Location-based recommendation generator

• US 9,906,611 B2
• Filed: 09/21/2015
• Issued: 02/27/2018
• Est. Priority Date: 09/21/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Ganci, Jr., John M., Rakshit, Sarbajit K., Trim, Craig M.
• Primary Examiner(s): Keehn, Richard G
• Application Number:
  US14/859,442
• Publication Number:
  US 20170085657A1
• Time in Patent Office: 890 Days
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A computer-implemented method includes identifying a profile. The method identifies one or more mobility patterns. The one or more mobility patterns are associated with the profile. The method identifies social media content from at least one location. The social media content from at least one location is associated with the profile. The method identifies user generated content from at least one location. The user generated content is associated with the profile. The method determines a set of behavioral patterns for the profile. The set of behavioral patterns is based on the mobility patterns, the social media content from at least one location, and the user generated content from at least one location. The method returns a recommendation for the profile. A corresponding computer system and computer program product are also disclosed.

Claims

1. A computer-implemented method comprising:

identifying a profile;

monitoring online activity of a user associated with the profile;

based, at least in part, on a frequency of access of a given online location by the user, identifying one or more online activity patterns for the user based on said online activity, said one or more online activity patterns being associated with the user associated with said profile;

identifying social media content from at least one location frequented by the user, said social media content from at least one location being associated with the user associated with said profile;

identifying user generated content from at least one location, said user generated content being associated with the user associated with said profile;

determining a set of time-based behavioral patterns for the user associated with said profile, said set of time-based behavioral patterns being based on said online activity patterns, said social media content from at least one location, and said user generated content from at least one location; and

based on a behavior being predicted to occur within a specific time period that is associated with the behavioral pattern of the user, returning a recommendation for the user associated with said profile prior to the behavior being exhibited by the user, said recommendation being based on said set of time-based behavioral patterns.

2. The computer-implemented method of claim 1, wherein identifying one or more online activity patterns comprises:

identifying one or more primary locations; and

associating the one or more primary locations with the user associated with said profile.

3. The computer-implemented method of claim 1, wherein determining a set of time-based behavioral patterns for the user associated with said profile comprises:

analyzing text data, said text data being extracted from said social media content and said user generated content; and

constructing said set of time-based behavioral patterns based on said text data.

4. The computer implemented method of claim 3, wherein analyzing text data is based on psycholinguistic factors.

5. The computer implemented method of claim 1, wherein determining a set of time-based behavioral patterns for the user associated with said profile comprises:

aggregating said set of time-based behavioral patterns for the user associated with said profile with one or more alternative sets of time-based behavioral patterns for one or more alternative profiles;

constructing an aggregated set of time-based behavioral patterns; and

constructing said set of time-based behavioral patterns, said set of behavior patterns being based on said aggregated set of time-based behavioral patterns.

6. The computer implemented method of claim 5, wherein aggregating said set of time-based behavioral patterns for the user associated with said profile with one or more alternative sets of time-based behavioral patterns for one or more alternative profiles comprises:

identifying at least one point of commonality between said set of time-based behavioral patterns and said alternative set of time-based behavioral patterns; and

returning a recommendation, said recommendation being based on said at least one point of commonality between said set of time-based behavioral patterns and said alternative set of time-based behavioral patterns.

7. A computer program product comprising:

one or more computer readable storage media and program instructions stored on one or more computer readable storage media, said program instructions comprising instructions to;

identify a profile;

monitor online activity of a user associated with the profile;

based, at least in part, on a frequency of access of a given online location by the user, identify one or more online activity patterns for the user based on said online activity, said one or more online activity patterns being associated with the user associated with said profile;

identify social media content from at least one location frequented by the user, said social media content from at least one location being associated with the user associated with said profile;

identify user generated content from at least one location, said user generated content being associated with the user associated with said profile;

determine a set of time-based behavioral patterns for the user associated with said profile, said set of time-based behavioral patterns being based on said online activity patterns, said social media content from at least one location, and said user generated content from at least one location; and

based on a behavior being predicted to occur within a specific time period that is associated with the behavioral pattern of the user, return a recommendation for the user associated with said profile prior to the behavior being exhibited by the user, said recommendation being based on said set of time-based behavioral patterns.

