Method and arrangement for supporting analysis of social networks in a communication network

• US 9,305,110 B2
• Filed: 09/28/2009
• Issued: 04/05/2016
• Est. Priority Date: 09/28/2009
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Hildorsson, Fredrik, Kvernvik, Tor
• Primary Examiner(s): Gillis, Brian J
• Assistant Examiner(s): TURRIATE GASTULO, JUAN CARLOS
• Application Number:
  US13/498,230
• Publication Number:
  US 20120185540A1
• Time in Patent Office: 2,381 Days
• Field of Search: 709/204
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• 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
• CPC Class Codes: H04W 8/186 Processing of subscriber group data

Abstract

A method and apparatus for supporting social network analysis of terminal users in a communication network. Users being located relatively close to each other when making calls are more likely to be socially “connected” than users having mutually more remote locations. A partitioning unit (100) determines a representative geographical location for individual users based on traffic data and location data (102,104). User partitions are then made based on the users'"'"' representative geographical locations such that one particular user partition contains users having representative geographical locations within a limited geographical area. The user partition is then provided to a social network analysis function (106) for further analysis (108).

Claims

1. A method executed by a partitioning device for supporting social network analysis of terminal users in a communication network, comprising:

obtaining, from data records available in the communication network, traffic data and location data related to calls made by said users during a period of time, wherein the traffic data and location data related to any calls made by a given user during the period of time indicate one or more locations at which that given user made those calls;

determining a representative geographical location for individual ones of said users based on said traffic data and location data, wherein the representative geographical location of a user is a location representative of where the user more often than not makes his or her calls, as indicated by the traffic data and location data obtained for calls made by that given user during the period of time;

forming a user partition that defines a group of said users having representative geographical locations within a predetermined area; and

providing said user partition to a social network analysis function.

2. The method according to claim 1, wherein said user partition is represented as a division on a graph comprising said users.

3. The method according to claim 1, wherein said predetermined area coincides with a densely populated geographical district or region.

4. The method according to claim 1, wherein said forming further comprises forming a plurality of location-based user partitions that define different groups of said users having representative geographical locations within different limited areas.

5. The method according to claim 4, wherein said forming comprises forming the location-based user partitions according to a predefined network partition plan of corresponding predetermined areas, by using the network partition plan to map each user'"'"'s representative geographical location to a location-based user partition.

6. The method according to claim 5, further comprising adjusting the network partition plan based on feedback from the social network analysis function regarding social network analysis done using the formed location-based user partitions.

7. The method according to claim 4, wherein said forming comprises forming said location-based user partitions to include clusters of users in relatively close proximity to each other according to their representative geographical locations, and to form said user partitions such that a relatively small number of calls have been made across different user partitions.

8. The method according to claim 4, further comprising adjusting said location-based user partitions to reduce the amount of calls executed across different user partitions, and thereby reduce the number of implied social connections or ties across different user partitions.

9. The method according to claim 1, wherein said obtaining comprises obtaining the traffic data and location data from charging data records.

10. The method according to claim 9, wherein said obtaining further comprises extracting location data from at least one of:

information on the geographical location of cells;

service and location areas in the case the communication network is a mobile network; and

connection points at which portable terminals connect to the communication network in the case the communication network is a fixed network.

21. method of claim 1, wherein the method further comprises:

forming a plurality of user partitions, wherein each partition defines users that are likely to be socially connected; and

providing the plurality of user partitions to a social network analysis function, wherein providing said user partitions to a social network analysis function assists the social network analysis function to analyze, for each partition, the actual existence and/or extent of social connections amongst users in the same partition.

22. The method of claim 1, wherein said determining comprises excluding, based on the obtained traffic data, calls from a set of calls with obtained location data, and determining a representative geographic location based on the location data of remaining calls in the set.

23. The method of claim 1, wherein traffic data comprises how frequently calls were made by a user with respect to a plurality of locations identified in the location data, and determining a representative geographical location for a user comprises determining based on the location that had the most frequent calls.

25. The method according to claim 1, wherein the data records include charging data records, data records generated by one or more traffic analyzing devices in the communication network, data records generated by one or more positioning functions in the communication network for determining the position of users, or any combination thereof.

11. A partitioning device configured to support social network analysis of terminal users in a communication network, comprising a processor and a memory containing instructions executable by said processor whereby said device is operative to:

obtain, from data records available in the communication network, traffic data and location data related to calls made by said users during a period of time, wherein the traffic data and location data related to any calls made by a given user during the period of time indicate one or more locations at which that given user made those calls;

determine a representative geographical location for individual ones of said users based on said traffic data and location data, wherein the representative geographical location of a user is a location representative of where the user more often than not makes his or her calls, as indicated by the traffic data and location data obtained for calls made by that given user during the period of time;

form a user partition that defines a group of users having representative geographical locations within a predetermined area; and

provide said user partition to a social network analysis function.

12. The partitioning device according to claim 11, wherein the partitioning device is further configured to represent said user partition as a division on a graph comprising said users.

13. The partitioning device according to claim 11, wherein said predetermined area coincides with a densely populated geographical district or region.

14. The partitioning device according to claim 11, wherein the partitioning device is further configured to form a plurality of location-based user partitions defining different groups of users having representative geographical locations within different limited areas.

15. The partitioning device according to claim 14, wherein the partitioning device is further configured to form said user partitions according to a predefined network partition plan of corresponding predetermined areas, by using the partition plan to map each user'"'"'s representative location to a location-based user partition.

16. The partitioning device according to claim 15, wherein the partitioning device is further configured to adjust the network partition plan based on feedback from the social network analysis function regarding social network analysis done using the formed location-based user partitions.

17. The partitioning device according to claim 15, wherein the partitioning device is further configured to adjust said location-based user partitions by minimizing the amount of calls executed across different user partitions, and thereby minimize the number of implied social connections or ties across different user partitions.

18. The partitioning device according to claim 14, wherein the partitioning device is further configured to form said user partitions to include clusters of users in relatively close proximity to each other according to their representative locations, and to form said user partitions such that a relatively small number of calls have been made across different user partitions.

19. The partitioning device according to claim 11, wherein the partitioning device is configured to obtain the traffic data and location data from charging data records.

20. The partitioning device according to claim 19, wherein the partitioning device is further configured to extract location data from at least one of:

information on the geographical location of cells;

service and location areas in the case the communication network is a mobile network; and

connection points at which portable terminals connect to the communication network in the case the communication network is a fixed network.

26. The partitioning device according to claim 11, wherein the data records include charging data records, data records generated by one or more traffic analyzing devices in the communication network, data records generated by one or more positioning functions in the communication network for determining the position of users, or any combination thereof.

24. A method of facilitating analysis of social connections amongst a population of terminal users in a communication network, the method comprising:

for each of the terminal users in said population, obtaining, from data records available in the communication network, data indicating locations that the user has previously been at when participating in communication sessions via the communication network during a period of time and determining, based on that data, a representative geographical location for the user which represents the user as more often than not being at that location when participating in communication sessions, as indicated by the data obtained for the user;

partitioning said population of users into different partitions of users that are likely to be socially connected, by defining different partitions as including different groups of users having representative geographical locations within different limited areas; and

assisting a social network analysis function to analyze, for each of said partitions, the actual existence and/or extent of social connections amongst users in that same partition, rather than analyzing the actual existence and/or extent of social connections amongst all users in said population as a whole, by sending information indicating each of said partitions to the social network analysis function.

27. The method according to claim 24, wherein the data records include charging data records, data records generated by one or more traffic analyzing devices in the communication network, data records generated by one or more positioning functions in the communication network for determining the position of users, or any combination thereof.