Determining an active persona of a user device

Patent metadata

Field	Value
Publication number	US-9405838-B2
Application number	US-201414446991-A
Country	US
Kind code	B2
Filing date	Jul 30, 2014
Priority date	Dec 27, 2013
Publication date	Aug 2, 2016
Grant date	Aug 2, 2016

Abstract

A method for determining an active persona of a user device includes determining a first user device state of a user device. The active persona is indicative of a predicted objective of the user of the user device. The first state defines an action currently being performed on the user device and a set of observations corresponding to the user device. The method includes inputting the first user device state to a model and determining the active persona of the user device based on the output of the model. The model is configured to receive a user device state and outputs probability values associated with one or more clusters, each cluster being indicative of one or more items of interest corresponding to the user device. The method further includes performing a procedure using the active persona of the user device.

First claim

What is claimed is:

1. A method comprising:
determining, by a processing device, a first user device state of a user device, the first user device state defining an action currently being performed on the user device and one or more observations corresponding to the user device;
inputting, by the processing device, the first user device state to a model that receives a user device state and outputs probability values associated with one or more clusters, each cluster being indicative of one or more items of interest corresponding to the user device;
determining, by the processing device, an active persona of the user device based on the output of the model, the active persona being indicative of a predicted objective of a user of the user device; and
performing, by the processing device, a procedure using the active persona of the user device.

2. The method of claim 1 , further comprising:
capturing, by the processing device, a second user device state after determining the active persona of the user device the second user device state being subsequent to the first user device state and defining a subsequent action being performed on the user device and one or more subsequent observations; and
updating, by the processing device, the model based on the second user device state and the first user device state.

3. The method of claim 1 , wherein the model is a Hidden Markov Model.

4. The method of claim 1 , wherein the action being performed by the user device is based on an active process of the user device.

5. The method of claim 4 , wherein the active process is one of an active application being executed by the user device, an active media content being played by the user device, or an active search query being provided by the user device.

6. The method of claim 4 , wherein determining the first user device state includes determining an active cluster to which the active process corresponds using an inverted index, the active cluster being indicative of an active item of interest corresponding to the user device.

7. The method of claim 6 , further comprising:
determining, by the processing device, a plurality of items of interest of the user device, each item of interest indicating one of an application installed on the user device, a media content previously played on the user device, or a search query previously provided from the user device;
providing, by the processing device, the plurality of items of interest to a persona server; and
receiving, by the processing device, the inverted index from the persona server, the inverted index containing a plurality of inverted index entries, each inverted index entry corresponding to one of the items of interest and identifying one or more clusters to which the item of interest belongs.

8. The method of claim 1 , wherein determining the first user device state includes obtaining output values of one or more peripheral devices of the user device.

9. The method of claim 1 , wherein performing the procedure using the active persona includes communicating the active persona to a search engine as part of a search query.

10. The method of claim 1 , wherein performing the procedure using the active persona includes communicating the active persona to an application server in communication with the user device.

11. The method of claim 1 , wherein performing the procedure using the active persona includes rearranging a home screen of the user device based on the active persona.

12. The method of claim 1 , wherein the active persona is a vector indicating the probabilities output by the model, wherein each element of the vector indicates a probability that the user device will transition from a current item of interest to a cluster associated with the probability value that contains a second item of interest.

13. The method of claim 1 , wherein obtaining the active persona includes:
obtaining a vector indicating the probabilities output by the model, each element of the vector indicating a probability that the user device will transition from a current item of interest to a cluster associated with the probability value that contains a second item of interest; and
mapping the vector to a category based on one or more rules.

14. A user device comprising:
a storage device including one or more computer readable mediums that store a model that receives a user device state of a user device and outputs probability values associated with one or more clusters, each cluster being indicative of one or more items of interest corresponding to the user device; and
a processing device, the processing device executing computer-readable instructions that when executed by the processing device cause the user device to:
determine a first user device state of the user device, the first user device state defining an action currently being performed on the user device and one or more observations corresponding to the user device;
input the first user device state to the model;
determine an active persona of the user device based on the output of the model, the active persona being indicative of a predicted objective of the user of the user device; and
perform a procedure using the active persona of the user device.

15. The user device of claim 14 , wherein the computer readable instructions further cause the processing device to:
capture a second user device state after determining the active persona of the user device the second user device state being subsequent to the first user device state and defining a subsequent action being performed on the user device and one or more subsequent observations; and
update the model based on the first user device state and the second user device state.

16. The user device of claim 14 , wherein the model is a Hidden Markov Model.

17. The user device of claim 14 , wherein the action being performed by the user device is based on an active process of the user device.

18. The user device of claim 17 , wherein the active process is one of an active application being executed by the user device, an active media content being played by the user device, or an active search query being provided by the user device.

19. The user device of claim 18 , wherein determining the first user device state includes determining an active cluster to which the active process corresponds using an inverted index, the active cluster being indicative of an active item of interest corresponding to the user device.

20. The user device of claim 19 , wherein the computer readable instructions further cause the processing device to:
determine a plurality of items of interest of the user device, each item of interest indicating one of an application installed on the user device, a media content previously played by the user device, or a search query previously provided from the user device;
provide the plurality of items of interest to a persona server; and
receive the inverted index from the persona server, the inverted index containing a plurality of inverted index entries, each inverted index entry corresponding to one of the items of interest and identifying one or more clusters to which the item of interest belongs.

21. The user device of claim 14 , wherein determining the first user device state includes obtaining output values of one or more peripheral devices of the user device.

22. The user device of claim 14 , wherein performing the procedure using the active persona includes communicating the active persona to a search

Assignees

• Quixey Inc

Inventors

• Patil Sameer
• Glover Eric J

Classifications

• G06F17/30867 Primary

  Physics · mapped topic

• G06F17/30622

  Physics · mapped topic

• G06Q30/0251

  Targeted advertisements · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title