Granted Patent B2

US 7,519,587 · App. 10/941,786 · Granted Apr 14, 2009

Assignees: Goldman Sachs & Co.; Regulatory DataCorp International, LLC

Abstract

Claims (50)

1. A method for determining the relevancy of information contained in an input data packet, the method comprising:

comparing said information in said input data packet with a set of relevant keywords to determine that said input data packet contains one or more of said relevant keywords;

tagging portions of said input data packet to identify said one or more relevant keywords, one or more relationship terms, and one or more action terms contained in said information within the input data packet;

analyzing said tagged data packet based on the presence and usage of said one or more relevant keywords, one or more relationship terms, and one or more action terms; and

identifying said information as relevant if the analysis indicates said one or more relevant keywords, one or more relationship terms, and one or more action terms;

generating an output data packet including said tagged portions,

wherein said analyzing said tagged data packet includes identifying a relationship between a name and an organization.

2. The method of claim 1 , wherein said identifying said information as relevant further comprises:

generating a relevancy score for said information in said input data packet and comparing said relevancy score to a threshold.

3. The method of claim 1 , wherein said one or more relationship terms is at least one of a relationship between an event, a person, a place, or an organization.

4. The method of claim 1 wherein each of said one or more action and relationship terms are terms associated with one of said relevant keywords selected as indicating a relevancy of said information.

5. The method of claim 1 , wherein said input data packet is received from a data gathering device gathering information from a plurality of data sources.

6. The method of claim 1 , further comprising:

transmitting said output data packet to a database system for storage of said output data packet.

7. The method of claim 1 , wherein said analyzing said tagged data packet includes identifying a relationship between an organization and an event.

8. The method of claim 1 , wherein said analyzing said tagged data packet includes identifying a verb associated with said keyword.

9. The method of claim 1 , wherein said identifying said information as relevant further comprises:

referring said data packet to an operator for manual review.

10. The method of claim 1 , further comprising:

determining whether said output data packet is redundant with information previously stored in a database system.

11. The method of claim 1 , wherein said information is associated with political risk, or environmental risk.

12. The method of claim 1 wherein said information is associated with regulatory risk or legal risk.

13. A system for determining the relevancy of information contained in an input data packet, the system comprising:

a processor;

a communication device, coupled to receive the input data packet from a source; and

a storage device in communication with said processor and storing instructions adapted to be executed by said processor to:

identify at least one portion of the information in said input data packet as having a relevancy with respect to risk;

filter the information based at least in part on the identified at least one portion;

tag the identified at least one portion to identify one or more relevant keywords, one or more relationship terms, and one or more action terms contained in the identified portion within the input data packet;

analyze the identified at least one portion based on a presence and usage of the one or more relevant keywords, the one or more relationship terms, and the one or more action terms;

identify said information as relevant if the analysis indicates said one or more relevant keywords, one or more relationship terms, and one or more action terms; and

generate an output data packet including said tagged portions,

wherein said analyzing said tagged data packet includes identifying a relationship between a name and an organization.

14. The system of claim 13 , wherein the stored instructions are further adapted to be executed by said processor to:

determine a relevancy of the information with respect to risk, the determination based at least in part on the identified at least one portion; and

filter the information based at least in part on the determined relevancy of the information with respect to risk.

15. The system of claim 13 , wherein the information is associated with regulatory risk, political risk, or environmental risk.

16. A computer-readable medium having computer executable software code stored therein, the code comprising:

code to receive information in at least one standardized format;

code to identify at least one portion of the information having a relevancy with respect to risk;

code to filter the information based at least in part on the identified at least one portion;

code to tag the identified at least one portion to identify one or more relevant keywords, one or more relationship terms, and one or more action terms contained in the identified portion within the data packet;

code to analyze the identified at least one portion based on a presence and usage of the one or more relevant keywords, the one or more relationship terms, and the one or more action terms;

code to identify said information as relevant if the analysis indicates said one or more relevant keywords, one or more relationship terms, and one or more action terms; and

code to generate an output data packet including said tagged portions,

wherein said code to analyze said tagged data packet includes code to identify a relationship between a name and an organization.

17. The computer-readable medium of claim 16 , wherein the code further comprises;

code to determine a relevancy of the information with respect to risk, the determination based at least in part on the identified at least one portion; and

code to filter the information based at least in part on the determined relevancy of the information with respect to risk.

18. The medium of claim 16 , wherein the information is associated with regulatory risk, political risk, or environmental risk.

Assignments (11)

Continuity (2)