Wireless network connectivity prediction based on user patterns and behavior

• US 9,883,331 B2
• Filed: 03/30/2012
• Issued: 01/30/2018
• Est. Priority Date: 03/30/2012
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Agerstam, Mats, Srikanteswara, Srikathyayani Kathyayani
• Primary Examiner(s): Eng, George
• Assistant Examiner(s): Gao, Jing
• Application Number:
  US13/997,819
• Publication Number:
  US 20140287773A1
• Time in Patent Office: 2,132 Days
• CPC Class Codes: G01S 5/0252 Radio frequency fingerprinting
• 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 48/16 Discovering, processing access restriction or access information
• CPC Class Codes: H04W 48/18 Selecting a network or a communication service
• CPC Class Codes: H04W 52/0251 using monitoring of local events, e.g. events related to user activity
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

Disclosed in some examples is a method including determining a plurality of user locations, the plurality of user locations determined based upon a clustering of wireless networks scanned by a network interface card communicatively coupled to the processor during an active period of the processor; determining a current location of the user, the current location being one of the plurality of user locations; and scanning for a plurality of wireless networks associated with one or more next locations, the one or more next locations selected from the plurality of user locations based upon the current user location and a measured probability.

Claims

1. A method comprising:

activating a network interface card coupled to one or more processors, the one or more processors alternating between an active state and a low power state;

determining a plurality of locations for the network interface card using the one or more processors, the plurality of locations for the network interface card determined based upon a clustering of wireless networks scanned by the network interface card during an active period of the one or more processors, the one or more processors operating in the active state during the active period;

determining a current location of the network interface card, the current location being one of the plurality of locations for the network interface card, wherein determining the current location of the network interface card is completed upon initiating a transition of the one or more processors from the active state to the low power state; and

scanning, in the low power state, for a plurality of wireless networks associated with one or more next locations, the one or more next locations selected from the plurality of locations for the network interface card based upon the current location of the network interface card and a set of measured probabilities, wherein each measured probability indicates a probability that the network interface card is at one or more of the next locations, wherein the plurality of wireless networks includes wireless networks associated with the one or more next locations in proportion to the measured probabilities, and wherein selected wireless networks associated with the one or more next locations have a higher historical signal strength than unselected wireless networks associated with the one or more next locations.

2. The method of claim 1, comprising determining the current location of the network interface card based upon a comparison of a plurality of wireless networks currently scanned and a plurality of wireless networks associated with the plurality of locations for the network interface card.

3. The method of claim 1, wherein determining a plurality of locations for the network interface card using one or more processors comprises:

creating a plurality of traces, each trace containing a list of a plurality of wireless network identifiers scanned during a particular period of time;

dividing the plurality of traces into a plurality of segments, each segment comprising at least two traces, the at least two traces grouped into the segment based upon a uniformity of the wireless network identifiers associated with the at least two segments; and

creating a plurality of clusters comprised of at least two segments based upon a similarity of the at least two segments, each of the plurality of clusters corresponding to a location.

4. The method of claim 3, wherein the plurality of clusters are created using a K-means algorithm.

5. The method of claim 3, comprising determining a plurality of wireless network identifiers associated with the plurality of clusters based upon a determination that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location.

6. The method claim 5, wherein the determination that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location comprises determining that the wireless network identifiers associated with particular location are present in that location above a threshold amount of times.

7. The method of claim 1, wherein the wireless networks are wireless networks operating in accordance with an 802.11 family of standards.

8. The method of claim 1, comprising calculating a transition matrix based upon the clustering of similar wireless networks scanned and wherein determining the one or more next locations comprises determining a most probable next locations based upon the transition matrix and the current location of the network interface card.

9. The method of claim 1, wherein scanning for the plurality of wireless networks is done in response to powering down the one or more processors into the low power state.

10. The method of claim 1, wherein responsive to finding one of the plurality of networks associated with one or more next locations, connecting to the found one or more of the plurality of networks, wherein connecting to the found one or more of the plurality of networks includes transitioning the one or more processors from the low power state to the active state.

11. The method of claim 10, comprising waking up one or more of the processors and notifying one or more applications to synchronize data over the connected wireless network responsive to connecting to the found one or more of the plurality of networks.

12. An apparatus of a s (STA), the apparatus comprising:

memory; and

one or more processors, in combination with the memory, configured to;

determine a plurality of STA locations, the plurality of STA locations determined based upon a clustering of wireless networks scanned by a network interface card communicatively coupled to the processor during an active period of the one or more processors, the one or more processors operating in an active state during the active period;

determine a current location of the STA, the current location being one of the plurality of STA locations, wherein the determination of the current location of the STA is completed upon initiation of a transition of the one or more processors from the active state to a low power state; and

scan, in the low power state, for a plurality of wireless networks associated with one or more next locations, the one or more next locations selected from the plurality of STA locations based upon the current STA location and a set of measured probabilities, wherein each measured probability indicates a probability that the STA is at one or more of the next locations, wherein the plurality of wireless networks includes wireless networks associated with the one or more next locations in proportion to the measured, probabilities and wherein selected wireless networks associated with the one or more next locations have a higher historical signal strength than unselected wireless networks associated with the one or more next locations.

