Learning an entity's trust model and risk tolerance to calculate a risk score

• US 9,721,296 B1
• Filed: 03/24/2016
• Issued: 08/01/2017
• Est. Priority Date: 03/24/2016
• Status: Active Grant

• Current Assignee: www.TrustScience.com Inc.
• Original Assignee: www.TrustScience.com Inc.
• Inventors: Chrapko, Evan V
• Primary Examiner(s): Hamilton, Lalita M
• Application Number:
  US15/079,952
• Time in Patent Office: 495 Days
• Field of Search: 705 35, 705 38
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 30/018 Certifying business or products
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems and methods are described herein for learning an entity'"'"'s trust model and risk tolerance. An entity'"'"'s trust score may be calculated based on data from a variety of data sources, and this data may be combined according to a set of weights which reflect an entity'"'"'s trust model and risk tolerance. For example, an entity may weight data of a certain type more heavily for certain types of transactions and another type of data more heavily for other transactions. By gathering data about the entity, a system may predict the entity'"'"'s trust model and risk tolerance and adjust the set of weights accordingly for calculating trust scores. Furthermore, by monitoring how entities adjust weights for different transaction types, default weighting profiles may be created that are customized for specific transaction types. As another example, an entity'"'"'s trust score, as reported to a requesting entity, may be adjusted based on that requesting entity'"'"'s own trust model, or how “trusting” the requesting entity is.

Claims

1. A method for adjusting, for a requesting entity, a trust score for a second entity, the method comprising:

determining, using processing circuitry, a baseline trust score for the second entity;

receiving data about the requesting entity from a first remote source, wherein the received data comprises text data about the requesting entity;

retrieving, from a database, a file indicating one or more trusting keywords;

comparing the text data to the one or more trusting keywords to determine whether the text data contains the one or more trusting keywords;

in response to determining that the text data contains the one or more trusting keywords, calculating a trusting adjustment score for the requesting entity based on the received data from the first remote source;

determining an adjusted trust score for the second entity by combining the trusting adjustment score and the baseline trust score for the second entity; and

transmitting to the requesting entity an indication of the adjusted trust score.

2. The method of claim 1 wherein combining the trusting adjustment score and the baseline trust score for the second entity comprises multiplying the baseline trust score for the second entity by the trusting adjustment score.

3. The method of claim 1 wherein combining the trusting adjustment score and the baseline trust score for the second entity comprises combining the baseline trust score for the second entity and the trusting adjustment score according to a weighted sum.

4. The method of claim 3 wherein the weighted sum is based on a user-assigned weight.

5. The method of claim 1 wherein the received data further comprises a user indication of how trusting the user believes the requesting entity to be, wherein the user is associated with a third entity that is different from the requesting entity.

6. The method of claim 1 further comprising:

storing the trusting adjustment score for the requesting entity; and

using the stored trusting adjustment score to determine an adjusted trust score for a third entity by combining the stored trusting adjustment score and a baseline trust score for the third entity.

7. The method of claim 6 further comprising:

receiving second data about the requesting entity from a second remote source; and

updating the stored trusting adjustment score based on the received second data from the second remote source.

8. The method of claim 1 further comprising:

receiving an indication of an activity to be performed together by the requesting entity and the second entity; and

updating the trusting adjustment score based on the indication of the activity.

9. The method of claim 1 wherein the second entity is associated with a second node in a network community, and a fourth entity is associated with a first node in a network community, and wherein determining a baseline trust score for the second entity comprises:

identifying paths to the second node from the first node within the network community; and

determining the baseline trust score for the second entity based on the identified paths.

10. The method of claim 9 wherein the identified paths each comprise one or more links, wherein each link is assigned a user connectivity value, and wherein determining the baseline trust score for the second entity based on the identified paths comprises:

combining the user connectivity values to determine the baseline trust score for the second entity based on the identified paths.

11. The method of claim 1 wherein the received data further comprises at least one of video data, audio data, pictorial data, numerical data, or user input data.

12. A system for adjusting, for a requesting entity, a trust score for a second entity, the system comprising:

processing circuitry configured to;

determine a baseline trust score for the second entity;

receive data about the requesting entity from a first remote source, wherein the received data comprises text data about the requesting entity;

retrieving, from a database, a file indicating one or more trusting keywords;

comparing the text data to the one or more trusting keywords to determine whether the text data contains the one or more trusting keywords;

in response to determining that the text data contains the one or more trusting keywords, calculate a trusting adjustment score for the requesting entity based on the received data from the first remote source;

determine an adjusted trust score for the second entity by combining the trusting adjustment score and the baseline trust score for the second entity; and

transmit to the requesting entity an indication of the adjusted trust score.

13. The system of claim 12 wherein the processing circuitry is configured to combine the trusting adjustment score and the baseline trust score for the second entity by multiplying the baseline trust score for the second entity by the trusting adjustment score.

14. The system of claim 12 wherein the processing circuitry is configured to combine the trusting adjustment score and the baseline trust score for the second entity by combining the baseline trust score for the second entity and the trusting adjustment score according to a weighted sum.

15. The system of claim 14 wherein the weighted sum is based on a user-assigned weight.

16. The system of claim 12 wherein the received data further comprises a user indication of how trusting the user believes the requesting entity to be, wherein the user is associated with a third entity that is different from the requesting entity.

17. The system of claim 12, the processing circuitry further configured to:

store the trusting adjustment score for the requesting entity; and

use the stored trusting adjustment score to determine an adjusted trust score for a third entity by combining the stored trusting adjustment score and a baseline trust score for the third entity.

18. The system of claim 17, the processing circuitry further configured to:

receive second data about the requesting entity from a second remote source; and

update the stored trusting adjustment score based on the received second data from the second remote source.

19. The system of claim 12, the processing circuitry further configured to:

receive an indication of an activity to be performed together by the requesting entity and the second entity; and

update the trusting adjustment score based on the indication of the activity.

20. The system of claim 12 wherein the second entity is associated with a second node in a network community, and a fourth entity is associated with a first node in a network community, and wherein the processing circuitry is configured to determine a baseline trust score for the second entity by:

identifying paths to the second node from the first node within the network community; and

determining the baseline trust score for the second entity based on the identified paths.

21. The system of claim 20 wherein the identified paths each comprise one or more links, wherein each link is assigned a user connectivity value, and wherein the processing circuitry is configured to determine the baseline trust score for the second entity based on the identified paths by:

combining the user connectivity values to determine the baseline trust score for the second entity based on the identified paths.

22. The system of claim 12 wherein the received data further comprises at least one of video data, audio data, pictorial data, numerical data, or user input data.