Behavioral analysis engine for profiling wireless subscribers

• US 10,664,851 B1
• Filed: 08/03/2016
• Issued: 05/26/2020
• Est. Priority Date: 11/08/2006
• Status: Active Grant

• Current Assignee: T-Mobile Innovations LLC (Deutsche Telekom AG)
• Original Assignee: Sprint Communications Company LP (Deutsche Telekom AG)
• Inventors: Barnes, James D., Biere, Devon, Potluri, Dora, Sharma, Sanjay, Srinivasan, Lavanya
• Primary Examiner(s): Delich, Stephanie Z
• Application Number:
  US15/227,950
• Time in Patent Office: 1,392 Days
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0267 Wireless devices
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04L 12/14 Charging , metering or billing arrangements for data wireline or wireless communications
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04M 15/41 Billing record details, i.e. parameters, identifiers, structure of call data record [CDR]
• CPC Class Codes: H04M 15/44 Augmented, consolidated or itemized billing statement or bill presentation
• CPC Class Codes: H04M 15/58 based on statistics of usage or network monitoring
• CPC Class Codes: H04M 15/60 based on actual use of network resources
• CPC Class Codes: H04M 15/61 based on the service used
• CPC Class Codes: H04M 15/8083 involving reduced rates or discounts, e.g. time-of-day reductions or volume discounts
• CPC Class Codes: H04W 4/24 Accounting or billing

Abstract

A method and system are disclosed for behavioral analysis for profiling wireless subscribers. The method includes loading carrier reference data comprising a set of common categories and loading a plurality of behavior records of at least two types, wherein each behavior record is generated by a mobile device activity of a subscriber. The method proceeds by associating each behavior record with one or more of the categories, thereby generating categorized data records. Finally each category associated with a behavior record is added to a subscriber profile for the subscriber whose activity generated the behavior record.

Claims

1. A computer-implemented method of collecting, processing, and analyzing subscriber data, comprising:

loading, from a reference data source to a behavioral engine stored in a non-transitory memory and executed by at least one processor of a server at a carrier network provider, carrier reference data comprising definitions of a plurality of behavioral categories, a premium content catalog, and definitions of a plurality of premium content categories;

monitoring and tracking, at a plurality of different data sources, mobile device activities of a plurality of subscribers associated with a plurality of mobile devices via generation of a plurality of raw data records, wherein the mobile device activities that generate the plurality of raw data records comprise;

at least one of a text message, a mobile picture mail, or a mobile video mail,

content purchased from a content store by the plurality of subscribers using the plurality of mobile devices,

when and how the content purchased by each subscriber of the plurality of subscribers is used by the subscriber on a mobile device of the plurality of mobile devices, and

mobile web requests for Wireless Application Protocol (WAP) pages from the plurality of mobile devices;

processing and parsing, by the behavioral engine, the plurality of raw data records generated according to the mobile device activities to identify content associated with the plurality of raw data records based on the carrier reference data;

determining, by the behavioral engine, for each raw data record of the plurality of raw data records generated according to the mobile device activities, a category of a plurality of categories that is associated with the identified content of the raw data record based on the carrier reference data;

building, by the behavioral engine, a subscriber profile of a plurality of subscriber profiles for each subscriber of the plurality of subscribers and compiling each determined category associated with each raw data record of the plurality of raw data records generated according to the mobile device activities based on behavior of the subscriber into the subscriber profile for the subscriber;

identifying, by the behavioral engine, a subset of subscriber profiles associated with a subset of subscribers from the plurality of subscribers by applying one or more business rules to the plurality of subscriber profiles; and

identifying, by a computer, an advertisement to provide to one of the plurality of mobile devices based on at least one subscriber profile associated with at least one subscriber selected from the subset of subscribers by applying one or more business rules to the at least one subscriber profile.

2. The method of claim 1, further comprising generating a categorized data record of a plurality of categorized data records for each raw data record of the plurality of raw data records by associating, by the behavioral engine, the determined category of the plurality of categories with the raw data record.

