Personalized content and services based on profile information

• US 10,341,459 B2
• Filed: 09/18/2015
• Issued: 07/02/2019
• Est. Priority Date: 09/18/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Abrahams, Faried, Dhondse, Amol A., Holley, Kerrie L., Pikle, Anand, Sivakumar, Gandhi, Thomas, Lennox E.
• Primary Examiner(s): Savla, Arpan P.
• Assistant Examiner(s): Davanlou, Soheila (Gina)
• Application Number:
  US14/858,407
• Publication Number:
  US 20170086029A1
• Time in Patent Office: 1,383 Days
• Field of Search: None
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

An approach includes a system implemented in a computer infrastructure including a processor. The approach further includes the processor configured to receive dimensionally aware linkages. The approach further includes the processor configured to retrieve aggregated data from a data set. The approach further includes the processor configured to identify at least one affinity cluster related to the dimensionally aware linkages in at least two dimensions and the retrieved aggregated data by performing at least one lookup linkage which matches at least one dimension of the at least two dimensions of the dimensionally aware linkages with the retrieved aggregated data. The approach further includes the processor configured to provide personalized content to a user having same or similar user preferences as the received dimensionally aware linkages based on the identified at least one affinity cluster.

Claims

1. A system implemented in a computer infrastructure including a processor configured to:

receive, by the processor, dimensionally aware linkages in at least two dimensions including a time period and a location on a geospatial map;

retrieve, by the processor, aggregated data from a data set of mobile data, social media data, Internet data, private network data, and cloud computing data;

identify, by the processor, at least one affinity cluster related to the dimensionally aware linkages in the at least two dimensions and the retrieved aggregated data by performing at least one lookup linkage which matches at least one dimension of the at least two dimensions of the dimensionally aware linkages with the retrieved aggregated data; and

provide, by the processor, personalized content dynamically and in real-time with a high level of confidence to a user having same or similar user preferences as the received dimensionally aware linkages based on the identified at least one affinity cluster,

wherein the dimensionally aware linkages associate the time period and the location together to form linkages in the at least two dimensions,

the processor comprises a profile crawler which is configured to self-learn based on behavioral patterns, the received dimensionally aware linkages, and the at least one affinity cluster, and

the processor is further configured to;

increase a confidence level of the identified at least one affinity cluster for providing the personalized content in response to a number of matches of the at least one dimension of the dimensionally aware linkages exceeding a predetermined threshold,

decrease the confidence level of the identified at least one affinity cluster for providing the personalized content in response to the number of matches of the at least one dimension of the dimensionally aware linkages not exceeding the predetermined threshold,

broaden a first dimension of the dimensionally aware linkages in response to a number of matches of the first dimension of the dimensionally aware linkages not exceeding a first predetermined threshold and reevaluating the broader first dimension to identify a first affinity cluster, and

broaden a second dimension of the dimensionally aware linkages in response to a number of matches of the second dimension of the dimensionally aware linkages not exceeding a second predetermined threshold and reevaluating the broader second dimension to identify a second affinity cluster.

2. The system of claim 1, wherein the data set further comprises machine-generated data, navigational data, and vehicle data.

3. The system of claim 1, wherein the at least two dimensions further comprises a profile set and a subject.

4. The system of claim 1, wherein the personalized content comprises at least one of an audio selection, a video selection, a television program, and a campaign.

5. The system of claim 1, wherein the processor configured to identify the at least one affinity cluster further comprises:

performing first lookup linkages which match the first dimension of the at least two dimensions of the dimensionally aware linkages with the retrieved aggregated data;

identifying the first affinity cluster related to the first dimension of the dimensionally aware linkages in response to the number of matches of the first dimension of the dimensionally aware linkages exceeding the first predetermined threshold;

performing second lookup linkages which match the second dimension of the at least two dimensions of the dimensionally aware linkages with the retrieved aggregated data;

identifying the second affinity cluster related to the second dimension of the dimensionally aware linkages in response to the number of matches of the second dimension of the dimensionally aware linkages exceeding the second predetermined threshold; and

providing the personalized content based on the identified at least one affinity cluster which comprises the first affinity cluster and the second affinity cluster.

6. The system of claim 1, wherein the processor is further configured to associate at least one of a subject and a profile set to the identified at least one affinity cluster based on the dimensionally aware linkages in the at least two dimensions and the retrieved aggregated data in order to provide the personalized content to the user having same or similar user preferences as the received dimensionally aware linkages.

