Correlating user interests and location in a mobile network

• US 8,229,470 B1
• Filed: 10/22/2010
• Issued: 07/24/2012
• Est. Priority Date: 10/22/2010
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: Narus, Inc. (Gen Digital Inc.)
• Inventors: Nucci, Antonio, Kuzmanovic, Aleksandar, Ranjan, Supranamaya, Trestian, Ionut
• Primary Examiner(s): Hu, Jinsong
• Assistant Examiner(s): MORALES FERNANDEZ, BENJAMIN
• Application Number:
  US12/910,731
• Time in Patent Office: 641 Days
• Field of Search: None
• US Class Current: 455/456.3
• CPC Class Codes: H04W 4/022 with dynamic range variability
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

A method for providing location based service in a cellular data service network (CDSN) by analyzing accounting data packets of the CDSN to determine a user mobility pattern, classifying application data packets of the CDSN into pre-determined application categories, analyzing the accounting data packets and the application data packets to associate the user mobility pattern and one of the pre-determined application category, comparing a newly received accounting data packet and the user mobility pattern to identify a match, and providing, in response to identifying the match, the location based service to a user based on the pre-determined application category.

Claims

1. A method for providing location based service in a cellular data service network (CDSN) having a plurality of base stations, comprising:

obtaining, from the CDSN, a plurality of accounting data packets and a plurality of application data packets associated with at least a portion of users of the CDSN, wherein the plurality of accounting data packets comprises metering information of CDSN usage by at least the portion of the users for transmitting the plurality of application data packets;

analyzing, using a central processing unit (CPU) of a computer, the plurality of accounting data packets to determine a user mobility pattern representing a statistical pattern of time correlated user base station connections of at least the portion of the users in the CDSN, comprising;

formulating a plurality of binary rules for association rule mining of the plurality of accounting data packets, wherein each of the plurality of binary rules is associated with a proposition of an antecedent implying an consequent and corresponds to a hypothetical user mobility pattern, wherein the antecedent states a first connection to a source base station within a time window with a pre-determined start time, wherein the consequent states a second connection to a target base station within a pre-determined time duration subsequent to the first connection;

performing the association rule mining of the plurality of accounting data packets based on the plurality of binary rules to generate a confidence probability of the hypothetical user mobility pattern; and

identifying the hypothetical user mobility pattern as the user mobility pattern in response to the confidence probability exceeding a pre-determined threshold;

classifying, using the CPU, each of the plurality of application data packets as belonging to one or more of a plurality of pre-determined application categories based on keyword search;

analyzing, using the CPU, the plurality of accounting data packets and the plurality of application data packets, based on network addresses and timestamps contained therein, to associate the user mobility pattern and a pre-determined application category of the plurality of pre-determined application categories;

comparing, in response to receiving by the CDSN an accounting data packet associated with a first user of the users, the accounting data packet and the user mobility pattern to identify a match; and

providing, in response to identifying the match, the location based service to the first user based on the pre-determined application category.

2. The method of claim 1, further comprising:

analyzing the plurality of accounting data packets to identify a plurality of user mobility events; and

identifying a portion of the plurality of user mobility events each comprising a first timestamp consistent with a timing condition of the hypothetical mobility pattern, wherein generating the confidence probability comprises tallying the portion of the plurality of user mobility events, wherein associating the user mobility pattern and the pre-determined application category comprises associating the portion of the plurality of user mobility events and an application data packet of the plurality of application data packets based on a comparison of the first timestamp and a second timestamp contained in the application data packet, wherein each of the portion of the plurality of user mobility events and the application data packet comprises a network address of the network addresses assigned to a connection session for connecting a second user of the plurality of users to the CDSN, wherein the portion of the plurality of user mobility events further comprises a user identifier identifying the second user.

3. The method of claim 1, wherein the match is identified if a timestamp of the accounting data packet and a timing condition of the user mobility pattern correspond to at least one selected from a group consisting of a same time window in a day, a same time window in a week, a same time window in a month, and a same time in a year.

4. The method of claim 1, wherein providing the location based service to the first user based on the pre-determined application category comprises:

identifying a hotspot associated with the user mobility pattern, wherein the accounting data packet associated with the first user indicates that the first user is in the hotspot; and

in response to identifying the location based service as associated with the pre-determined application category, enhancing user experience by at least one selected from a group consisting of caching information associated with the location based service at the hotspot and increasing quality of service of the location based service at the hotspot.

