified by the parser component with the plurality of users to define user context for the locations; and

a crowd component that when executed by at least one processor causes the at least one processor to analyze the user context defined by the memory component to identify points of interest for the plurality of users.

17. The computer-readable media of claim 16, wherein the mining component is limited by one or more of the following:

geospatial restrictions, social graph restrictions, temporal restrictions, activity restrictions, and statistical sampling.

18. The computer-readable media of claim 16, wherein the crowd component updates the points of interest based on the user context defined by the memory component.

19. The computer-readable media of claim 16, wherein the mining component accesses social networking data via a network to obtain at least a portion of the location data.

20. The computer-readable media of claim 16, wherein the memory component stores the user context as a data structures for each of the plurality of users in the form of <

user, location keywords, location data>

.