7. The system of claim 1, wherein the predetermined threshold is hard coded in the profile crawler.

8. The system of claim 7, wherein the predetermined threshold is a same number as the first predetermined threshold and the second predetermined threshold.

9. A method comprising:

receiving, by a computer processor, a request for a profile affinity which comprises at least two dimensions including a time period and a location on a geospatial map;

comparing, by the computer processor, at least one dimension of the profile affinity which comprises the at least two dimensions with aggregated data in order to dynamically and in real-time with a high level of confidence find a match between the at least one dimension of the profile affinity which comprises the at least two dimensions and the aggregated data;

increasing, by the computer processor, a confidence level for providing personalized content in response to the match existing between the at least one dimension of the profile affinity and the aggregated data; and

decreasing, by the computer processor, the confidence level for providing the personalized content in response to the match not existing between the at least one dimension of the profile affinity and the aggregated data;

broadening, by the computer processor, a first dimension of the at least one dimension in response to the match not existing between the first dimension of the profile affinity and the aggregated data, and reevaluating the broader first dimension to identify a first affinity cluster, and

broadening, by the computer processor, a second dimension of the at least one dimension in response to the match not existing between the second dimension of the profile affinity and the aggregated data, and reevaluating the broader second dimension to identify a second affinity cluster,

wherein the aggregated data comprises a data set of mobile data, social media data, Internet data, private network data, and cloud computing data,

the profile affinity associates the time period and the location together to form linkages in the at least two dimensions, and

the computer processor comprises a profile crawler which is configured to self-learn based on behavioral patterns, the linkages in the at least two dimensions, and the profile affinity.

10. The method of claim 9, wherein the at least two dimensions further comprises a profile set and a subject.

11. The method of claim 9, further comprising retrieving linked affinity clusters in response to the match existing between the at least one dimension of the profile affinity and the aggregated data.

12. The method of claim 9, further comprising:

retrieving linked affinity clusters in response to a match existing between the broadened at least one dimension of the profile affinity and the aggregated data.

13. The method of claim 9, wherein the personalized content comprises at least one of an audio selection, a video selection, a television program, and a campaign.

14. A computer program product for providing at least one service, the computer program product comprising a computer readable hardware storage device having readable program code stored thereon, the program code comprising:

first program code executable by a processor to obtain dimensionally aware linkages in at least two dimensions including a time period and a location on a geospatial map;

second program code executable by the processor to obtain aggregate data from a data set of mobile data, social media data, Internet data, private network data, and cloud computing data;

third program code executable by the processor to identify at least one affinity cluster related to the dimensionally aware linkages in the at least two dimensions and the obtained aggregated data by performing at least one lookup linkage which matches at least one dimension of the at least two dimensions of the dimensionally aware linkages with the obtained aggregated data; and

fourth program code executable by the processor to provide the at least one service dynamically and in real-time with a high level of confidence to a user having same or similar user preferences as the obtained dimensionally aware linkages based on the identified at least one affinity cluster;

fifth program code executable by the processor to increase a confidence level of the identified at least one affinity cluster for providing the at least one service in response to a number of matches of the at least two dimensions of the dimensionally aware linkages exceeding a predetermined threshold;

sixth program code executable by the processor to decrease the confidence level of the identified at least one affinity cluster for providing the at least one service in response to the number of matches of the at least two dimensions of the dimensionally aware linkages not exceeding the predetermined threshold;

seventh program code executable by the processor to broaden a first dimension of the dimensionally aware linkages in response to a number of matches of the first dimension of the dimensionally aware linkages not exceeding a first predetermined threshold and reevaluating the broader first dimension to identify a first affinity cluster; and

eighth program code executable by the processor to broaden a second dimension of the dimensionally aware linkages in response to a number of matches of the second dimension of the dimensionally aware linkages not exceeding a second predetermined threshold and reevaluating the broader second dimension to identify a second affinity cluster,

wherein the dimensionally aware linkages associate the time period and the location together to form linkages in the at least two dimensions, and

the processor comprises a profile crawler which is configured to self-learn based on behavioral patterns, the received dimensionally aware linkages, and the at least one affinity cluster.

15. The computer program product of claim 14, wherein the data set further comprises machine-generated data, navigational data, and vehicle data.

16. The computer program product of claim 14, wherein the at least one service comprises at least one of an insight, a recommendation, and an alert.

17. The computer program product of claim 14, wherein the at least two dimensions further comprises a profile set and a subject.