Utilizing mobile wireless devices to analyze movement of crowds

• US 9,699,603 B2
• Filed: 10/14/2015
• Issued: 07/04/2017
• Est. Priority Date: 10/14/2015
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Shen, Zhitao, Tang, David, Liu, Hao, Zhang, Yu
• Primary Examiner(s): Ngo, Chuong A
• Application Number:
  US14/882,670
• Publication Number:
  US 20170111760A1
• Time in Patent Office: 629 Days
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 24/04 Arrangements for maintaining operational condition
• 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 64/006 with additional information processing, e.g. for direction or speed determination
• CPC Class Codes: H04W 84/12 WLAN [Wireless Local Area Networks]

Abstract

According to the techniques presented herein, location data from signals transmitted by a plurality of mobile wireless devices in a wireless network are obtained. For each mobile wireless device, location data time points are aggregated to generate a plurality of routines or paths of movement for each mobile wireless device within a predefined space. The predefined space is partitioned into a plurality of units and each routine of the plurality of routines is also partitioned into a plurality of subroutines or segments. For each unit, one or more subroutines within a predefined distance of a frequent subroutine are combined with the frequent subroutine, and the frequent subroutines may be displayed on a graphical interface to visualize aggregate movement of the plurality of mobile wireless devices within the predefined space. Frequent subroutines may be analyzed in an automated manner to generate notifications and alerts.

Claims

1. A computer-implemented method comprising:

obtaining location data from signals transmitted by a plurality of mobile wireless devices in a wireless network wherein the plurality of mobile wireless devices are moving within a predefined space, and wherein the location data comprises a plurality of location data time points;

aggregating, for each mobile wireless device, the plurality of location data time points to form sets of the location data time points for each mobile wireless device;

generating a plurality of routines from the sets of location data time points, wherein each routine is a path of movement of the respective mobile wireless device within the predefined space;

partitioning the predefined space into a plurality of units and each routine of the plurality of routines into a plurality of subroutines, wherein each subroutine is a path segment of the corresponding path of movement within a particular unit;

combining, for each unit, one or more subroutines with a respective frequent subroutine, when the one or more subroutines are within a predetermined distance of the respective frequent subroutine, and wherein the respective frequent subroutine represents an aggregate of other subroutines within the unit that are within a specified distance of each other; and

displaying frequent subroutines on a graphical user interface to visualize aggregate movement of the plurality of mobile wireless devices within the predefined space.

2. The method of claim 1, further comprising:

obtaining a first plurality of routines from a first plurality of mobile wireless devices from a database comprising historical trajectories of the first plurality of mobile wireless devices;

partitioning each routine of the first plurality of routines into a first plurality of subroutines;

clustering the first plurality of subroutines based on a distance function to form one or more clusters for each of the plurality of units; and

aggregating the clustered subroutines to form first frequent subroutines, when a number of subroutines of the first plurality of subroutines within a given cluster is above a threshold frequency value.

3. The method of claim 1, further comprising:

creating a new frequent subroutine for a group of subroutines that are outside of a predetermined distance from any frequent subroutine, when the number of subroutines in the group exceeds a threshold frequency value and are within a specified distance of each other.

4. The method of claim 1, further comprising:

determining whether a given subroutine has expired;

removing the expired subroutine from the frequent subroutine; and

updating a frequency associated with the frequent subroutine to reflect the removal of the expired subroutine.

5. The method of claim 1, wherein combining further comprises combining one or more subroutines with a first frequent subroutine, when the one or more subroutines are within a predetermined distance of the first frequent subroutine, and updating a frequency characteristic associated with the first frequent subroutine to reflect the inclusion of the one or more subroutines into the first frequent subroutine.

6. The method of claim 1, wherein displaying further comprises displaying aggregate movement of the plurality of mobile wireless devices within the predefined space to detect an anomaly, and further comprising providing a notification in response to the detected anomaly.

7. The method of claim 1, wherein each of the location data time points comprises a timestamp, a unique mobile wireless device identifier, and location information indicating where in the predefined space an associated mobile wireless device is located.

8. The method of claim 1, wherein displaying further comprising:

displaying a density of mobile wireless devices associated with each frequent subroutine in real-time.

9. An apparatus comprising:

a network interface unit configured enable network communications;

a memory; and

a processor coupled to the network interface unit and configured to;

obtain location data from signals transmitted by a plurality of mobile wireless devices in a wireless network wherein the plurality of mobile wireless devices are moving within a predefined space, and wherein the location data comprises a plurality of location data time points;

aggregate, for each mobile wireless device, the plurality of location data time points to form sets of the location data time points for each mobile wireless device;

generate a plurality of routines from the sets of location data time points, wherein each routine is a path of movement of the respective mobile wireless device within the predefined space;

partition the predefined space into a plurality of units and each routine of the plurality of routines into a plurality of subroutines, wherein each subroutine is a path segment of the corresponding path of movement within a particular unit;

combine, for each unit, one or more subroutines with a respective frequent subroutine, when the one or more subroutines are within a predetermined distance of the respective frequent subroutine, and wherein the respective frequent subroutine represents an aggregate of other subroutines within the unit that are within a specified distance of each other; and

display frequent subroutines on a graphical user interface to visualize aggregate movement of the plurality of mobile wireless devices within the predefined space.