13. The apparatus of claim 12, wherein the one or more processors are configured to determine the current location of the STA based upon a comparison of a plurality of wireless networks currently scanned and a plurality of wireless networks associated with the plurality of STA locations.

14. The apparatus of claim 12, wherein the one or more processors are configured to determine a plurality of STA locations by:

creating a plurality of traces, each trace containing a list of a plurality of wireless network identifiers scanned during a particular period of time;

dividing the plurality of traces into a plurality of segments, each segment comprising at least two traces, the at least two traces grouped into the segment based upon a uniformity of the wireless network identifiers associated with the at least two segments; and

creating a plurality of clusters comprised of at least two segments based upon a similarity of the at least two segments, each of the plurality of clusters corresponding to a location.

15. The apparatus of claim 14, wherein the plurality of clusters are created using a K-means algorithm.

16. The apparatus of claim 14, wherein the one or more processors are configured to determine a plurality of wireless network identifiers associated with the plurality of clusters based upon a determination that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location.

17. The apparatus of claim 16, wherein the one or more processors are configured to determine that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location by determining that the wireless network identifiers associated with a particular location are present in that location above a threshold amount of times.

18. The apparatus of claim 12, wherein the wireless networks are wireless networks operating in accordance with an 802.11 family of standards.

19. The apparatus of claim 12, wherein the one or more processors are configured to calculate a transition matrix based upon the clustering of similar wireless networks scanned and wherein the one or more processors are configured to determine the one or more next locations by determining a most probable next locations based upon the transition matrix and the current STA location.

20. apparatus of claim 12, wherein the one or more processors are configured to scan for the plurality of wireless networks in response to powering down the one or more processors into the low power state.

21. The apparatus of claim 12, wherein the one or more processors are configured to connect to the found one or more of the plurality of networks in response to finding one of the plurality of networks associated with one or more next locations, wherein configuring the one or more processors to connect to the found one or more of the plurality of networks transitions the one or more processors from the low power state to the active state.

22. The apparatus of claim 21, wherein the one or more processors are configured to wake up and notify one or more applications to synchronize data over the connected wireless network responsive to connecting to the found one or more of the plurality of networks.

23. A non-transitory machine readable medium that stores instructions which when performed by an apparatus of a station (STA) machine, cause the STA machine to perform operations comprising:

determine a plurality of STA machine locations, the plurality of STA machine locations determined based upon a clustering of wireless networks scanned by a network interface card communicatively coupled to one or more processors during an active period of the one or more processors, the one or more processors operating in an active state during the active period;

determine a current location of the STA machine, the current location being one of the plurality of STA machine locations, wherein the determination of the current location of the STA machine is completed upon initiating a transition of the one or more processors from the active state to a low power state; and

scan, in the low power state, for a plurality of wireless networks associated with one or more next locations, the one or more next locations selected from the plurality of STA machine locations based upon the current STA machine location and a set of measured probabilities, wherein each measured probability indicates a probability that the STA machine is at one or more of the next locations, and wherein the plurality of wireless networks includes wireless networks associated with the one or more next locations in proportion to the measured probabilities, wherein selected wireless networks associated with the one or more next locations have a higher historical signal strength than unselected wireless networks associated with the one or more next locations.

24. The non-transitory machine readable medium of claim 23, wherein the instructions for determining the current location of the STA machine include instructions, which when performed by the apparatus of the STA machine, cause the apparatus of the STA machine to determine the current location of the STA machine based upon a comparison of a plurality of wireless networks currently scanned and a plurality of wireless networks associated with the plurality of STA machine locations.

25. The non-transitory machine readable medium of claim 23, wherein the instructions for determining a plurality of STA machine locations comprise instructions which when performed by the apparatus of the STA machine, cause the apparatus of the STA machine to perform the operations of:

creating a plurality of traces, each trace containing a list of a plurality of wireless network identifiers scanned during a particular period of time;

dividing the plurality of traces into a plurality of segments, each segment comprising at least two traces, the at least two traces grouped into the segment based upon a uniformity of the wireless network identifiers associated with the at least two segments; and

creating a plurality of clusters comprised of at least two segments based upon a similarity of the at least two segments, each of the plurality of clusters corresponding to a location.

