Method and system for identifying mobile user cluster by call detail record

• US 20060293025A1
• Filed: 06/23/2006
• Published: 12/28/2006
• Est. Priority Date: 06/23/2005
• Status: Active Grant

• Current Assignee: Ground Hog Inc.
• Original Assignee: Groundhog Technologies, Inc.
• Inventors: Chen, Meng-Seng, Teng, Wei-Guang, Chang, Chao-Chi, Chiou, Ta-Gang
• Granted Patent: US 8,346,208 B2
• Time in Patent Office: Days
• US Class Current: 455/405
• CPC Class Codes: H04W 4/08 User group management
• CPC Class Codes: H04W 4/24 Accounting or billing
• CPC Class Codes: H04W 8/18 Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data

Abstract

A system and method for identifying a mobile user cluster by call detail records (CDRs) is provided. The system and method identifies at least one mobile user cluster according to a plurality of CDRs generated by a plurality of mobile users during a first period and a second period of time. Each mobile user of the identified cluster generates at least one CDR at a same geographical location during the first period of time, and a mobile user sequence is formed between any two mobile users of the identified cluster. At least one CDR is generated between any two neighboring mobile users of the mobile user sequence during the second period of time. Examples for the mobile user cluster include cohabiting family members, familiar neighborhood, colleagues, schoolmates, etc.

Claims

1. A method for identifying a mobile user cluster by call detail records comprising steps of:

identifying a plurality of mobile users according to a plurality of first call detail records generated at a geographical location during a first period of time; and

identifying at least one mobile user cluster according to a plurality of second call detail records generated by the mobile users during a second period of time, wherein a mobile user sequence is formed between any two mobile users of the mobile user cluster, and at least one of the second call detail records is generated between any two neighboring mobile users of the mobile user sequence.

2. The method of claim 1, wherein the step of identifying at least one mobile user cluster comprises:

generating a connected graph of the identified mobile users according to the second call detail records.

3. The method of claim 2, wherein the step of identifying at least one mobile user cluster further comprises:

performing a graph partitioning on the connected graph to identify the mobile user cluster.

4. The method of claim 1, wherein the step of identifying at least one mobile user cluster comprises:

generating a mathematic expression corresponding to a connected graph of the identified mobile users according to the second call detail records.

5. The method of claim 4, wherein the step of identifying at least one mobile user cluster further comprises:

performing a statistical induction method on the mathematic expression to identify the mobile user cluster.

6. The method of claim 1, wherein in the step of identifying a plurality of mobile users, the first call detail records are generated by a base transceiver station (BTS) at or near the geographical location.

7. The method of claim 1, further comprising:

estimating a relationship property of the identified mobile user cluster according to the geographical location and the first period of time.

8. The method of claim 1, further comprising:

determining a relationship strength of the identified mobile user cluster according to the second call detail records generated between the mobile users of the identified mobile user cluster.

9. The method of claim 8, wherein the relationship strength is determined according to an amount of the second call detail records generated between the mobile users of the mobile user cluster.

10. The method of claim 8, wherein the relationship strength is determined according to a call duration corresponding to the second call detail records generated between the mobile users of the mobile user cluster.

11. The method of claim 8, wherein the relationship strength is determined according to a call cost corresponding to the second call detail records generated between the mobile users of the mobile user cluster.

12. The method of claim 1, wherein each of the first and second call detail records is a voice call detail record or a data call detail record.

13. A method for identifying a mobile user cluster by call detail records, wherein the method identifies at least one mobile user cluster according to a plurality of call detail records generated by a plurality of mobile users during a first period and a second period of time, wherein each mobile user of the identified mobile user cluster generates at least one of the call detail records at a same geographical location during the first period of time, and a mobile user sequence is formed between any two mobile users of the identified mobile user cluster, wherein at least one of the call detail records is generated between any two neighboring mobile users of the mobile user sequence during the second period of time.

14. The method of claim 13, comprising:

identifying a plurality of first mobile users according to the call detail records generated by the mobile users during the first period of time, wherein each of the first mobile users generates at least one of the call detail records at the same geographical location during the first period of time;

generating a connected graph of the first mobile users according to the call detail records generated by the first mobile users during the second period of time; and

performing a graph partitioning on the connected graph to identify the mobile user cluster.

15. The method of claim 13, comprising:

identifying a plurality of first mobile users according to the call detail records generated by the mobile users during the first period of time, wherein each of the first mobile users generates at least one of the call detail records at the same geographical location during the first period of time;

generating a mathematic expression corresponding to a connected graph of the first mobile users according to the call detail records generated by the first mobile users during the second period of time; and

performing a statistical induction method on the mathematic expression to identify the mobile user cluster.

16. The method of claim 13, comprising:

estimating a relationship property of the identified mobile user cluster according to the geographical location and the first period of time.

17. The method of claim 13, comprising:

determining a relationship strength of the identified mobile user cluster according to the call detail records generated between the mobile users of the identified mobile user cluster during the second time of period.

18. A system for identifying a mobile user cluster by call detail records comprising:

a storage medium for storing a plurality of call detail records generated by a plurality of mobile users during a first period and a second period of time; and

a processor, coupled to the storage medium, for identifying at least one mobile user cluster according to the call detail records, wherein each mobile user of the identified mobile user cluster generates at least one of the call detail records at a same geographical location during the first period of time, and a mobile user sequence is formed between any two mobile users of the identified mobile user cluster, wherein at least one of the call detail records is generated between any two neighboring mobile users of the mobile user sequence during the second period of time.

19. The system of claim 18, wherein the processor estimates a relationship property of the identified mobile user cluster according to the geographical location and the first period of time.

20. The system of claim 18, wherein the processor determines a relationship strength of the identified mobile user cluster according to the call detail records generated between the mobile users of the identified mobile user cluster during the second time of period.