INFERRING USER MOOD BASED ON USER AND GROUP CHARACTERISTIC DATA

• US 20140025620A1
• Filed: 07/23/2012
• Published: 01/23/2014
• Est. Priority Date: 07/23/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Greenzeiger, Michael Froimowitz, Phulari, Ravindra, Sanghavi, Mehul K.
• Granted Patent: US 8,965,828 B2
• Time in Patent Office: Days
• US Class Current: 706/47
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

An individual'"'"'s responsiveness to targeted content delivery can be affected by a number of factors, such as an interest in the content, other content the user is currently interacting with, the user'"'"'s current location, or even the time of day. A way of improving targeted content delivery can be to infer a user'"'"'s current mood and then deliver content that is selected, at least in part, based on the inferred mood. The present technology analyzes mood-associated characteristic data collected over a period of time to produce at least one baseline mood profile for a user. The user'"'"'s current mood can then be inferred by applying one or more mood rules to compare current mood-associated data to at least one baseline mood profile for the user.

Claims

1. A computer-implemented method comprising:

receiving current mood-associated data associated with a user, the current mood-associated data specifying one or more current mood-associated data items, wherein at least one current mood-associated data item corresponds to a recently consumed content item;

obtaining at least one baseline mood profile;

applying, via a processor, at least one mood rule to the current mood-associated data and the at least one baseline mood profile to generate an inferred mood for the user.

2. The method of claim 1, wherein the at least one current mood-associated data item has associated event data, the event data corresponding to how the consumption of the content item occurred.

3. The method of claim 2, wherein event data comprises at least one of date, day, time, day part, location, device type, network, or website.

4. The method of claim 1 further comprising:

assigning a confidence score to the inferred mood.

5. The method of claim 1, wherein the at least one baseline mood profile is specific to the user.

6. The method of claim 1, wherein applying at least one mood rule to generate an inferred mood further comprises:

applying a first mood rule to the current mood-associated data and the at least one baseline mood profile to generate a first inferred mood with an associated first confidence score;

applying a second mood rule to the current mood-associated data and the at least one baseline mood profile to generate a second inferred mood with an associated second confidence score;

selecting one of the first inferred mood and the second inferred mood based on the first confidence score and the second confidence score.

7. The method of claim 1, further comprising:

assigning the user to at least one mood segment based on the inferred mood.

8. A non-transitory computer-readable storage media storing instructions which, when executed by a computing device, causes the computing device to perform steps comprising:

receiving user characteristic data associated with a user, the user characteristic data specifying one or more current mood-associated characteristic values, wherein at least one current mood-associated characteristic value corresponds to a recently consumed content item;

analyzing the user characteristic data with respect to at least one obtained baseline mood profile to generate an inferred mood for the user;

identifying a plurality of targeted content packages for the user, wherein the identifying is performed independent of the inferred mood;

prioritizing the plurality of targeted content packages, wherein the prioritizing is based at least in part on the inferred mood;

9. The non-transitory computer-readable storage media of claim 8 further comprising:

serving to the user, a targeted content package, the targeted content package selected from the prioritized plurality of targeted content packages.

10. The non-transitory computer-readable storage media of claim 8 further comprising:

updating the at least one obtained baseline mood profile based on the received user characteristic data.

11. The non-transitory computer-readable storage media of claim 8, wherein the at least one current mood-associated characteristic value has associated event data, the event data corresponding to how the consumption of the content item occurred.

12. The non-transitory computer-readable storage media of claim 8, wherein a recently consumed content item comprises at least one of a digital media item, a social networking activity, or an invitational content item response.

13. The non-transitory computer-readable storage media of claim 12, wherein a current mood-associated characteristic value further corresponds to at least one of facial expression characteristics, vocal expression characteristics, or biometric values.

14. A system comprising:

a server;

a first module configured to control the server to obtain user characteristic data, the user characteristic data comprising mood-associated characteristic data, wherein the mood-associated characteristic data species at least one recently consumed content item;

a second module configured to control the server to obtain at least one baseline mood profile;

a third module configured to control the server to derive an inferred current mood by comparing the mood-associated characteristic data to the at least one obtained baseline mood profile;

a fourth module configured to control the server to assign the user to a mood segment based on the inferred current mood.

15. The system of claim 14 further comprising:

a fifth module configured to control the server to re-generate at least one baseline mood profile based on the received user characteristic data.

16. The system of claim 14, wherein obtaining a baseline mood profile further comprises:

a fifth module configured to control the server to obtain mood-associated characteristic data associated with the user;

a sixth module configured to control the server to analyze the mood-associated characteristic data to generate the baseline mood profile.

17. The system of claim 14, further comprising:

a fifth module configured to control the server to serve a targeted content package based on the assigned mood segments.

18. The system of claim 14, wherein the at least one recently consumed content item has an assigned weight.

19. The system of claim 18, wherein an assigned weight is higher when a content item is consumed more recently.

20. The system of claim 18, wherein an assigned weight is higher when a content item is more frequently consumed.

21. The system of claim 14, wherein comparing the mood-associated characteristic data to the at least one baseline mood profile is performed by applying at least one mood rule.

22. A method comprising:

receiving current mood-associated data associated with a user, the current mood-associated data specifying one or more current mood-associated data items, wherein at least one current mood-associated data item corresponds to a recently consumed content item;

deriving, via a processor, an inferred mood for the user by applying at least one mood rule to the current mood-associated data and at least one obtained baseline mood profile;

identifying a plurality of targeted content packages for the user, wherein the identifying is performed independent of an inferred mood;

prioritizing the plurality of targeted content packages, wherein the prioritizing is based at least in part on the inferred mood;

23. The method of claim 22, wherein at least one baseline mood profile is a general baseline mood profile.

24. The method of claim 23 further comprising:

serving to the user, a targeted content package, the targeted content package selected from the prioritized plurality of content packages.

25. A computer implemented method comprising:

receiving user characteristic data associated with an identified user, the user characteristic data comprising current mood-associated characteristic data, wherein the current mood-associated characteristic data specifies at least one recently consumed content item;

obtaining at least one baseline mood profile for the identified user;

inferring, via a processor, a current mood based on a relationship between the received current mood-associated characteristic data and the at least one baseline mood profile;

sending the inferred current mood.

26. The method of claim 25 further comprising:

updating at least one baseline mood profile based on the received current mood-associated characteristic data; and

purging the received user characteristic data.

27. The method of claim 25, wherein the inferred current mood is sent in conjunction with a request for invitational content.