5. The method of claim 1, wherein the plurality of accounting data packets comprise a RADIUS (Remote Authentication Dial In User Service) accounting protocol data packet, wherein the plurality of application data packets comprise a HTTP (Hypertext Transfer Protocol) data packet comprising a URL (Uniform Resource Locator) associated with the LBS, and wherein the network addresses comprise an IP (Internet Protocol) address.

6. The method of claim 1, wherein the plurality of base stations comprise at least one selected from a group consisting of a cellular phone network base station, a Wi-Fi access point, a WiMax (Worldwide Interoperability for Microwave Access) base station, and a 3GPP LTE (Third Generation Partnership Project Long Term Evolution) base station.

7. A system for providing location based service in a cellular data service network (CDSN), comprising:

a plurality of base stations of the CDSN;

a processor; and

memory storing instructions, when executed by the processor, comprising functionalities for;

obtaining, from the CDSN, a plurality of accounting data packets and a plurality of application data packets associated with at least a portion of users of the CDSN, wherein the plurality of accounting data packets comprises metering information of CDSN usage by at least the portion of the users for transmitting the plurality of application data packets;

analyzing the plurality of accounting data packets to determine a user mobility pattern representing a statistical pattern of time correlated user base station connections of at least the portion of the users in the CDSN, comprising;

formulating a plurality of binary rules for association rule mining of the plurality of accounting data packets, wherein each of the plurality of binary rules is associated with a proposition of an antecedent implying an consequent and corresponds to a hypothetical user mobility pattern, wherein the antecedent states a first connection to a source base station within a time window with a pre-determined start time, wherein the consequent states a second connection to a target base station within a pre-determined time duration subsequent to the first connection;

performing the association rule mining of the plurality of accounting data packets based on the plurality of binary rules to generate a confidence probability of the hypothetical user mobility pattern; and

identifying the hypothetical user mobility pattern as the user mobility pattern in response to the confidence probability exceeding a pre-determined threshold;

classifying each of the plurality of application data packets as belonging to one or more of a plurality of pre-determined application categories based on keyword search;

analyzing the plurality of accounting data packets and the plurality of application data packets, based on network addresses and timestamps contained therein, to associate the user mobility pattern and a pre-determined application category of the plurality of pre-determined application categories;

comparing, in response to receiving by the CDSN an accounting data packet associated with a first user of the users, the accounting data packet and the user mobility pattern to identify a match; and

providing, in response to identifying the match, the location based service to the first user based on the pre-determined application category.

8. The system of claim 7, the instruction when executed by the processor further comprising functionality for:

analyzing the plurality of accounting data packets to identify a plurality of user mobility events; and

identifying a portion of the plurality of user mobility events each comprising a first timestamp consistent with a timing condition of the hypothetical mobility pattern, wherein generating the confidence probability comprises tallying the portion of the plurality of user mobility events,

wherein associating the user mobility pattern and the pre-determined application category comprises associating the portion of the plurality of user mobility events and an application data packet of the plurality of application data packets based on a comparison of the first timestamp and a second timestamp contained in the application data packet, wherein each of the portion of the plurality of user mobility events and the application data packet comprises a network address of the network addresses assigned to a connection session for connecting a second user of the plurality of users to the CDSN, wherein the portion of the plurality of user mobility events further comprises a user identifier identifying the second user.

9. The system of claim 7, wherein the match is identified if a timestamp of the accounting data packet and a timing condition of the user mobility pattern correspond to at least one selected from a group consisting of a same time window in a day, a same time window in a week, a same time window in a month, and a same time in a year.

10. The system of claim 7, wherein providing the location based service to the first user based on the pre-determined application category comprises:

identifying a hotspot associated with the user mobility pattern, wherein the accounting data packet associated with the first user indicates that the first user is in the hotspot; and

in response to identifying the location based service as associated with the pre-determined application category, enhancing user experience by at least one selected from a group consisting of caching information associated with the location based service at the hotspot and increasing quality of service of the location based service at the hotspot.

11. The system of claim 7, wherein the plurality of accounting data packets comprise a RADIUS (Remote Authentication Dial In User Service) accounting protocol data packet, wherein the plurality of application data packets comprise a HTTP (Hypertext Transfer Protocol) data packet comprising a URL (Uniform Resource Locator) associated with the LBS, and wherein the network addresses comprise an IP (Internet Protocol) address.

