System and method for analyzing and modeling content

Abstract

Described herein are systems and methods for aggregating, parsing, and annotating regulatory context for use in resolving transactional inquiries. In one embodiment, a method comprises: aggregating documents from a plurality of data sources and storing the aggregated documents in a document database; selecting a first document from the document database; extracting regulatory content from the first document; parsing the regulatory content into a structured data object; identifying a substantively-relevant portion of the regulatory content in the structured data object; generating an annotation associated with the substantively-relevant portion; storing the generated annotation in an annotation database; and generating a domain-specific data structure for resolving transactional inquiries based on the annotation database.

What is claimed is: 
     
         1 . A method for resolving legal or regulatory inquiries and generating audit records, the method comprising:
 a) aggregating, by a processing device, documents from a plurality of data sources and storing the aggregated documents in a document database, wherein each document comprises legal and regulatory content for a legal and regulatory domain;   b) selecting, by the processing device, a first document from the document database, the first document expressed in a first format;   c) converting, by the processing device, the first document into a structured data object, the structured data object expressed in a structured data format independent of the first format of the first document;   d) generating, by the processing device, a plurality of annotations associated with the structured data object, each annotation associated with a data structure representing logic within the legal and regulatory content, wherein the plurality of annotations form a comprehensive data structure representing the entire logic within the legal and regulatory content;   e) storing, by the processing device, the generated annotations in an annotation database comprising annotations associated with the documents in the document database;   f) transforming, by the processing device, the structured data object into a domain-specific data structure, the domain-specific data structure comprising a compiled executable logical model for decision making to resolve transactional inquiries in the legal and regulatory domain, wherein the domain-specific data structure is derived at least partially from one or more logical relationships between the generated annotations and one or more annotations of the annotation database;   g) receiving, by the processing device, a request to resolve an inquiry in the legal and regulatory domain pertaining to a proposed transaction, the request comprising a plurality of transaction-specific parameters;   h) executing, by the processing device, the complied executable logical model, using the plurality of transaction-specific parameters as inputs, to resolve the inquiry; and   i) generating, by the processing device, an audit record comprising a visualization of the executable logical model, how each decision in the executable logical model was made, and the resolution of the inquiry.   
     
     
         2 . The method of  claim 1 , wherein the request to resolve an inquiry is not search request and the proposed transaction is not a search. 
     
     
         3 . The method of  claim 2 , wherein the proposed transaction comprises a financial transaction. 
     
     
         4 . The method of  claim 1 , wherein the entire first document is converted into a structured data object. 
     
     
         5 . The method of  claim 1 , wherein the plurality of annotations are non-semantic. 
     
     
         6 . The method of  claim 5 , wherein the plurality of annotations are not generated as mark-up and are not generated as tags. 
     
     
         7 . The method of  claim 1 , wherein one or more of the annotations comprises a taxonomy of a rule, a scope to which the rule applies, and a classification of the annotation. 
     
     
         8 . The method of  claim 7 , wherein the one or more of the annotations further comprises one or more of a definition of a legislative term, a definition of a data element, a cross-reference to another annotation, an expression of a relationship between entities, or an expression of a relationship between data elements. 
     
     
         9 . The method of  claim 1 , wherein generating the plurality of annotations comprises extracting a rule-specific indicator from the legal and regulatory content. 
     
     
         10 . The method of  claim 9 , wherein the processing device utilizes a natural language processing algorithm to identify the rule-specific indicator within the legal and regulatory content. 
     
     
         11 . The method of  claim 1 , wherein the request to resolve a transactional inquiry in the legal and regulatory domain comprises a request to determine obligations of one or more parties associated with the proposed transaction, and wherein the resolution of the inquiry comprises an indication of the obligations of the one or more parties. 
     
     
         12 . The method of  claim 1 , further comprising determining, by the processing device, that the first document corresponds to an updated version of a previously-stored document in the document database, wherein the updated version corresponds to legal and regulatory content not present in the previously stored document. 
     
     
         13 . The method of  claim 1 , wherein aggregating the documents from the plurality of data sources comprises: identifying, by the processing device, one or more documents available from the plurality of data sources that have associated hash values that differ from hash values associated with any of the documents previously stored in the document database; and retrieving, by the processing device, the one or more documents and storing the one or more documents in the document database. 
     
     
         14 . The method of  claim 1 , further comprising selecting, by the processing device, the plurality of data sources from which to aggregate the documents based on a target regulation category. 
     
     
         15 . The method of  claim 1 , further comprising periodically reaggregating, by the processing device, the documents from the plurality of data sources and calculating a hash value for each document to detect changes to the documents. 
     