26. The non-transitory machine readable medium of claim 25, wherein the instructions for creating a plurality of clusters include instructions which when performed by the apparatus of the STA machine cause the apparatus of the STA machine to create the plurality of clusters using a K-means algorithm.

27. The non-transitory machine readable medium of claim 25, wherein the instructions for determining the plurality of wireless network identifiers associated with the plurality of clusters comprises instructions, which when performed by the apparatus of the STA machine, cause the apparatus of the STA machine to determine the plurality of wireless network identifiers based upon a determination that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location.

28. The non-transitory machine readable medium of claim 27, wherein the instructions for determining that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location includes instructions which when performed by the apparatus of the STA machine causes the apparatus of the STA machine to perform the operations of determining that the wireless network identifiers associated with a particular location are present in that location above a threshold amount of times.

29. The non-transitory machine readable medium of claim 23, wherein the wireless networks are wireless networks operating in accordance with an 802.11 family of standards.

30. The non-transitory machine readable medium of claim 23, wherein the instructions include instructions which when performed by the apparatus of the STA machine, cause the apparatus of the STA machine to perform the operations of calculating a transition matrix based upon the clustering of similar wireless networks scanned and wherein the instructions for determining the one or more next locations include instructions, which when performed by the apparatus of the STA machine cause the apparatus of the STA machine to perform the operations of determining a most probable next locations based upon the transition matrix and the current STA machine location.

31. The non-transitory machine-readable medium of claim 23, wherein the instructions include instructions which when performed by the apparatus of the STA machine cause the apparatus of the STA machine to scan for the plurality of wireless networks in response to powering down the one or more processors into the low power state.

32. The non-transitory machine-readable medium of claim 23, wherein the instructions include instructions which when performed by the apparatus of the STA machine cause the apparatus of the STA machine to perform the operations of:

responsive to finding one of the plurality of networks associated with one or more next locations, connecting to the found one or more of the plurality of networks, wherein connecting to the found one or more of the plurality of networks includes transitioning the one or more processors from the low power state to the active state.

33. The non-transitory machine-readable medium of claim 32, wherein the instructions include instructions which when performed by the apparatus of the STA machine cause the apparatus of the STA machine to perform the operations of:

waking up the processor and notifying one or more applications to synchronize data over the connected wireless network responsive to connecting to the found one or more of the plurality of networks.

34. An apparatus comprising:

at least one processor;

a network interface card; and

at least one machine readable medium including instructions that, when executed by the at least one processor, configure the at least one processor to complete operations to;

determine a plurality of user locations, the plurality of user locations determined based upon a clustering of wireless networks seen by a computing device during an active period of the computing device;

determine a current location of the user, the current location being one of the plurality of user locations, wherein the determination of the current location of the user is completed upon initiation of a transition of the computing device from an active period to an inactive period;

select one or more next locations from the plurality of user locations based upon the current user location and a set of measured probabilities, wherein each measured probability indicates a probability that the user is at one or more of the next locations, wherein the plurality of wireless networks includes wireless networks associated with the one or more next locations in proportion to the measured probabilities, wherein selected wireless networks associated with the one or more next locations have a higher historical signal strength than unselected wireless networks associated with the one or more next locations, and wherein selecting the one of more next locations is completed during the inactive period of the computing device; and

output the plurality of wireless networks associated with one or more next locations to the network interface card.

35. The apparatus of claim 34, wherein the instructions further configure the at least one processor to perform operations to determine the current location of the user based upon a comparison of a plurality of wireless networks currently scanned and a plurality of wireless networks associated with the plurality of user locations.

36. The apparatus of claim 34, wherein the instructions further configure the at least one processor to perform operations to:

create a plurality of traces, wherein each trace contains a list of a plurality of wireless network identifiers scanned during a particular period of time;

divide the plurality of traces into a plurality of segments, each segment comprising at least two traces, the at least two traces grouped into the segment based upon a uniformity of the wireless network identifiers associated with the at least two segments; and

create a plurality of clusters comprised of at least two segments based upon a similarity of the at least two segments, wherein each of the plurality of clusters corresponds to a location.

37. The apparatus of claim 36, wherein the instructions further configure the at least one processor to perform operations to determine a plurality of wireless network identifiers associated with the plurality of clusters based upon a determination that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location.

38. The apparatus of claim 37, wherein the instructions further configure the at least one processor to perform operations to determine that the wireless network identifiers associated with the plurality of clusters are likely to be available at the associated location by determining that the wireless network identifiers associated with a particular location are present in that location above a threshold amount of times.

39. The apparatus of claim 34, wherein the instructions further configure the at least one processor to perform operations to calculate a transition matrix based upon the clustering of similar wireless networks scanned and wherein the selection module is configured to determine the one or more next locations by determining a most probable next locations based upon the transition matrix and the current user location.