Enhanced data collection and analysis facility

• US 10,389,828 B2
• Filed: 04/28/2017
• Issued: 08/20/2019
• Est. Priority Date: 04/28/2017
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Andrade, Paulo Mario, Nakano, Fernando, Abdullah, Khalid, Vuori, Kimmo, Garcia, Steven, Vohra, Vaibhav, Buzzalino, Arturo, Moreira, Elias Junior, Pande, Bhomik, Shelokar, Prakash
• Primary Examiner(s): Shin, Kyung H
• Application Number:
  US15/581,556
• Publication Number:
  US 20180316571A1
• Time in Patent Office: 844 Days
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06Q 10/0633 Workflow analysis
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

In one general aspect, a system and method are described for generating a classification model to determine predictive user behavior. The method may include obtaining data from a mobile network provider. The data including a plurality of utilization metrics pertaining to a plurality of mobile devices carrying out a plurality of network interactions, the plurality of mobile devices being associated with a plurality of users. The method may also include categorizing the data into a plurality of Internet domains associated with the data and determining a plurality of patterns in the data. The method may further include determining an additional pattern in the data, and generating a plurality of rules based on the plurality of patterns and the additional pattern.

Claims

1. A computer-implemented method for generating a classification model to determine predictive user behavior, the method comprising:

obtaining data from a mobile network provider, the data including a plurality of utilization metrics pertaining to a plurality of mobile devices carrying out a plurality of network interactions, the plurality of mobile devices being associated with a plurality of users;

categorizing the data into a plurality of Internet domains comprising Internet Protocol (IP) resources associated with the data, wherein the data is categorized according to particular categories of the IP resources in which the data pertains, and wherein the IP resources include two or more of a web-site or a web-based service;

determining a plurality of patterns in the data, the plurality of patterns being used to correlate a first category represented in the data with at least a portion of the plurality of Internet domains;

determining an additional pattern in the data, the additional pattern correlating a second category represented in the data with at least a portion of the plurality of Internet domains; and

generating a plurality of rules based on the plurality of patterns and the additional pattern.

2. The method of claim 1, further comprising:

obtaining additional data from one or more mobile network providers;

applying the plurality of rules to the additional data to classify the data according to one or more of the plurality of patterns;

generating a plurality of age bands, each of which correlate to at least one of the plurality of patterns represented in the data;

generating at least two gender groups, one of which correlates to the additional pattern represented in the data;

recognizing, for presentation in a graphical user interface, a plurality of graphical reports indicating behavior for mobile device users represented in the additional data, the behavior indicated in the plurality of patterns and graphed according to age band and gender; and

in response to receiving a request to view analysis of the additional data, presenting, in the graphical user interface, at least one of the plurality of graphical reports.

3. The method of claim 1, further comprising:

grouping the plurality of Internet domains into a plurality of content topics representing the data;

determining browsing patterns in the data according to the plurality of content topics, the behavior being identified and processed according to a plurality of predefined age bands and gender groups; and

generating a plurality of updated rules based on the determined browsing patterns.

4. The method of claim 1, further comprising:

determining that a portion of the plurality of utilization metrics include automated mobile device network activities; and

before categorizing the data into the plurality of Internet domains, filtering the portion from the data, the filtering being based at least in part on a plurality of mobile call rules.

5. The method of claim 4, wherein the mobile call rules pertain to call time, call duration, gap duration consistency, devices called, and device location.

6. The method of claim 1, wherein the plurality of Internet domains define a browsing profile associated with one or more of the plurality of mobile devices.

7. The method of claim 1, wherein the plurality of utilization metrics are associated with one or more voice transaction, short message service transaction, HTTP access transaction, and location transaction.

8. The method of claim 1, further comprising filtering the data by selecting and removing a portion of the Internet domains from the data in response to determining that the data represents less than a predefined threshold time for visiting the Internet domains.

9. A computer program product for generating a classification model to determine predictive user behavior, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed by at least one computing device, are configured to cause the at least one computing device to:

obtain data from a mobile network provider, the data including a plurality of utilization metrics pertaining to a plurality of mobile devices carrying out a plurality of network interactions, the plurality of mobile devices being associated with a plurality of users;

categorize the data into a plurality of Internet domains comprising Internet Protocol (IP) resources associated with the data, wherein the data is categorized according to particular categories of the IP resources in which the data pertains, and wherein the IP resources include two or more of a web-site or a web-based service;

determine a plurality of patterns in the data, the plurality of patterns being used to correlate a first category represented in the data with at least a portion of the plurality of Internet domains;

determine an additional pattern in the data, the additional pattern correlating a second category represented in the data with at least a portion of the plurality of Internet domains; and

generate a plurality of rules based on the plurality of patterns and the additional pattern.

