DETERMINING POINTS OF INTEREST USING INTELLIGENT AGENTS AND SEMANTIC DATA

• US 20150254278A1
• Filed: 05/21/2015
• Published: 09/10/2015
• Est. Priority Date: 11/24/2010
• Status: Active Grant

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: GLACHANT, Mathieu J. R., JENKINS, Alvin, RAMANATHAN, Sri, TERRY, Matthew A., TREVATHAN, Matthew B.
• Granted Patent: US 9,646,026 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

A method, a system, and a computer program product are provided for determining points of interest using intelligent agents and semantic data. The method is implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium having programming instructions operable for receiving a media data comprising a location data comprising where media was captured. The instructions are also operable for determining at least one point of interest based on the media data, tying the media data to the at least one point of interest, and providing the media data tied to the at least one point of interest to an end user.

Claims

1. A method comprising:

receiving, by a computer processor, media data comprising location data that includes where media was captured; and

determining, by the computer processor, a center of a cluster of the media based on the location data and direction data comprising a direction a device was pointing to capture the media;

wherein the determining the center of the cluster of the media comprises;

determining a geographic center of the media based on an average midpoint of the location data;

determining an azimuth-based center of the media based on an intersection of the direction data; and

determining a hybrid center as the center of the cluster of the media based on the geographic center and the azimuth-based center.

2. The method of claim 1, further comprising receiving semantic data comprising at least one of a description and an event for the location data of the media.

3. The method of claim 2, further comprising determining at least one point of interest based on the media data, the center of the cluster of the media, and the semantic data.

4. The method of claim 3, wherein the determining of the at least one point of interest based on the geographic center comprises:

plotting a predetermined area around the geographic center; and

determining whether at least one current point of interest falls within the predetermined area.

5. The method of claim 3, wherein the determining of the at least one point of interest comprises determining the semantic data based on the media data.

6. The method of claim 3, wherein the determining of the at least one point of interest comprises:

determining at least one current point of interest based on the media data; and

determining the at least one point of interest based on the at least one current point of interest.

7. The method of claim 3, further comprising tying the media data to the semantic data related to the at least one point of interest,

wherein the tying the media data to the semantic data comprises:

determining a level of confidence that the media data is related to the semantic data; and

inferring the media data is related to the semantic data if the level of confidence is greater than or equal to a predetermined threshold.

8. The method of claim 3, further comprising:

tying the media data to the at least one point of interest; and

providing the media data tied to the at least one point of interest to an end user.

9. The method of claim 8, wherein the tying the media data to the at least one point of interest comprises tagging the media with the at least one point of interest.

10. A system implemented in hardware, comprising:

a media agent configured to receive media data comprising location data of where media was captured and direction data comprising a direction a device was pointing to capture the media; and

a center agent configured to determine a center of a cluster of the media,

wherein the center agent is configured to;

determine a geographic center of the cluster of the media based on an average midpoint of the location data;

determine an azimuth-based center of the cluster of the media based on an intersection of the direction data; and

determine a hybrid center as the center of the cluster of the media based on the geographic center and the azimuth-based center.

11. The method of claim 10, further comprising a semantic data agent configured to determine semantic data based on the media data, the semantic data comprising at least one of a description, and an event for the location data of the media.

12. The method of claim 11, further comprising an arbiter module configured to:

receive the media data from the media agent;

receive the center of the cluster of the media from the center agent;

receive the semantic data from the semantic data agent;

determine at least one point of interest based on the media data, the center of the cluster of the media, and the semantic data;

tie the media data to the at least one point of interest;

receive from an end user a request for the media related to the at least one point of interest; and

provide the end user at least one of another media and another media data tied to the at least one point of interest.