Determining trustworthiness and compatibility of a person

• US 10,169,708 B2
• Filed: 12/28/2015
• Issued: 01/01/2019
• Est. Priority Date: 09/16/2014
• Status: Active Grant

• Current Assignee: AirBNB Incorporated
• Original Assignee: AirBNB Incorporated
• Inventors: Baveja, Sarabjit Singh, Sarma, Anish Das, Dalvi, Nilesh
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US14/980,343
• Publication Number:
  US 20160110648A1
• Time in Patent Office: 1,100 Days
• Field of Search: 706 14
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/048 Fuzzy inferencing

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying documents related to a person, deriving behavior and personality trait metrics from analyzing the documents for information relevant to assessing behavior and personality of the person, and determine a trustworthiness score or compatibility score of the person based on the behavior and personality trait metrics using a scoring system.

Claims

1. A method comprising:

obtaining, using one or more computer processors, identification attributes of a person;

identifying, using the one or more computer processors, identity information within each document of a plurality of documents;

determining, using the one or more computer processors, the uniqueness of the identity information identified within each document of the plurality of documents;

calculating, using the one or more computer processors, an identity score for each document of the plurality of documents based on matching one or more identification attributes of the person to the identity information in each document of the plurality of documents and the uniqueness of the identity information;

obtaining, using the one or more computer processors, a request for a trustworthiness score of the person from a requestor device;

analyzing, using the one or more computer processors, each of the plurality of documents to identify content attributes that occur in a dictionary for behavior or personality traits;

calculating, using the one or more computer processors, an initial score for each behavior and personality trait related to the identified content attributes using the identity score for each document;

calculating, using the one or more computer processors, trait metrics for each behavior or personality trait by combining initial scores for each behavior or personality trait;

providing, using the one or more computer processors, the trait metrics as input to a rule based scoring and machine learning system

obtaining, from the rule based scoring and machine learning system, a trustworthiness score of the person output from the rule based scoring and machine learning system;

providing, using the one or more computer processors, the trustworthiness score of the person to the requestor device;

receiving an indication that a second person trusts the person;

creating a relationship between the second person and the person; and

adjusting the trustworthiness score of the person based on, at least, a trustworthiness score of the second person.

2. The method of claim 1, wherein calculating an initial score for each behavior and personality trait related to the identified content attributes using the identity score for each document is further based on weights associated with the identified content attributes.

3. The method of claim 2, wherein analyzing each of the plurality of documents to identify content attributes comprises identifying one or more portions of each document that contain text authored by the person or that provide information about the person.

4. The method of claim 1, further comprising:

determining that the trustworthiness score is not accurate; and

retraining the rule based scoring and machine learning system to correct for the inaccuracy using the trait metrics.

5. The method of claim 1, wherein a behavior or personality trait includes at least one of a group comprising:

badness, anti-social tendencies, goodness, conscientiousness, openness, extraversion, agreeableness, neuroticism, narcissism, Machiavellianism, and psychopathy.

6. The method of claim 1, wherein a behavior or personality trait includes at least one of a group comprising:

creating a false or misleading online profile or providing false or misleading information to a service provider, involvement with drugs or alcohol, involvement with hate websites or organizations, involvement in sex work, involvement in a crime, involvement in civil litigation, being a known fraudster or scammer, involvement in pornography, and authoring online content with negative language.

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

determining whether the identification attributes are authentic;

deriving the one or more trait metrics based on determining the identification attributes are authentic; and

deriving additional identification attributes and iteratively deriving additional trait metrics based on the additional identification attributes.

8. The method of claim 7, wherein determining whether the identification attributes are authentic comprises:

determining if the identity information of the person contained in one or more documents of the plurality of documents is consistent with the identification attributes.

9. The method of claim 1, further comprising:

formulating a plurality of queries using the identification attributes, the queries configured to maximize retrieval of relevant documents and information;

submitting the queries to one or more remote systems; and

receiving search results comprising the plurality of documents, from the one or more remote systems in response to submitting the queries.

10. The method of claim 1, wherein identifying content attributes that occur in a dictionary for behavior or personality traits is further based on the identity score of the document.

11. The method of claim 1, wherein calculating the initial score for each behavior and personality trait is further based on a recency of each document.

12. A computing system comprising:

a memory that stores instructions; and

one or more processors configured by the instructions to perform operations comprising;

obtaining identification attributes of a person;

identifying identity information within each document of a plurality of documents;

determining the uniqueness of the identity information identified within each document of the plurality of documents;

calculating an identity score for each document of the plurality of documents based on matching one or more identification attributes of the person to the identity information in each document of the plurality of documents and the uniqueness of the identity information;

obtaining a request for a trustworthiness score of the person from a requestor device;

analyzing each of the plurality of documents to identify content attributes that occur in a dictionary for behavior or personality traits;

calculating an initial score for each behavior and personality trait related to the identified content attributes using the identity score for each document;

calculating trait metrics for each behavior or personality trait by combining initial scores for each behavior or personality trait;

providing the trait metrics as input to a rule based scoring and machine learning system;

obtaining, from the rule based scoring and machine learning system, a trustworthiness score of the person output from the rule based scoring and machine learning system;

providing the trustworthiness score of the person to the requestor device;

receiving an indication that a second person trusts the person;

creating a relationship between the second person and the person; and

adjusting the trustworthiness score of the person based on, at least, a trustworthiness score of the second person.

13. A non-transitory computer-readable medium comprising instruction stored thereon that are executable by at least one processor to cause a computing device to perform operations comprising:

obtaining identification attributes of a person;

identifying identity information within each document of a plurality of documents;

determining the uniqueness of the identity information identified within each document of the plurality of documents;

calculating an identity score for each document of the plurality of documents based on matching one or more identification attributes of the person to the identity information in each document of the plurality of documents and the uniqueness of the identity information;

obtaining a request for a trustworthiness score of the person from a requestor device;

analyzing each of the plurality of documents to identify content attributes that occur in a dictionary for behavior or personality traits;

calculating an initial score for each behavior and personality trait related to the identified content attributes using the identity score for each document;

calculating trait metrics for each behavior or personality trait by combining initial scores for each behavior or personality trait;

providing the trait metrics as input to a rule based scoring and machine learning system obtaining, from the rule based scoring and machine learning system, a trustworthiness score of the person output from the rule based scoring and machine learning system;

providing the trustworthiness score of the person to the requestor device;

receiving an indication that a second person trusts the person;

creating a relationship between the second person and the person; and

adjusting the trustworthiness score of the person based on, at least, a trustworthiness score of the second person.