CONTEXTUAL INFORMATION PROVIDER

• US 20140032453A1
• Filed: 07/24/2013
• Published: 01/30/2014
• Est. Priority Date: 07/25/2012
• Status: Active Grant

• Current Assignee: ARO, Inc. (Dibona Holding)
• Original Assignee: ARO, Inc. (Dibona Holding)
• Inventors: Eustice, Kevin Francis, Liu, Alan Linchuan, Perkowitz, Michael, Hickl, Andrew F., Allen, Paul G.
• Granted Patent: US 8,892,480 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A user'"'"'s context history is used to help select contextual information to provide to the user. Context data describing the user'"'"'s current context is received and a plurality of information items corresponding to the user'"'"'s current context are identified from a contextual information corpus. A personalized user behavior model for the user is applied to determine the likelihood that each of the identified information items will be of value to the user. One or more of the information items are selected based on the corresponding likelihoods and the selected information items are provided for presentation to the user.

Claims

1. A method of providing contextual information to a user, comprising:

receiving context data describing the user'"'"'s current context;

identifying a plurality of information items corresponding to the user'"'"'s current context;

applying a personalized user behavior model for the user to determine, for each of the plurality of information items, a likelihood that the information item will be of value to the user;

selecting an information item from among the plurality of information items based on the corresponding likelihood; and

providing the selected information item for presentation to the user.

2. The method of claim 1, wherein the context data includes an indication of at least two of:

a current location of the user, a current time, and a current activity of the user.

3. The method of claim 1, wherein identifying a plurality of items corresponding to the user'"'"'s current context comprises:

determining a location of the user from the contextual data;

determining a distance between the location of the user and a location corresponding to a first information item in a corpus; and

including the first information item in the plurality of information items responsive to the distance being less than a threshold.

4. The method of claim 1, wherein the personalized user behavior model comprises a routine model and identifying a plurality of items corresponding to the user'"'"'s current context comprises:

applying the routine model to the user'"'"'s current context to predict a likely future location for the user;

determining a distance between the likely future location and a location corresponding to a first information item in a corpus; and

including the first information item in the plurality of information items responsive to the distance being less than a threshold.

5. The method of claim 1, wherein the personalized user behavior model comprises a routine model and identifying a plurality of items corresponding to the user'"'"'s current context comprises:

applying the routine model to the user'"'"'s current context to predict a likely future context for the user;

comparing the likely future context to a first context associated with a first information item in a corpus; and

including the first information item in the plurality of information items responsive to a correspondence between the likely future context and the first context.

6. The method of claim 1, wherein the user behavior model comprises a routine model that describes correlations between contexts, the routine model comprising a transition rule including a source context and a destination context, the likelihood of a given information item being of value based on both the source context corresponding to the user'"'"'s current context and the destination context corresponding to the given information item.

7. The method of claim 1, wherein the user behavior model comprises a personality model comprising a plurality of metrics indicating the user'"'"'s position on a corresponding plurality of personality dimensions, the likelihood of a given information item being of value based on a correspondence between the plurality of metrics and the given information item.

8. The method of claim 1, further comprising:

receiving feedback indicating the user found value in presentation of the selected information item; and

updating the user behavior model such that information items of a same type as the selected information item are in future determined to have a higher likelihood of value to the user.

9. The method of claim 1, wherein the user behavior model comprises a personality model comprising a plurality of metrics indicating the user'"'"'s affinity with a corresponding plurality of personality traits, the method further comprising:

receiving feedback indicating the user found value in presentation of the selected information item; and

identifying one or more contributing personality traits from among the plurality of personality traits based on the contributing personality traits having contributed to selection of the selected information item; and

increasing the user'"'"'s affinity with the contributing personality traits.

10. The method of claim 1, wherein the user behavior model comprises a routine model that describes correlations between contexts, the routine model comprising a plurality of transition rules, the method further comprising:

receiving feedback indicating the user found value in presentation of the selected information item; and

identifying a contributing transition rule from among the plurality of transition rules based on the contributing transition rule having contributed to selection of the selected information item, the contributing transition rule comprising a source context and a destination context; and

storing an indication that the user found value in presentation of the selected information item in conjunction with the contributing transition rule such that information items associated with destination context are in future determined to have a higher likelihood when the user is associated with the source context.