3. The method of claim 2, further comprising:

storing each subscriber profile built by the behavioral engine in a non-transitory memory of a subscriber data repository communicatively coupled to the server at the carrier network provider; and

discarding, by a computer, the plurality of raw data records after generation of the plurality of categorized data records.

4. The method of claim 1, wherein the carrier reference data further comprises a behavioral category hierarchy, and wherein the plurality of raw data records comprises premium content download transaction records.

5. The method of claim 1, wherein the premium content catalog comprises a list of a plurality of items available for purchase, an item identifier for each of the plurality of items available for purchase, and a category of the plurality of premium content categories associated with each of the plurality of items available for purchase.

6. The method of claim 1, wherein the content purchased comprises at least one of a song, a mobile device application, a mobile device screensaver, a mobile device call tone, a mobile device game, a mobile device ringer, a mobile device theme, or a mobile device wallpaper.

7. The method of claim 1, wherein at least some of the mobile device activities are monitored and tracked on the plurality of mobile devices by a data service usage data source.

8. The method of claim 7, wherein the plurality of different data sources comprises the data service usage data source, a data service and content purchases data source, and a WAP request data source.

9. The method of claim 1, wherein each raw data record generated based on the content purchased from the content store comprises an identity of the content and purchase price, each raw data record generated based on when and how the content purchased is used by the subscriber on their mobile device comprises at least two of a storage location of the content purchased, amount of network resources consumed in delivering the content purchased, time of usage, or configuration settings, and each raw data record generated based on the mobile web requests for WAP pages comprises a WAP address and one or more web keywords.

10. The method of claim 1, further comprising sending a download recommendation to one of the plurality of mobile devices associated with one of the plurality of subscribers based on a subscriber profile associated with the one of the plurality of subscriber profiles.

11. A carrier system for collecting, processing, and analyzing subscriber data, comprising:

a plurality of different data sources that monitor and track mobile device activities of a plurality of subscribers associated with a plurality of mobile devices via generation of a plurality of raw data records, wherein the mobile device activities that generate the plurality of raw data records comprise;

at least one of a text message, a mobile picture mail, or a mobile video mail,

content purchased from a content store by the plurality of subscribers using the plurality of mobile devices,

when and how the content purchased by each subscriber of the plurality of subscribers is used by the subscriber on a mobile device of the plurality of mobile devices, and

mobile web requests for Wireless Application Protocol (WAP) pages from the plurality of mobile devices; and

a server at a carrier network provider that is communicatively coupled to each of the plurality of different data sources via a network of the carrier network provider, the server comprising one or more processors and a behavioral engine stored in a non-transitory memory, that upon execution by at least one processor, configures the at least one processor to;

obtain, from a reference data source, carrier reference data comprising definitions of a plurality of behavioral categories, a premium content catalog, and definitions of a plurality of premium content categories,

process and parse the plurality of raw data records generated according to the mobile device activities to identify content associated with the plurality of raw data records based on carrier reference data,

determine, for each raw data record of the plurality of raw data records generated according to the mobile device activities, a category of a plurality of categories that is associated with the identified content of the raw data record based on the carrier reference data,

build a subscriber profile of a plurality of subscriber profiles for each subscriber of the plurality of subscribers and compiling each determined category associated with each raw data record of the plurality of raw data records generated according to the mobile device activities based on behavior of the subscriber into the subscriber profile for the subscriber,

identify a subset of subscriber profiles associated with a subset of subscribers from the plurality of subscribers by applying one or more business rules to the plurality of subscriber profiles, and

identify an advertisement to provide to one of the plurality of mobile devices based on at least one subscriber profile associated with at least one subscriber selected from the subset of subscribers by applying one or more business rules to the at least one subscriber profile.

