Network server arrangements for processing non-parametric, multi-dimensional, spatial and temporal human behavior or technical observations measured pervasively, and related methods for the same

Patent metadata

Field	Value
Publication number	US-9449279-B2
Application number	US-201514852255-A
Country	US
Kind code	B2
Filing date	Sep 11, 2015
Priority date	Jun 24, 2010
Publication date	Sep 20, 2016
Grant date	Sep 20, 2016

Abstract

Network server arrangement for processing non-parametric, multi-dimensional, spatial and temporal human behavior or technical observations measured pervasively, and related method for the same are disclosed. An example computer system to process usage data received from a wireless device, the computer system including a memory including machine readable instructions; and a processor to execute the instructions to: process the usage data to identify applications which were sequentially accessed on the wireless device in a time period; build a behavior model based on the identified applications, the behavior model to describe user behavior associated with the wireless device; execute the behavior model to predict usage of an application on the wireless device; based on the prediction, monitor usage of the wireless device to determine an accuracy of the prediction; and update the behavior model based on the accuracy of the prediction.

First claim

What is claimed is:

1. A tangible machine-readable medium comprising instructions which, when executed, cause a machine to at least:
process usage data to identify first and second user-invoked applications which were accessed sequentially on a wireless device in a time period, the first and second applications being accessed sequentially without an intermediary application being accessed after the first application is accessed and prior to the second application being accessed;
build, using an aggregator, a behavior model based on the identified applications, the behavior model to describe user behavior associated with the wireless device;
execute, using a predictor, the behavior model to predict usage of an application on the wireless device;
based on the prediction, monitor usage of the wireless device to determine an accuracy of the prediction; and
update the behavior model based on the accuracy of the prediction, at least one of the aggregator or the predictor includes a logic circuit.

2. The tangible machine-readable medium of claim 1 , wherein the behavior model includes time-stamped vectors.

3. The tangible machine-readable medium of claim 2 , wherein the instructions, when executed, cause the machine to correlate the time-stamped vectors to predict the usage of an application on the wireless device.

4. The tangible machine-readable medium of claim 2 , wherein the instructions, when executed, cause the machine to correlate two or more of the time-stamped vectors to identify a change in a usage pattern of one of the identified applications.

5. The tangible machine-readable medium of claim 2 , wherein the instructions, when executed, cause the machine to build the behavior model by aggregating the usage data.

6. The tangible machine-readable medium of claim 2 , wherein the usage data is first usage data, the wireless device is a first wireless device, wherein the instructions, when executed, cause the machine to correlate the first usage data and second usage data from a second wireless device to determine a similarity value between the first usage data and the second usage data.

7. The tangible machine-readable medium of claim 2 , wherein the instructions, when executed, cause the machine to process the usage data to identify application usage data and real-time location data and correlate the application usage data and the real-time location data to identify a place where at least one of the applications was used.

8. The tangible machine-readable medium of claim 1 , wherein the instructions, when executed, cause the machine to provide an advertisement to the wireless device based on the behavior model.

9. The tangible machine-readable medium of claim 1 , wherein the instructions, when executed, cause the machine to perform a cluster analysis on the usage data and to update the behavior model with results of the cluster analysis.

10. A computer system to process usage data received from a wireless device, the computer system comprising:
a memory including machine readable instructions; and
a processor to execute the instructions to:
process the usage data to identify first and second user-invoked applications which were sequentially accessed on the wireless device in a time period, the first and second applications being sequentially accessed without an intermediary application being accessed after the first application is accessed and prior to the second application being accessed;
build, using an aggregator, a behavior model based on the identified applications, the behavior model to describe user behavior associated with the wireless device;
execute, using a predictor, the behavior model to predict usage of an application on the wireless device;
based on the prediction, monitor usage of the wireless device to determine an accuracy of the prediction; and
update the behavior model based on the accuracy of the prediction, wherein at least one of the aggregator or the predictor includes a logic circuit.

11. The computer system of claim 10 , wherein the behavior model includes time-stamped vectors.

12. The computer system of claim 11 , wherein the processor is to execute the behavior model to predict the usage by correlating the time-stamped vectors to predict the usage of an application on the wireless device.

13. The computer system of claim 11 , wherein the processor is to correlate two or more of the time-stamped vectors to identify a change in a usage pattern of one of the identified applications.

14. The computer system of claim 10 , wherein the processor is to provide an advertisement to the wireless device based on the prediction.

15. The computer system of claim 14 , wherein content of the advertisement is associated with the predicted usage of the application.

16. The computer system of claim 10 , wherein the processor is to process the usage data to identify application usage data and real-time location data, and the processor is to correlate the application usage data and the real-time location data to identify a place where at least one of the applications was used.

17. The computer system of claim 16 , wherein the processor is to provide an advertisement to the wireless device based on the place.

18. The computer system of claim 10 , wherein the processor is to perform a cluster analysis on the usage data and to update the behavior model with results of the cluster analysis.

19. The computer system of claim 10 , wherein the processor is to build the behavior model by aggregating the usage data.

20. The computer system of claim 10 , wherein the usage data is first usage data, the wireless device is a first wireless device, and the processor is to correlate the first usage data and second usage data from a second wireless device to determine a similarity value between the first usage data and the second usage data.

21. The computer system of claim 10 , wherein the behavior model is a Markov model.

22. A computer implemented method to process usage data received from a wireless device, the method comprising:
processing, by executing an instruction with a processor, the usage data to identify first and second user-invoked applications accessed sequentially on the wireless device in a time period, the first and second applications being accessed sequentially without an intermediary application being accessed after the first application is accessed and prior to the second application being accessed;
building, with an aggregator implemented by the processor, a behavior model based on the identified applications, the behavior model to describe user behavior associated with the wireless device;
executing the behavior model with a predictor implemented by the processor to predict usage of an application on the wireless device;
based on the prediction, monitoring usage of the wireless device with the processor to determine an accuracy of the prediction; and
updating the behavior model with the processor based on the accuracy of the prediction by executing an instruction, wherein at least one of the aggregator or the predictor includes a logic circuit.

23. The method of claim 22 , wherein the behavior model includes time-stamped vectors.

24. The method claim 23 , further including correlating the time-stamped vectors to predict the usage of an application on the wireless device.

25. The method of claim 23 , further including correlating two or more of the time-stamped vectors to identify a change i

Assignees

• Nielsen Co Us Llc

Inventors

• Verkasalo Hannu

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F16/738

  Presentation of query results · CPC title

• G06F16/24565

  Triggers; Constraints · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06F16/29

  Geographical information databases · CPC title