12. The system of claim 7, wherein the plurality of base stations comprise at least one selected from a group consisting of a cellular phone network base station, a Wi-Fi access point, a WiMax (Worldwide Interoperability for Microwave Access) base station, and a 3GPP LTE (Third Generation Partnership Project Long Term Evolution) base station.

13. A non-transitory computer readable medium storing instructions for providing

location based service in a cellular data service network (CDSN) having a plurality of base stations, the instructions, when executed by a processor of a computer, comprising functionality for:

obtaining, from the CDSN, a plurality of accounting data packets and a plurality of application data packets associated with at least a portion of users of the CDSN, wherein the plurality of accounting data packets comprises metering information of CDSN usage by at least the portion of the users for transmitting the plurality of application data packets;

analyzing, using a central processing unit (CPU) of a computer, the plurality of accounting data packets to determine a user mobility pattern representing a statistical pattern of time correlated user base station connections of at least the portion of the users in the CDSN, comprising;

formulating a plurality of binary rules for association rule mining of the plurality of accounting data packets, wherein each of the plurality of binary rules is associated with a proposition of an antecedent implying an consequent and corresponds to a hypothetical user mobility pattern, wherein the antecedent states a first connection to a source base station within a time window with a pre-determined start time, wherein the consequent states a second connection to a target base station within a pre-determined time duration subsequent to the first connection;

performing the association rule mining of the plurality of accounting data packets based on the plurality of binary rules to generate a confidence probability of the hypothetical user mobility pattern; and

identifying the hypothetical user mobility pattern as the user mobility pattern in response to the confidence probability exceeding a pre-determined threshold;

classifying, using the CPU, each of the plurality of application data packets as belonging to one or more of a plurality of pre-determined application categories based on keyword search;

analyzing, using the CPU, the plurality of accounting data packets and the plurality of application data packets, based on network addresses and timestamps contained therein, to associate the user mobility pattern and a pre-determined application category of the plurality of pre-determined application categories;

comparing, in response to receiving by the CDSN an accounting data packet associated with a first user of the users, the accounting data packet and the user mobility pattern to identify a match; and

providing, in response to identifying the match, the location based service to the first user based on the pre-determined application category.

14. The non-transitory computer readable medium of claim 13, the instructions, when executed by the processor, further comprising functionality for:

analyzing the plurality of accounting data packets to identify a plurality of user mobility events; and

identifying a portion of the plurality of user mobility events each comprising a first timestamp consistent with a timing condition of the hypothetical mobility pattern, wherein generating the confidence probability comprises tallying the portion of the plurality of user mobility events,

wherein associating the user mobility pattern and the pre-determined application category comprises associating the portion of the plurality of user mobility events and an application data packet of the plurality of application data packets based on a comparison of the first timestamp and a second timestamp contained in the application data packet, wherein each of the portion of the plurality of user mobility events and the application data packet comprises a network address of the network addresses assigned to a connection session for connecting a second user of the plurality of users to the CDSN, wherein the portion of the plurality of user mobility events further comprises a user identifier identifying the second user.

15. The non-transitory computer readable medium of claim 13, wherein the match is identified if a timestamp of the accounting data packet and a timing condition of the user mobility pattern correspond to at least one selected from a group consisting of a same time window in a day, a same time window in a week, a same time window in a month, and a same time in a year.

16. The non-transitory computer readable medium of claim 13, wherein providing the location based service to the first user based on the pre-determined application category comprises:

identifying a hotspot associated with the user mobility pattern, wherein the accounting data packet associated with the first user indicates that the first user is in the hotspot; and

in response to identifying the location based service as associated with the pre-determined application category, enhancing user experience by at least one selected from a group consisting of caching information associated with the location based service at the hotspot and increasing quality of service of the location based service at the hotspot.

17. The non-transitory computer readable medium of claim 13, wherein the plurality of accounting data packets comprise a RADIUS (Remote Authentication Dial In User Service) accounting protocol data packet,

wherein the plurality of application data packets comprise a HTTP (Hypertext Transfer Protocol) data packet comprising a URL (Uniform Resource Locator) associated with the LBS, and wherein the network addresses comprise an IP (Internet Protocol) address.

18. The non-transitory computer readable medium of claim 13, wherein the plurality of base stations comprise at least one selected from a group consisting of a cellular phone network base station, a Wi-Fi access point, a WiMax (Worldwide Interoperability for Microwave Access) base station, and a 3GPP LTE (Third Generation Partnership Project Long Term Evolution) base station.