12. The carrier system of claim 11, wherein the behavioral engine further:

generates a categorized data record of a plurality of categorized data records for each raw data record of the plurality of raw data records by associating the determined category of the plurality of categories with the raw data record, and

discards the plurality of raw data records once the plurality of categorized data records is generated.

13. The carrier system of claim 12, further comprising a subscriber data repository that stores, in a non-transitory memory, the plurality of categorized data records in an aggregate level and each subscriber profile built by the behavioral engine at an individual level.

14. The carrier system of claim 13, further comprising a plurality of business unit project engines that configure a processor of the server to access the subscriber data repository to apply business rules to the plurality of categorized data records, wherein each business rule for each business unit project engine is unique to a project carried out by a particular group within an enterprise of the carrier network provider.

15. The carrier system of claim 14, wherein a business rule applied to the plurality of categorized data records configures the processor to determine, at an individual level, that a particular subscriber should be selected as a target subscriber for the project by determining that the particular subscriber is active for one of the plurality of categories based on a threshold comprising an activation flag.

16. The carrier system of claim 14, wherein a business rule applied to the plurality of categorized data records configures the processor of the server to determine, at an aggregate level, that a particular grouping of subscribers should be selected for targeting for the project by determining that the particular grouping of subscribers is active for one of the plurality of categories based on a threshold that comprises activation flags.

17. The carrier system of claim 11, wherein at least some of the mobile device activities are monitored and tracked on the plurality of mobile devices by a data service usage data source.

18. The carrier system of claim 17, wherein the plurality of different data sources comprises the data service usage data source, a data service and content purchases data source, and a WAP request data source.

19. A computer-implemented method of collecting, processing, and analyzing subscriber data, comprising:

loading, from a reference data source to a behavioral engine stored in a non-transitory memory and executed by at least one processor of a server at a carrier network provider, carrier reference data comprising definitions of a plurality of behavioral categories, a premium content catalog, and definitions of a plurality of premium content categories;

monitoring and tracking, at a plurality of different data sources, mobile device activities of a plurality of subscribers associated with a plurality of mobile devices via generation of a plurality of raw data records, wherein the mobile device activities that generate the plurality of raw data records comprise;

at least one of a text message, a mobile picture mail, or a mobile video mail,

content purchased from a content store by the plurality of subscribers using the plurality of mobile devices,

when and how the content purchased by each subscriber of the plurality of subscribers is used by the subscriber on a mobile device of the plurality of mobile devices, and

mobile web requests for Wireless Application Protocol (WAP) pages from the plurality of mobile devices;

processing and parsing, by the behavioral engine, the plurality of raw data records generated according to the mobile device activities to identify content associated with plurality of raw data records based on the carrier reference data;

determining, by the behavioral engine, for each raw data record of the plurality of raw data records generated according to the mobile device activities, a category of a plurality of categories that is associated with the identified content of the raw data record based on the carrier reference data;

building, by the behavioral engine, a subscriber profile of a plurality of subscriber profiles for each subscriber of the plurality of subscribers and compiling each determined category associated with each raw data record of the plurality of raw data records generated according to the mobile device activities based on behavior of the subscriber into the subscriber profile for the subscriber;

identifying, by the behavioral engine, a subset of subscriber profiles associated with a subset of subscribers from the plurality of subscribers by applying a first business rule selected by a first business group of the carrier network provider to the plurality of subscriber profiles, wherein the first business rule applied by the behavioral engine determines that each subscriber in the subset of subscribers is active in at least one category of the plurality of categories by applying different weights to at least some of the types of mobile device activities of the subscriber; and

identifying, by a computer, an advertisement to provide to at least one of the plurality of mobile devices based on at least one subscriber profile associated with at least one subscriber selected from the subset of subscribers by applying a second business rule selected by a second business group of the carrier network provider to the at least one subscriber profile.

20. The method of claim 19, wherein a mobile device activity of a ringer purchase by the subscriber in the at least one category is weighted more heavily than a mobile device activity of a WAP request by the subscriber in the at least one category in determining whether the subscriber is active in the at least one category.