11. A non-transitory computer-readable storage medium comprising executable computer program code for providing contextual information to a user, the computer program code comprising instructions for:

receiving context data describing the user'"'"'s current context;

identifying a plurality of information items corresponding to the user'"'"'s current context;

applying a personalized user behavior model for the user to determine, for each of the plurality of information items, a likelihood that the information item will be of value to the user;

selecting an information item from among the plurality of information items based on the corresponding likelihood; and

providing the selected information item for presentation to the user.

12. The non-transitory computer-readable storage medium of claim 11, wherein the context data includes an indication of at least two of:

a current location of the user, a current time, and a current activity of the user.

13. The non-transitory computer-readable storage medium of claim 11, wherein identifying a plurality of items corresponding to the user'"'"'s current context comprises:

determining a location of the user from the contextual data;

determining a distance between the location of the user and a location corresponding to a first information item in a corpus; and

including the first information item in the plurality of information items responsive to the distance being less than a threshold.

14. The non-transitory computer-readable storage medium of claim 11, wherein the personalized user behavior model comprises a routine model and identifying a plurality of items corresponding to the user'"'"'s current context comprises:

applying the routine model to the user'"'"'s current context to predict a likely future location for the user;

determining a distance between the likely future location and a location corresponding to a first information item in a corpus; and

including the first information item in the plurality of information items responsive to the distance being less than a threshold.

15. The non-transitory computer-readable storage medium of claim 11, wherein the personalized user behavior model comprises a routine model and identifying a plurality of items corresponding to the user'"'"'s current context comprises:

applying the routine model to the user'"'"'s current context to predict a likely future context for the user;

comparing the likely future context to a first context associated with a first information item in a corpus; and

including the first information item in the plurality of information items responsive to a correspondence between the likely future context and the first context.

16. The non-transitory computer-readable storage medium of claim 11, wherein the user behavior model comprises a routine model that describes correlations between contexts, the routine model comprising a transition rule including a source context and a destination context, the likelihood of a given information item being of value based on both the source context corresponding to the user'"'"'s current context and the destination context corresponding to the given information item.

17. The non-transitory computer-readable storage medium of claim 11, wherein the user behavior model comprises a personality model comprising a plurality of metrics indicating the user'"'"'s position on a corresponding plurality of personality dimensions, the likelihood of a given information item being of value based on a correspondence between the plurality of metrics and the given information item.

18. The non-transitory computer-readable storage medium of claim 11, the computer program code further comprising instructions for:

receiving feedback indicating the user found value in presentation of the selected information item; and

updating the user behavior model such that information items of a same type as the selected information item are in future determined to have a higher likelihood of value to the user.

19. The non-transitory computer-readable storage medium of claim 11, wherein the user behavior model comprises a personality model comprising a plurality of metrics indicating the user'"'"'s affinity with a corresponding plurality of personality traits, the computer program code further comprising instructions for:

receiving feedback indicating the user found value in presentation of the selected information item; and

identifying one or more contributing personality traits from among the plurality of personality traits based on the contributing personality traits having contributed to selection of the selected information item; and

increasing the user'"'"'s affinity with the contributing personality traits.

20. The non-transitory computer-readable storage medium of claim 11, wherein the user behavior model comprises a routine model that describes correlations between contexts, the routine model comprising a plurality of transition rules, the computer program code further comprising instructions for:

receiving feedback indicating the user found value in presentation of the selected information item; and

identifying a contributing transition rule from among the plurality of transition rules based on the contributing transition rule having contributed to selection of the selected information item, the contributing transition rule comprising a source context and a destination context; and

storing an indication that the user found value in presentation of the selected information item in conjunction with the contributing transition rule such that information items associated with destination context are in future determined to have a higher likelihood when the user is associated with the source context.