10. The apparatus of claim 9, wherein the processor is further configured to:

obtain a first plurality of routines from a first plurality of mobile wireless devices from a database comprising historical trajectories of the first plurality of mobile wireless devices;

partition each routine of the first plurality of subroutines into a first plurality of subroutines;

cluster the first plurality of subroutines based on a distance function to form one or more clusters for each of the plurality of units; and

aggregate the clustered subroutines to form first frequent subroutines, when a number of subroutines of the first plurality of subroutines within a given cluster is above a threshold frequency value.

11. The apparatus of claim 9, wherein the processor is further configured to:

create a new frequent subroutine for a group of subroutines that are outside of a predetermined distance from any frequent subroutine, when the number of subroutines in the group exceeds a threshold frequency value and are within a specified distance of each other.

12. The apparatus of claim 9, wherein the processor is further configured to:

determine whether a given subroutine has expired;

remove the expired subroutine from the frequent subroutine; and

update a frequency associated with the frequent subroutine to reflect the removal of the expired subroutine.

13. The apparatus of claim 9, wherein the processor is further configured to:

combine one or more subroutines with a first frequent subroutine, when the one or more subroutines are within a predetermined distance of the first frequent subroutine, and updating a frequency characteristic associated with the first frequent subroutine to reflect the inclusion of the one or more subroutines into the first frequent subroutine.

14. The apparatus of claim 9, wherein the processor is further configured to:

display aggregate movement of the plurality of mobile wireless devices within the predefined space to detect an anomaly, and further comprising providing a notification in response to the detected anomaly.

15. The apparatus of claim 14, wherein the processor is further configured to:

display a density of mobile wireless devices associated with each frequent subroutine in real-time.

16. A non-transitory computer readable storage media encoded with instructions that, when executed by a processor of a computing device, cause the processor to:

obtain location data, via a network interface, from signals transmitted by a plurality of mobile wireless devices in a wireless network wherein the plurality of mobile wireless devices are moving within a predefined space, and wherein the location data comprises a plurality of location data time points;

aggregate, for each mobile wireless device, the plurality of location data time points to form sets of the location data time points for each mobile wireless device;

generate a plurality of routines from the sets of location data time points, wherein each routine is a path of movement of the respective mobile wireless device within the predefined space;

partition the predefined space into a plurality of units and each routine of the plurality of routines into a plurality of subroutines, wherein each subroutine is a path segment of the corresponding path of movement within a particular unit;

combine, for each unit, one or more subroutines with a respective frequent subroutine, when the one or more subroutines are within a predetermined distance of the respective frequent subroutine, and wherein the respective frequent subroutine represents an aggregate of other subroutines within the unit that are within a specified distance of each other; and

display frequent subroutines on a graphical user interface to visualize aggregate movement of the plurality of mobile wireless devices within the predefined space.

17. The non-transitory computer readable storage media of claim 16, wherein the processor is configured to:

obtain a first plurality of routines from a first plurality of mobile wireless devices from a database comprising historical trajectories of the first plurality of mobile wireless devices;

partition each routine of the first plurality of routines into a first plurality of subroutines;

cluster the first plurality of subroutines based on a distance function to form one or more clusters for each of the plurality of units; and

aggregate the clustered subroutines to form first frequent subroutines, when a number of subroutines of the first plurality of subroutines within a given cluster is above a threshold frequency value.

18. The non-transitory computer readable storage media of claim 16, wherein the processor is configured to:

create a new frequent subroutine for a group of subroutines that are outside of a predetermined distance from any frequent subroutine, when the number of subroutines in the group exceeds a threshold frequency value and are within a specified distance of each other.

19. The non-transitory computer readable storage media of claim 16, wherein the processor is configured to:

determine whether a given subroutine has expired;

remove the expired subroutine from the frequent subroutine; and

update a frequency associated with the frequent subroutine to reflect the removal of the expired subroutine.

20. The non-transitory computer readable storage media of claim 16 wherein the processor is configured to:

combine one or more subroutines with a first frequent subroutine, when the one or more subroutines are within a predetermined distance of the first frequent subroutine, and updating a frequency characteristic associated with the first frequent subroutine to reflect the inclusion of the one or more subroutines into the first frequent subroutine.