Assigning confidence levels to online profiles

• US 10,043,221 B2
• Filed: 11/02/2015
• Issued: 08/07/2018
• Est. Priority Date: 11/02/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Ganci, Jr., John M., Keen, Martin G., Rakshit, Sarbajit K.
• Primary Examiner(s): NGUYEN, KIM T
• Application Number:
  US14/929,790
• Publication Number:
  US 20170124082A1
• Time in Patent Office: 1,009 Days
• Field of Search: 707706, 707727
• 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

The disclosure is directed to a method for assigning confidence levels to data. A method in accordance with an embodiment includes: analyzing at least one data stream from at least one social media account associated with an entity to generate historical data for the entity; comparing the historical data for the entity to profile data in an entity profile of the entity; determining at least one confidence level based on the comparing; and assigning the at least one confidence level to at least one data item in the profile data.

Claims

1. A method for assigning confidence levels to data, comprising:

analyzing at least one data stream from at least one social media account associated with an entity to generate historical data for the entity, the historical data including a current image of the entity;

comparing the historical data for the entity to profile data in an entity profile of the entity, the profile data in the entity profile including a profile image of the entity;

determining at least one confidence level based on the comparing;

assigning the at least one confidence level to at least one data item in the profile data, and assigning an overall confidence level to the entire entity profile of the entity;

wherein the analyzing further comprises analyzing text, at least one image, and associated metadata in each data stream to determine interests and sentiments of the entity;

wherein the comparing further comprises comparing the current image of the entity in the historical data to the profile image of the entity in the profile data in the entity profile to confirm an appearance of the entity; and

iteratively performing the analyzing, comparing, determining, and assigning to refine the at least one confidence level over time or to assign at least one new confidence level.

2. The method according to claim 1, further comprising granting permission, by the entity, for the at least one data stream from the at least one social media account to be analyzed to generate the historical data.

3. The method according to claim 1, wherein the determining further comprises determining a similarity of the historical data with the profile data in the entity profile of the entity.

4. A matching service, comprising:

a matching system for searching a plurality of entity profiles and for outputting search results including a list of entities;

an analysis engine for analyzing at least one data stream from at least one social media account associated with an entity to generate historical data for the entity, the entity having an entity profile in the plurality of entity profiles, the profile data including a profile image of the entity;

a comparing system for comparing the historical data for the entity to profile data in the entity profile of the entity, the profile data in the entity profile including a profile image of the entity, and determining at least one confidence level based on the comparing,

assigning the at least one confidence level to at least one data item in the profile data, and assigning an overall confidence level to the entire entity profile of the entity;

wherein the analyzing further comprises analyzing text, at least one image, and associated metadata in each data stream to determine interests and sentiments of the entity;

wherein the comparing further comprises comparing the current image of the entity in the historical data to the profile image of the entity in the profile data in the entity profile to confirm an appearance of the entity;

modifying the list of entities based on the at least one assigned confidence level; and

iteratively performing the analyzing, comparing, determining, and assigning to refine the at least one confidence level over time or to assign at least one new confidence level.

5. The matching service according to claim 4, wherein the modifying the list of entities further comprises moving the entity higher or lower in the list of entities based on the at least one assigned confidence level.

6. The matching service according to claim 4, wherein the entity grants permission for the at least one data stream from the at least one social media account to be analyzed by the analysis engine to generate the historical data.

7. A computer program product comprising program code embodied in at least one computer-readable storage medium, which when executed, enables a computer system to implement a method for assigning confidence levels to data, the method comprising:

analyzing at least one data stream from at least one social media account associated with an entity to generate historical data for the entity, the historical data including a current image of the entity;

comparing the historical data for the entity to profile data in an entity profile of the entity, the profile data in the entity profile including a profile image of the entity;

determining at least one confidence level based on the comparing;

assigning the at least one confidence level to at least one data item in the profile data, and assigning an overall confidence level to the entire entity profile of the entity;

wherein the analyzing further comprises analyzing text, at least one image, and associated metadata in each data stream to determine interests and sentiments of the entity;

wherein the comparing further comprises comparing the current image of the entity in the historical data to the profile image of the entity in the profile data in the entity profile to confirm an appearance of the entity;

and

iteratively performing the analyzing, comparing, determining, and assigning to refine the at least one confidence level over time or to assign at least one new confidence level.

8. The computer program product according to claim 7, the method further comprising granting permission, by the entity, for the at least one data stream from the at least one social media account to be analyzed to generate the historical data.