Methods and systems for transforming multiple data streams into social scoring and intelligence on individuals and groups

• US 9,594,810 B2
• Filed: 03/15/2013
• Issued: 03/14/2017
• Est. Priority Date: 09/24/2012
• Status: Active Grant

• Current Assignee: Jungotv LLC
• Original Assignee: Reunify
• Inventors: Fullman, Elena, Adibi, Jafar, Fullman, Edward, Fullman, Joseph, Robertson, Patrick, Ettelaie, Emil, Kwon, Namhee
• Primary Examiner(s): Liu, Hexing
• Application Number:
  US13/843,431
• Publication Number:
  US 20140089334A1
• Time in Patent Office: 1,460 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A system, method and computer program product for determining and identifying a highly accurate description of an entity, including discovering hidden attributes, features, characteristics, behaviors, and opinions of an entity; and identifying the entity through processing, summarizing, abstracting, generalizing, discovering, and inferring information from a plurality of databases including publicly available data, private purchased data, private data provided by others, and derived data from public or private data.

Claims

1. A computer implemented system for determining and identifying a highly accurate description of an entity, the system comprising:

a processor and a memory executing;

a profiling device that combines psychographic and demographic data from a plurality of different sources to generate individual and group DNAs comprising binary values related to the psychographic and demographic data that can be assigned binary values, and individual and group signatures comprising scores in a range from 0 to 100 related to the psychographic and demographic data that can be assigned numerical values ranging from 0 to 100;

a clustering device that combines the generated DNAs and signatures from the profiling device into a plurality of baskets of combinations of related data entries and features, including clustering into 200 baskets each of which is defined by 250,000 related data entries and features; and

a projecting device that projects a data vector representing a new individual or a group onto the baskets from the clustering device by determining a degree to which the data vector belongs to each basket, and generating a fingerprint vector including the likelihood of the data vector falling into each basket.

2. The system of claim 1, wherein the system further comprises an aligning device configured to align online and offline social graphs with the generated fingerprints for optimizing offers and communications at a point of contact on a web sites, a mobile or social application, a call center, and a points-of-sale.

3. The system of claim 1, wherein the system further comprises a combining device configured to combine publicly available data for the entity with private data provided by a user, an individual or an organization.

4. The system of claim 1, wherein the system further comprises a display device configured to abstract, represent, cluster and illustrate data points including an entity interest, feature, and opinion based on soft or hard numbers and the baskets of the demographics and psychographics.

5. The system of claim 1, wherein the system further comprises a profiling device configured to build a profile for the entity based on combination of data standardization, field approximation, field matching, and linking profiles.

6. A method for a computer implemented system for determining and identifying a highly accurate description of an entity, the method comprising:

combining with a profiling device psychographic and demographic data from a plurality of different sources to generate individual and group DNAs comprising binary values related to the psychographic and demographic data that can be assigned binary values, and individual and group signatures comprising scores in a range from 0 to 100 related to the psychographic and demographic data that can be assigned numerical values ranging from 0 to 100;

combining with a clustering device the generated DNAs and signatures from the profiling device into a plurality of baskets of combinations of related data entries and features, including clustering into 200 baskets each of which is defined by 250,000 related data entries and features; and

projecting with a projecting device a data vector representing a new individual or a group onto the baskets from the clustering device by determining a degree to which the data vector belongs to each basket, and generating a fingerprint vector including the likelihood of the data vector falling into each basket.

7. The method of claim 6, further comprising aligning with an aligning device online and offline social graphs with consumer psychographic research data for optimizing offers and communications at a point of contact on a web sites, a mobile or social application, a call center, and a points-of-sale.

8. The method of claim 6, further comprising combining with a combining device publicly available data for the entity with private data provided by a user, an individual or an organization.

9. The method of claim 6, further comprising abstracting, representing, clustering and illustrating data points with a display device as an entity interest, feature, and opinion based on soft or hard numbers and the baskets of the demographics and psychographics.

10. The method of claim 6, further comprising building with a profiling device a profile for the entity based on combination of data standardization, field approximation, field matching, and linking profiles.

11. A computer program product for a computer implemented system for determining and identifying a highly accurate description of an entity, and including one or more computer readable instructions embedded on a non-transitory, tangible computer readable medium and configured to cause one or more computer processors to perform the steps of:

combining with a profiling device psychographic and demographic data from a plurality of different sources to generate individual and group DNAs comprising binary values related to the psychographic and demographic data that can be assigned binary values, and individual and group signatures comprising scores in a range from 0 to 100 related to the psychographic and demographic data that can be assigned numerical values ranging from 0 to 100;

combining with a clustering device the generated DNAs and signatures from the profiling device into a plurality of baskets of combinations of related data entries and features, including clustering into 200 baskets each of which is defined by 250,000 related data entries and features; and

projecting with a projecting device a data vector representing a new individual or a group onto the baskets from the clustering device by determining a degree to which the data vector belongs to each basket, and generating a fingerprint vector including the likelihood of the data vector falling into each basket.

12. The computer program product of claim 11, further comprising further comprising aligning with an aligning device online and offline social graphs with consumer psychographic research data for optimizing offers and communications at a point of contact on a web sites, a mobile or social application, a call center, and a points-of-sale.

13. The computer program product of claim 11, further comprising further comprising combining with a combining device publicly available data for the entity with private data provided by a user, an individual or an organization.

14. The computer program product of claim 11, further comprising abstracting, representing, clustering and illustrating data points with a display device as an entity interest, feature, and opinion based on soft or hard numbers and the baskets of the demographics and psychographics.

15. The computer program product of claim 11, further comprising building with a profiling device a profile for the entity based on combination of data standardization, field approximation, field matching, and linking profiles.