Identifying and changing personal information

• US 8,027,975 B2
• Filed: 01/29/2008
• Issued: 09/27/2011
• Est. Priority Date: 01/31/2007
• Status: Active Grant

• Current Assignee: Reputation.com, Inc.
• Original Assignee: Reputation.com, Inc.
• Inventors: Thompson, David, Aubry, James, Fertik, Michael, Gabriel, Raefer, Kelley, Brian
• Primary Examiner(s): Vital; Pierre
• Assistant Examiner(s): OBISESAN, AUGUSTINE KUNLE
• Application Number:
  US12/021,978
• Publication Number:
  US 20080183700A1
• Time in Patent Office: 1,337 Days
• Field of Search: None
• US Class Current: 707/731
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0263 based upon Internet or website rating

Abstract

Systems, apparatuses, and methods for analyzing information about a user are presented which include obtaining at least one search result based on at least one search terms describing the user; presenting the at least one search result to the user; receiving an indication from the user of the desirability of a search result; and performing an action based on the desirability of the search result. Systems, apparatuses, and methods are also presented for determining a reputation score representing the reputation of a user which include collecting search results from data source, determining an effect on the reputation of the user of the search results from the data source, and calculating a reputation score for the user based on the determined effect on the reputation of the user from the search results from the data source.

Claims

1. A method for analyzing information about a user comprising the steps of:

obtaining, at a computer, at least one search result from a data source via a search engine based on at least one search term identifying the user;

identifying a contextual token or a mood-indicating token describing the user within a set of tokens surrounding a relevancy-indicating token in the at least one search result;

ascertaining an effect of the at least one search result on a reputation of the user based on whether the identified contextual or mood-indicating token positively or negatively affects the reputation of the user;

determining whether the at least one search result includes undesirable information negatively affecting the reputation of the user based on the ascertained effect of the at least one search result on the reputation of the user;

flagging the at least one search result if it is determined that the at least one search result includes undesirable information;

communicating with the data source to determine whether the undesirable information included in the flagged search result can be changed at the data source; and

if it is determined that the undesirable information can be changed at the data source, causing a change of the undesirable information at the data source.

2. The method of claim 1, further comprising the steps of:

determining an additional search term based on the at least one search result; and

using the additional search term in the obtaining step.

3. The method of claim 2, wherein determining the additional search term is performed automatically.

4. The method of claim 2, wherein determining the additional search term is performed by a human agent or the user.

5. The method of claim 1, wherein causing the data source to change the undesirable information comprises:

causing the data source to remove the undesirable information.

6. The method of claim 1, wherein the flagged search result contains data about the user that is incorrect.

7. The method of claim 1, wherein the flagged search result contains data that is damaging to a reputation of the user.

8. The method of claim 1, further comprising:

determining the relevancy of the at least one search result.

9. The method of claim 8, wherein determining the relevancy of the at least one search result comprises determining whether the at least one search result contains information associated with the user.

10. The method of claim 9, further comprising:

ignoring the at least one search result if the at least one search result does not contain information associated with the user.

11. The method of claim 9, further comprising:

determining an exclusionary search term when the at least one search result does not contain information associated with the user, wherein the exclusionary search term excludes a search result that does not contain information associated with the user; and

obtaining at least one search result for the user using the exclusionary search term.

12. The method of claim 1, further comprising:

obtaining at least one additional search result;

generating a search ranking system based on the at least one search result or the at least one additional search result; and

sorting the search results based on a search ranking system.

13. The method of claim 12, wherein a Bayesian network is used to generate the search ranking system.

14. The method of claim 13, wherein the Bayesian network utilizes a corpus of irrelevance-indicating tokens and a corpus of relevance-indicating tokens.

15. The method of claim 1, further comprising:

determining a signature for the at least one search result;

comparing the signature to a previously-obtained signature for a previously-obtained search result; and

determining the relevancy of the at least one search result when the signature and the previously-obtained signature are different.

16. The method of claim 1, wherein the obtaining at least one search result step is performed periodically.

17. The method of claim 16, wherein periodicity of performing the obtaining step is based on a user characteristic.

18. The method of claim 16, wherein periodicity of performing the obtaining step is determined based on a data source characteristic.

19. The method of claim 1, further comprising:

presenting the at least one search result to a human agent;

obtaining an indication of a categorization of the at least one search result from the human agent; and

automatically categorizing the at least one search result based on the indication from the human agent.

20. The method of claim 1, wherein obtaining the at least one search result comprises receiving at least one search result from a human agent, and the method further comprising:

obtaining an indication of a categorization of the at least one search result from the human agent; and

automatically categorizing the at least one search result based on the indication from the human agent.

21. The method of claim 1, further comprising:

receiving an indication of the relevancy of the at least one search result from the user or a human agent.

22. The method of claim 1, wherein obtaining the at least one search result comprises receiving at least one search result automatically, and the method further comprising:

obtaining an indication of a categorization of the at least one search result automatically; and

automatically categorizing the at least one search result based on the indication.

23. An apparatus for analyzing information about a user comprising:

at least one computing processor configured to;

obtain at least one search result from a data source via a search engine based on at least one search term identifying the user;

identify a contextual token or a mood-indicating token describing the user within a set of tokens surrounding a relevancy-indicating token in the at least one search result;

ascertain an effect of the at least one search result on a reputation of the user based on whether the identified contextual or mood-indicating token positively or negatively affects the reputation of the user;

determine whether the at least one search result includes undesirable information negatively affecting the reputation of the user based on the ascertained effect of the at least one search result on the reputation of the user;

flag the at least one search result if it is determined that the at least one search result includes undesirable information;

communicate with the data source to determine whether the undesirable information included in the flagged search result can be changed at the data source; and

if it is determined that the undesirable information can be changed at the data source, cause a change of the undesirable information at the data source.

24. A non-transitory computer readable medium storing instructions that, when executed, cause a computer to perform a method for analyzing information about a user, the method comprising:

obtaining at least one search result from a data source via a search engine based on at least one search term identifying the user;

identifying a contextual token or a mood-indicating token describing the user within a set of tokens surrounding a relevancy-indicating token in the at least one search result;

ascertaining an effect of the at least one search result on a reputation of the user based on whether the identified contextual or mood-indicating token positively or negatively affects the reputation of the user;

determining whether the at least one search result includes undesirable information negatively affecting the reputation of the user based on the ascertained effect of the at least one search result on the reputation of the user;

flagging the at least one search result if it is determined that the at least one search result includes undesirable information;

communicating with the data source to determine whether the undesirable information included in the flagged search result can be changed at the data source; and

if it is determined that the undesirable information can be changed at the data source, causing a change of the undesirable information at the data source.