Activity recognition systems and methods

• US 9,736,652 B2
• Filed: 11/05/2013
• Issued: 08/15/2017
• Est. Priority Date: 11/06/2012
• Status: Active Grant

• Current Assignee: Intertrust Technologies Corporation (Fidelio Acquisition Co LLC)
• Original Assignee: Intertrust Technologies Corporation (Fidelio Acquisition Co LLC)
• Inventors: Su, Jiawen, Ma, Yiming
• Primary Examiner(s): Diaby, Moustapha
• Application Number:
  US14/072,469
• Publication Number:
  US 20140128105A1
• Time in Patent Office: 1,379 Days
• Field of Search: None
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Systems and methods for recognizing and/or predicting activities of a user of a mobile device are disclosed. In certain embodiments, the systems and methods may predict a future activity and/or location of a mobile device user based on current and/or historical device data and/or other personal information relating to the user. In some embodiments, probabilistic determinations and/or other statistical models may be used to predict future activities and locations of a mobile device user. The disclosed systems and methods may further utilize location and/or activity recognition and/or prediction methods to deliver personalized services to a user of a mobile device at a particular time and/or location.

Claims

1. A method of providing a targeted service to a mobile device associated with a user, the method performed by a system comprising a processor and a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the system to perform the method, the method comprising:

receiving, at an interface of the system, device data from the mobile device;

identifying one or more first activities based on the device data, the one or more activities reflecting at least one current activity of the user;

identifying one or more other users related to the user based on information defining one or more social connections of the user, the one or more other users comprising one or more different individuals distinct from the user,

identifying one or more second activities based on the one or more first activities and activity information associated with the identified one or more other users, the one or more second activities reflecting at least one predicted future activity of the user associated with a predicted future location of the user, wherein identifying the one or more second activities comprises modeling a probability of one or more candidate activities occurring after the one or more first activities and selecting the one or more second activities from the one or more candidate activities based on a relative probability associated with the one or more second activities; and

transmitting, from the interface, information associated with a personalized service to the user based on the at least one predicted future activity,

wherein the personalized service comprises a targeted advertising service and the transmitted information comprises a targeted advertisement associated with an entity proximate to the predicted future location of the user.

2. The method of claim 1, wherein at least one current activity of the one or more first activities is associated with a current location of the user.

3. The method of claim 1, wherein the device data comprises at least one of data obtained by one or more sensors of the mobile device, location information of the mobile device, data generated by the user'"'"'s interactions with the mobile device, spatial historical travel patterns of the user of the mobile device, and temporal historical travel patterns of the user of the device.

4. The method of claim 1, wherein selecting the one or more second activities from the one or more candidate activities is further based on the one or more second activities having an associated probability exceeding a threshold.

5. The method of claim 4, wherein the probability of the one or more candidate activities occurring after the one or more first activities is modeled using a hidden Markov model.

6. The method of claim 4, wherein modeling the probability of the one or more candidate activities occurring after the one or more first activities is based on historical device data collected by the mobile device.

7. The method of claim 1, wherein the information defining the one or more social connections of the user comprises user contact information.

8. The method of claim 1, wherein the information defining the one or more social connections of the user comprises information received from a social media service.

9. The method of claim 1, wherein the information defining the one or more social connections of the user comprises information included in the received device data.