     
         16 . The method of  claim 1 , wherein the legal and regulatory content comprises one or more of: a law, a regulation, a rule, a legal text, a policy text, and a legal guidance. 
     
     
         17 . The method of  claim 1 , wherein the visualization comprises a logic flow chart. 
     
     
         18 . A system configured for resolving legal or regulatory inquiries and generating audit records, the system comprising:
 a) a data store for maintaining a document database and an annotation database; and   b) one or more processing devices communicatively coupled to the data store, wherein the one or more processing devices are configured to:
 i) aggregate documents from a plurality of data sources and store the aggregated documents in the document database, wherein each document comprises legal and regulatory content for a legal and regulatory domain; 
 ii) select a first document from the document database, the first document expressed in a first format; 
 iii) convert the first document into a structured data object, the structured data object expressed in a structured data format independent of the first format of the first document; 
 iv) generate a plurality of annotations associated with the structured data object, each annotation a data structure representing logic within the legal and regulatory content, wherein the plurality of annotations form a comprehensive data structure representing the entire logic within the legal and regulatory content; 
 v) store the generated annotation in the annotation database comprising annotations associated with the documents in the document database; 
 vi) transform the structured data object into a domain-specific data structure, the domain-specific data structure comprising a compiled executable logical model for decision making to resolve transactional inquiries in the legal and regulatory domain, wherein the domain-specific data structure is derived at least partially from one or more logical relationships between the generated annotations and one or more annotations of the annotation database; 
 vii) receive a request to resolve an inquiry in the legal and regulatory domain pertaining to a proposed transaction, the request comprising a plurality of transaction-specific parameters; 
 viii) execute the complied executable logical model, using the plurality of transaction-specific parameters as inputs, to resolve the inquiry; and 
 ix) generate an audit record comprising a visualization of the executable logical model, how each decision in the executable logical model was made, and the resolution of the inquiry. 
   
     
     
         19 . The system of  claim 18 , wherein the request to resolve an inquiry is not search request and the proposed transaction is not a search. 
     
     
         20 . The system of  claim 19 , wherein the proposed transaction comprises a financial transaction. 
     
     
         21 . The system of  claim 18 , wherein the entire first document is converted into a structured data object. 
     
     
         22 . The system of  claim 18 , wherein the plurality of annotations are non-semantic. 
     
     
         23 . The system of  claim 22 , wherein the plurality of annotations are not generated as mark-up and are not generated as tags. 
     
     
         24 . The system of  claim 18 , wherein one or more of the annotations comprises a taxonomy of a rule, a scope to which the rule applies, and a classification of the annotation. 
     
     
         25 . The system of  claim 24 , wherein the one or more of the annotations further comprises one or more of a definition of a legislative term, a definition of a data element, a cross-reference to another annotation, an expression of a relationship between entities, or an expression of a relationship between data elements. 
     
     
         26 . The system of  claim 18 , wherein generating the plurality of annotations comprises extracting a rule-specific indicator from the legal and regulatory content. 
     
     
         27 . The system of  claim 26 , wherein the one or more processing devices utilize a natural language processing algorithm to identify the rule-specific indicator within the legal and regulatory content. 
     
     
         28 . The system of  claim 18 , wherein the request to resolve a transactional inquiry in the legal and regulatory domain comprises a request to determine obligations of one or more parties associated with the proposed transaction, and wherein the resolution of the inquiry comprises an indication of the obligations of the one or more parties. 
     
     
         29 . The system of  claim 18 , wherein the one or more processing devices are further configured to determine that the first document corresponds to an updated version of a previously-stored document in the document database, wherein the updated version corresponds to legal and regulatory content not present in the previously stored document. 
     
     
         30 . The system of  claim 18 , wherein aggregating the documents from the plurality of data sources comprises: identifying one or more documents available from the plurality of data sources that have associated hash values that differ from hash values associated with any of the documents previously stored in the document database; and retrieving the one or more documents and storing the one or more documents in the document database. 
     
     
         31 . The system of  claim 18 , wherein the one or more processing devices are further configured to select the plurality of data sources from which to aggregate the documents based on a target regulation category. 
     
     
         32 . The system of  claim 18 , wherein the one or more processing devices are further configured to periodically reaggregate the documents from the plurality of data sources and calculating a hash value for each document to detect changes to the documents. 
     
     
         33 . The system of  claim 18 , wherein the legal and regulatory content comprises one or more of: a law, a regulation, a rule, a legal text, a policy text, and a legal guidance. 
     
     
         34 . The system of  claim 18 , wherein the visualization comprises a logic flow chart. 
     