8. The computer program product of claim 7, wherein said program instructions to identify one or more online activity patterns comprise instructions to:

identify one or more primary locations; and

associate the one or more primary locations with the user associated with said profile.

9. The computer program product of claim 7, wherein said program instructions to determine a set of time-based behavioral patterns for the user associated with said profile comprise instructions to:

analyze text data, said text data being extracted from said social media content and said user generated content; and

construct said set of time-based behavioral patterns based on said text data.

10. The computer program product of claim 9, wherein said program instructions to analyze text data are based on psycholinguistic factors.

11. The computer program product of claim 7, wherein said program instructions to determine a set of time-based behavioral patterns for the user associated with said profile comprise instructions to:

aggregate said set of time-based behavioral patterns for the user associated with said profile with one or more alternative sets of time-based behavioral patterns for one or more alternative profiles;

construct an aggregated set of time-based behavioral patterns; and

construct said set of time-based behavioral patterns, said set of behavior patterns being based on said aggregated set of time-based behavioral patterns.

12. The computer program product of claim 11, wherein said program instructions to aggregate said set of time-based behavioral patterns for the user associated with said profile with a second set of time-based behavioral patterns for a second profile comprise instructions to:

identify at least one point of commonality between said sets of time-based behavioral patterns; and

determine, based on said at least one point of commonality between said set of time-based behavioral patterns and said alternative set of time-based behavioral patterns.

13. A computer system comprising:

one or more computer processors;

one or more computer readable storage media;

computer program instructions stored;

said computer program instructions being stored on said computer readable storage media for execution by at least one of said one or more processors, said program instructions comprising instructions to;

identify a profile;

monitor online activity of a user associated with the profile;

based, at least in part, on a frequency of access of a given online location by the user, identify one or more online activity patterns for the user based on said online activity, said one or more online activity patterns being associated with the user associated with said profile;

identify social media content from at least one location frequented by the user, said social media content from at least one location being associated with the user associated with said profile;

identify user generated content from at least one location, said user generated content being associated with the user associated with said profile;

determine a set of time-based behavioral patterns for the user associated with said profile, said set of time-based behavioral patterns being based on said online activity patterns, said social media content from at least one location, and said user generated content from at least one location; and

based on a behavior being predicted to occur within a specific time period that is associated with the behavioral pattern of the user, return a recommendation for the user associated with said profile prior to the behavior being exhibited by the user, said recommendation being based on said set of time-based behavioral patterns.

14. The computer system of claim 13, wherein said program instructions comprising instructions to identify one or more online activity patterns comprise program instructions comprising instructions to:

identify one or more primary locations; and

associate the one or more primary locations with the user associated with said profile.

15. The computer system of claim 13, wherein said program instructions comprising instructions to determine a set of time-based behavioral patterns for the user associated with said profile comprise program instructions comprising instructions to:

analyze text data, said text data being extracted from said social media content and said user generated content; and

construct said set of time-based behavioral patterns based on said text data.

16. The computer system of claim 15, wherein said program instructions comprising instructions to analyze text data are based on psycholinguistic factors.

17. The computer system of claim 13, wherein said program instructions comprising instructions to determine a set of time-based behavioral patterns for the user associated with said profile comprise program instructions to:

aggregate said set of time-based behavioral patterns for the user associated with said profile with one or more alternative sets of time-based behavioral patterns for one or more alternative profiles;

construct an aggregated set of time-based behavioral patterns; and

construct said set of time-based behavioral patterns, said set of time-based behavior patterns being based on said aggregated set of time-based behavioral patterns.

18. The computer system of claim 17, wherein said program instructions comprising instructions to aggregate said set of time-based behavioral patterns for the user associated with said profile with a second set of time-based behavioral patterns for a second profile comprise program instructions to:

identify at least one point of commonality between said sets of time-based behavioral patterns; and

determine, based on said at least one point of commonality between said set of time-based behavioral patterns and said alternative set of time-based behavioral patterns.