10. The computer program product of claim 9, wherein the instructions are further configured to cause the at least one computing device to:

obtain additional data from one or more mobile network providers;

apply the plurality of rules to the additional data to classify the data according to one or more of the plurality of patterns;

generate a plurality of age bands, each of which correlate to at least one of the plurality of patterns represented in the data;

generate at least two gender groups, one of which correlates to the additional pattern represented in the data;

recognize, for presentation in a graphical user interface, a plurality of graphical reports indicating behavior for mobile device users represented in the additional data, the behavior indicated in the plurality of patterns and graphed according to age band and gender; and

in response to receiving a request to view analysis of the additional data, present, in the graphical user interface, at least one of the plurality of graphical reports.

11. The computer program product of claim 9, wherein the instructions are further configured to cause the at least one computing device to:

group the plurality of Internet domains into a plurality of content topics representing the data;

determine browsing patterns in the data according to the plurality of content topics, the behavior being identified and processed according to a plurality of predefined age bands and gender groups; and

generate a plurality of updated rules based on the determined browsing patterns.

12. The computer program product of claim 9, wherein the instructions are further configured to cause the at least one computing device to:

determine that a portion of the plurality of utilization metrics include automated mobile device network activities; and

before categorizing the data into the plurality of Internet domains, filter the portion from the data, the filtering being based at least in part on a plurality of mobile call rules.

13. The computer program product of claim 9, wherein the plurality of Internet domains define a browsing profile associated with one or more of the plurality of mobile devices.

14. The computer program product of claim 9, wherein the plurality of utilization metrics are associated with one or more voice transaction, short message service transaction, HTTP access transaction, and location transaction.

15. The computer program product of claim 9, wherein the instructions are further configured to cause the at least one computing device to filter the data by selecting and removing a portion of the Internet domains from the data in response to determining that the data represents less than a predefined threshold time for visiting the Internet domains.

16. A system comprising:

one or more backend services hosting a user interface infrastructure to display reports representing predictive user behavior; and

at least one memory accessible by the one or more backend services, the at least one memory including instructions on a computing device; and

at least one processor on the computing device, wherein the processor is operably coupled to the at least one memory and is arranged and configured to execute the instructions that, when executed, cause the processor to implement,

obtaining data from a mobile network provider, the data including a plurality of utilization metrics pertaining to a plurality of mobile devices carrying out a plurality of network interactions, the plurality of mobile devices being associated with a plurality of users;

categorizing the data into a plurality of Internet domains comprising Internet Protocol (IP) resources associated with the data, wherein the data is categorized according to particular categories of the IP resources in which the data pertains, and wherein the IP resources include two or more of a web-site or a web-based service;

determining a plurality of patterns in the data, the plurality of patterns being used to correlate age groups represented in the data with at least a portion of the plurality of Internet domains;

determining an additional pattern in the data, the additional pattern correlating each gender represented in the data with at least a portion of the plurality of Internet domains;

generating a plurality of rules based on the plurality of patterns and the additional pattern;

generating, for presentation in the user interface, a plurality of graphical reports indicating predictive user behavior indicated in the plurality of patterns and graphed according to age band and gender; and

in response to receiving a request to view analysis of the data, presenting, in the user interface, at least one of the plurality of graphical reports.

17. The system of claim 16, wherein the processor further implements:

grouping the plurality of Internet domains into a plurality of content categories representing the data;

determining browsing patterns in the data according to the plurality of content categories, the behavior being identified and processed according to a plurality of predefined age bands and gender groups; and

generating a plurality of updated rules based on the determined browsing patterns.

18. The system of claim 16, wherein the plurality of Internet domains define a browsing profile associated with one or more of the plurality of mobile devices.

19. The system of claim 16, wherein the plurality of utilization metrics are associated with one or more voice transaction, short message service transaction, HTTP access transaction, and location transaction.

20. The system of claim 16, wherein the processor further implements filtering the data by selecting and removing a portion of the Internet domains from the data in response to determining that the data represents less than a predefined threshold time for visiting the Internet domains.