     
         35 . A non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processing device, cause the processing device to resolve legal or regulatory inquiries and generate audit records by performing at least:
 a) aggregate documents from a plurality of data sources and store the aggregated documents in a document database, wherein each document comprises legal and regulatory content for a legal and regulatory domain;   b) select a first document from the document database, the first document expressed in a first format;   c) convert the first document into a structured data object, the structured data object expressed in a structured data format independent of the first format of the first document;   d) generate a plurality of annotations associated with the structured data object, each annotation a data structure representing logic within the legal and regulatory content, wherein the plurality of annotations form a comprehensive data structure representing the entire logic within the legal and regulatory content;   e) store the generated annotation in an annotation database comprising annotations associated with the documents in the document database;   f) transform the structured data object into a domain-specific data structure, the domain-specific data structure comprising a compiled executable logical model for decision making to resolve transactional inquiries in the legal and regulatory domain, wherein the domain-specific data structure is derived at least partially from one or more logical relationships between the generated annotation and one or more annotations of the annotation database;   g) receive a request to resolve an inquiry in the legal and regulatory domain pertaining to a proposed transaction, the request comprising a plurality of transaction-specific parameters;   h) execute the complied executable logical model, using the plurality of transaction-specific parameters as inputs, to resolve the inquiry; and   i) generate an audit record comprising a visualization of the executable logical model, how each decision in the executable logical model was made, and the resolution of the inquiry.   
     
     
         36 . The non-transitory computer-readable storage medium of  claim 35 , wherein the request to resolve an inquiry is not search request and the proposed transaction is not a search. 
     
     
         37 . The non-transitory computer-readable storage medium of  claim 36 , wherein the proposed transaction comprises a financial transaction. 
     
     
         38 . The non-transitory computer-readable storage medium of  claim 35 , wherein the entire first document is converted into a structured data object. 
     
     
         39 . The non-transitory computer-readable storage medium of  claim 35 , wherein the plurality of annotations are non-semantic. 
     
     
         40 . The non-transitory computer-readable storage medium of  claim 38 , wherein the plurality of annotations are not generated as mark-up and are not generated as tags. 
     
     
         41 . The non-transitory computer-readable storage medium of  claim 35 , wherein one or more of the annotations comprises a taxonomy of a rule, a scope to which the rule applies, and a classification of the annotation. 
     
     
         42 . The non-transitory computer-readable storage medium of  claim 41 , wherein the one or more of the annotations further comprises one or more of a definition of a legislative term, a definition of a data element, a cross-reference to another annotation, an expression of a relationship between entities, or an expression of a relationship between data elements. 
     
     
         43 . The non-transitory computer-readable storage medium of  claim 35 , wherein generating the plurality of annotations comprises extracting a rule-specific indicator from the legal and regulatory content. 
     
     
         44 . The non-transitory computer-readable storage medium of  claim 43 , wherein the processing device utilizes a natural language processing algorithm to identify the rule-specific indicator within the legal and regulatory content. 
     
     
         45 . The non-transitory computer-readable storage medium of  claim 35 , wherein the request to resolve a transactional inquiry in the legal and regulatory domain comprises a request to determine obligations of one or more parties associated with the proposed transaction, and wherein the resolution of the inquiry comprises an indication of the obligations of the one or more parties. 
     
     
         46 . The non-transitory computer-readable storage medium of  claim 35 , wherein the instructions, when executed by the processing device, further cause the processing device to determine that the first document corresponds to an updated version of a previously-stored document in the document database, wherein the updated version corresponds to legal and regulatory content not present in the previously stored document. 
     
     
         47 . The non-transitory computer-readable storage medium of  claim 35 , wherein aggregating the documents from the plurality of data sources comprises: identifying one or more documents available from the plurality of data sources that have associated hash values that differ from hash values associated with any of the documents previously stored in the document database; and retrieving the one or more documents and storing the one or more documents in the document database. 
     
     
         48 . The non-transitory computer-readable storage medium of  claim 35 , wherein the instructions, when executed by the processing device, further cause the processing device to select the plurality of data sources from which to aggregate the documents based on a target regulation category. 
     
     
         49 . The non-transitory computer-readable storage medium of  claim 35 , wherein the instructions, when executed by the processing device, further cause the processing device to periodically reaggregate the documents from the plurality of data sources and calculating a hash value for each document to detect changes to the documents. 
     
     
         50 . The non-transitory computer-readable storage medium of  claim 35 , wherein the legal and regulatory content comprises one or more of: a law, a regulation, a rule, a legal text, a policy text, and a legal guidance. 
     
     
         51 . The non-transitory computer-readable storage medium of  claim 35 , wherein the visualization comprises a logic flow chart.