Method and system for processing subpoena documents

1. A method for extracting information from a subpoena document, the method being implemented by at least one processor, the method comprising:

receiving, by the at least one processor, a subpoena document;

extracting, by the at least one processor, raw text included in the subpoena document;

identifying, by the at least one processor based on the extracted raw text, at least one entity that is named in the subpoena document by applying an artificial intelligence (AI) based framework that uses Natural Language Processing (NLP) and machine learning to implement an algorithm for the identifying of the at least one entity;

filtering, by the at least one processor, the identified at least one entity to extract at least one final entity by applying the AI framework to remove noise, wherein the at least one final entity includes at least one of a target entity, law enforcement agency, and crime category;

determining, by the at least one processor based on the extracted raw text, first information that relates to at least one from among a scope period associated with the subpoena document, a law enforcement agency associated with the subpoena document, and an investigative agent associated with the subpoena document by applying the AI framework to implement the algorithm for the determining of the first information;

obtaining, by the at least one processor, second information that relates to the at least one final entity; and

outputting, by the at least one processor, a subset of the determined first information and a subset of the obtained second information.

2. The method of claim 1 , wherein the extracting of the raw text comprises scanning the subpoena document with a device configured to perform an optical character recognition operation.

3. The method of claim 1 , wherein the obtaining of the second information comprises retrieving the second information from a database that includes customer-specific information.

4. The method of claim 3 , wherein the second information includes at least one from among a name of a person, a name of a company, a date of birth, a social security number, a tax identification number, an account number, an address of a location, and an organization associated with the at least one final entity.

5. The method of claim 4 , further comprising matching the at least one final entity with a name retrieved from the database that includes the customer-specific information by using a weighted fuzzy name match algorithm that calculates the Levenshtein distance between the at least one final entity and the name retrieved from the database.

6. The method of claim 1 , further comprising inferring a crime category associated with the subpoena document by comparing a behavior of a crime in the subpoena document with at least one similar behavior provided in at least one of negative media and transactions of other crimes.

7. The method of claim 1 , further comprising obtaining third information that includes at least one from among a transaction history of the at least one final entity, historical investigation information that relates to the at least one final entity, know your customer (KYC) information that relates to the at least one final entity, a suspicious activity report (SAR) that relates to the at least one final entity, and negative media information that relates to the at least one final entity.

8. The method of claim 7 , further comprising generating a report that includes information that is responsive to requests included in the subpoena document based on the obtained second information and the obtained third information.

9. A computing apparatus for extracting information from a subpoena document, the computing apparatus comprising:

a processor;

a memory; and

a communication interface coupled to each of the processor and the memory,

wherein the processor is configured to:

receive, via the communication interface, a subpoena document;

extract raw text included in the subpoena document;

identify, based on the extracted raw text, at least one entity that is named in the subpoena document by applying an artificial intelligence (AI) based framework that uses Natural Language Processing (NLP) and machine learning to implement an algorithm for the identifying of the at least one entity;

filter, by the at least one processor, the identified at least one entity to extract at least one final entity by applying the AI framework to remove noise, wherein the at least one final entity includes at least one of a target entity, law enforcement agency, and crime category;

determine, based on the extracted raw text, first information that relates to at least one from among a scope period associated with the subpoena document, a law enforcement agency associated with the subpoena document, and an investigative agent associated with the subpoena document by applying the AI framework to implement the algorithm for the determining of the first information;

obtain second information that relates to the at least one final entity; and

output a subset of the determined first information and a subset of the obtained second information.

10. The computing apparatus of claim 9 , wherein the processor is further configured to extract the raw text by scanning the subpoena document with a device configured to perform an optical character recognition operation.

11. The computing apparatus of claim 9 , wherein the processor is further configured to retrieve the second information from a database that includes customer-specific information and is stored in the memory.

12. The computing apparatus of claim 11 , wherein the second information includes at least one from among a name of a person, a name of a company, a date of birth, a social security number, a tax identification number, an account number, an address of a location, and an organization associated with the at least one final entity.

13. The computing apparatus of claim 12 , wherein the processor is further configured to match the at least one final entity with a name retrieved from the database that includes the customer-specific information by using a weighted fuzzy name match algorithm that calculates the Levenshtein distance between the at least one final entity and the name retrieved from the database.

14. The computing apparatus of claim 9 , wherein the processor is further configured to infer a crime category associated with the subpoena document by comparing a behavior of a crime in the subpoena document with at least one similar behavior provided in at least one of negative media and transactions of other crimes.

15. The computing apparatus of claim 9 , wherein the processor is further configured to obtain third information that includes at least one from among a transaction history of the at least one final entity, historical investigation information that relates to the at least one final entity, know your customer (KYC) information that relates to the at least one final entity, a suspicious activity report (SAR) that relates to the at least one final entity, and negative media information that relates to the at least one final entity.

16. The computing apparatus of claim 15 , wherein the processor is further configured to generate a report that includes information that is responsive to requests included in the subpoena document based on the obtained second information and the obtained third information.

17. A non-transitory computer readable storage medium storing instructions for extracting information from a subpoena document, the storage medium comprising executable code which, when executed by a processor, causes the processor to:

receive a subpoena document;

extract raw text included in the subpoena document;

identify, based on the extracted raw text, at least one entity that is named in the subpoena document by applying an artificial intelligence (AI) based framework that uses Natural Language Processing (NLP) and machine learning to implement an algorithm for the identifying of the at least one entity;

filter, by the at least one processor, the identified at least one entity to extract at least one final entity by applying the AI framework to remove noise, wherein the at least one final entity includes at least one of a target entity, law enforcement agency, and crime category;

determine, based on the extracted raw text, first information that relates to at least one from among a scope period associated with the subpoena document, a law enforcement agency associated with the subpoena document, and an investigative agent associated with the subpoena document by applying the AI framework to implement the algorithm for the determining of the first information;

obtain second information that relates to the at least one final entity; and

output a subset of the determined first information and a subset of the obtained second information.