Future location determination using social networks

• US 8,031,595 B2
• Filed: 08/21/2007
• Issued: 10/04/2011
• Est. Priority Date: 08/21/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hamilton, Rick A. II, O'Connell, Brian M., Katz, Neil A., Walker, Keith R.
• Primary Examiner(s): JAIN, RAJ K
• Application Number:
  US11/842,214
• Publication Number:
  US 20090054043A1
• Time in Patent Office: 1,505 Days
• Field of Search: None
• US Class Current: 370/230
• CPC Class Codes: G01S 5/0284 Relative positioning
• CPC Class Codes: G01S 5/0294 Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
• CPC Class Codes: H04M 3/42357 where the information is provided to a monitoring entity such as a potential calling party or a call processing server
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/21 for social networking applications
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

A computer-implemented method of predicting a future location of a mobile node can include determining a current location of a first mobile node, determining a location of at least a second mobile node, wherein the second mobile node is associated with the first mobile node via a social network, and generating a list including at least one candidate destination determined, at least in part, according to the location of the first mobile node and the location of the second mobile node. For each candidate destination on the list, a probability that the first mobile node is in route to that candidate destination location can be calculated. A candidate destination can be selected, according to the probabilities, from the list as a predicted future location of the first mobile node. The predicted future location of the first mobile node can be output.

Claims

1. A method of predicting a future location of a first mobile node comprising:

via a processor, determining a location of at least a second mobile node, wherein the second mobile node is associated with the first mobile node via a social network;

via the processor, generating a list comprising at least one candidate destination determined, at least in part, according to the location of the first mobile node and the location of the second mobile node;

for each candidate destination on the list, via the processor, calculating a probability that the first mobile node is in route to the candidate destination;

via the processor, selecting a candidate destination, according to the probabilities, from the list as a predicted future location of the first mobile node; and

via the processor, outputting the predicted future location of the first mobile node.

2. The method of claim 1, further comprising, via the processor, determining that the second mobile node is located within a predetermined distance of the first mobile node and that each candidate destination on the list is located within a predetermined distance of the second mobile node.

3. The method of claim 1, further comprising, via the processor, selecting the location of the second mobile node to be the at least one candidate destination of the list.

4. The method of claim 1, further comprising, via the processor, calculating a heading of the first mobile node, wherein calculating the probability further comprises increasing the probability for each candidate destination on the list located within a predetermined distance from a point on a path along the heading.

5. The method of claim 1, further comprising, via the processor, determining that the first mobile node is currently traveling along a route previously traveled by the first mobile node, wherein calculating the probability further comprises increasing the probability of each candidate destination on the list located within a predetermined distance of a point on the route currently traveled by the first mobile node.

6. The method of claim 1, further comprising, via the processor, identifying at least one candidate destination on the list as a destination previously visited by the first mobile node, wherein calculating the probability further comprises increasing the probability of each candidate destination on the list previously visited by the first mobile node.

7. The method of claim 1, wherein calculating the probability further comprises increasing the probability of each candidate destination according to a current time stamp and a schedule associated with the first mobile node.

8. The method of claim 1, further comprising:

via the processor, determining a measure of time that a third mobile node is proximate to the first mobile node; and

via the processor, selectively adding the third mobile node to the social network of the first mobile node according to the measure of time that the third mobile node is proximate to the first mobile node.

9. The method of claim 1, wherein a location of each of a plurality of second mobile nodes is determined, wherein calculating the probability further comprises:

via the processor, identifying each candidate destination on the list associated with two or more of the plurality of second mobile nodes; and

via the processor, for each identified candidate destination, increasing the probability of the candidate destination according to a number of the plurality of second mobile nodes associated with the candidate destination.

10. A method of predicting a future location of a mobile node comprising:

via a processor, determining a location for each of a plurality of mobile nodes associated with a base mobile node through a social network;

via the processor, for each of the plurality of mobile nodes, identifying at least one candidate destination within a predetermined distance of the mobile node;

via the processor, for each candidate destination, calculating a probability that the base mobile node is in route to the candidate destination, at least in part, according to a measure of connectivity between the base mobile node and the mobile node associated with each respective candidate destination;

via the processor, selecting a candidate destination, according to the probabilities, as a predicted future location of the base mobile node; and

via the processor, outputting the predicted future location of the base mobile node.

11. The method of claim 10, wherein identifying at least one candidate destination comprises, for at least one mobile node, identifying the location of the mobile node as the candidate destination associated with the mobile node.

12. The method of claim 10, further comprising, via the processor, identifying at least one candidate destination as a destination previously visited by the base mobile node, wherein calculating the probability further comprises, via the processor, increasing the probability of each candidate destination identified as a destination previously visited by the base mobile node.

13. The method of claim 10, further comprising, via the processor, determining that the base mobile node is traveling along a route previously traveled by the base mobile node, wherein calculating the probability further comprises, via the processor, increasing the probability of each candidate destination located within a predetermined distance of a point on the route currently traveled by the base mobile node.

14. The method of claim 10, wherein calculating the probability further comprises, via the processor, increasing the probability of each candidate destination according to a current time and a schedule associated with the based mobile node.

15. A computer program product comprising:

a computer-readable medium having computer-usable program code stored thereon to be executed by a processor for performing the steps of;

determining a location of at least a second mobile node, wherein the second mobile node is associated with the first mobile node via a social network;

generating a list comprising at least one candidate destination determined, at least in part, according to the location of the second mobile node;

for each candidate destination on the list, calculating a probability that the first mobile node is in route to that candidate destination;

selecting a candidate destination, according to the probabilities, from the list as a predicted future location of the first mobile node; and

outputting the predicted future location of the first mobile node.

16. The computer program product of claim 15, further comprising computer-usable program code for performing the step of determining that the second mobile node is located within a predetermined distance of the first mobile node and that each candidate destination on the list is located within a predetermined distance of the second mobile node.

17. The computer program product of claim 15, further comprising computer-usable program code for performing the step of selecting the location of the second mobile node as the at least one candidate location of the list.

18. The computer program product of claim 15, further comprising computer-usable program code for performing the step of calculating a heading of the first mobile node, wherein calculating the probability further comprises increasing the probability for each candidate destination on the list located within a predetermined distance from a point on a path along the heading.

19. The computer program product of claim 15, further comprising computer-usable program code for performing the step of determining that the first mobile node is currently traveling along a route previously traveled by the first mobile node, wherein calculating the probability further comprises increasing the probability of each candidate destination on the list located within a predetermined distance of a point on the route currently traveled by the first mobile node.

20. The computer program product of claim 15, further comprising computer-usable program code for performing the step of identifying at least one candidate destination on the list as a destination previously visited by the first mobile node, wherein calculating the probability further comprises increasing the probability of each candidate destination on the list previously visited by the first mobile node.