System and method for document extraction and synthesis

Abstract

Systems and methods for document extraction and synthesis. Specifically, a system and method for extracting portions of a document to be changed and automatedly synthesizing the changes to the extracted portion of the document to conform to the language and structure required for the final document. A user can modify an existing set of laws and automatedly transform the changes into a final document that complies with specified language and format requirements. For example, a bill drafter can select a provision of existing law to modify and the system will transform the changes to the existing law into a bill to be presented before the lawmaking body that complies with all of the precise language and formatting requirements of bills to be presented. Systems and methods may be provided in a stand-alone system or incorporated into document drafting systems capable of supporting the functionality of the present application.

What is claimed is: 
     
         1 . A method of bill synthesis, the method comprising:
 receiving at least one provision of law to be included in a snapshot document, wherein the snapshot document includes a set of original text for each provision of law to be changed;   determining a formalized reference for each provision of law included in the snapshot document, wherein the formalized reference is an original location for the provision of law;   receiving at least one in-line change to the set of original text for each provision of law, wherein the at least one change includes an insertion of text or a deletion of text into the text of the provision;   assigning each in-line change to at least one change set, wherein each change set represents a different legal effect, further wherein each change set groups each in-line change to the same legal effect;   receiving change set metadata associated with each change set, wherein the change set metadata includes a set of dependencies;   creating an updated snapshot document including the set of original text for each provision of law, the formalized reference for each provision of law, the in-line changes, the change sets, and the change set metadata for each change set;   automatedly extracting and enumerating from the updated snapshot document the change sets;   automatedly extracting from the updated snapshot document the change set metadata for each change set;   automatedly extracting and enumerating all changes made to the set of original text for each change set, wherein the extraction includes a reference to an exact location in the set of original text where the change occurs;   clustering adjacent changes for each change set together to create an enumerated list of changes for each change set;   constructing an internal data structure for each extracted change set, wherein the data structure includes a hierarchical representation of the changes to be made for each change set, the change set metadata, and the formalized reference for each provision included in the change set;   creating an XML changes document for each data structure constructed from the updated snapshot document;   analyzing the XML changes document based on a template library to determine at least one template model to synthesize a bill representation;   mapping the XML changes document to the at least one template model to create jurisdiction specific language for the bill representation using the changes from each change set in the data structures of the XML changes document;   generating the bill representation based on the mapping, wherein the bill representation provides the in-context changes from the updated snapshot document, the change set metadata from the updated snapshot document, and the formalized reference for each provision in a formalized manner and a manner required by a particular jurisdiction;   displaying to a user the generated bill representation; and   presenting the generated bill representation to a legislature from the particular jurisdiction.   
     
     
         2 . The method of  claim 1 , wherein the change set metadata includes a description of the legal effect and a set of effectivity rules for the change set. 
     
     
         3 . The method of  claim 1 , the method further comprising storing the snapshot document and storing the updated snapshot document. 
     
     
         4 . The method of  claim 1 , the method further comprising defining the at least one change set and change set metadata prior to receiving the at least one in-line change. 
     
     
         5 . The method of  claim 1 , wherein the internal data structure is organized with the change set at a top level, the provision of law to be changed at a next level, and the adjacent in-line changes at a bottom level. 
     
     
         6 . A method of bill synthesis, the method comprising:
 creating a snapshot document, wherein the snapshot document includes at least one provision of law to be changed and a formalized reference to an original location for each provision of law to be changed;   receiving changes to the snapshot document to create an updated snapshot document, wherein the updated snapshot document includes at least one insertion or at least one deletion to each provision of law to be changed, at least one change set, and change set metadata for the at least one change set, wherein each deletion and each insertion is assigned to at least one change set;   analyzing the updated snapshot document based on extracting and enumerating each change set and change set metadata and enumerating each addition and each deletion belonging to the change set to create a hierarchical internal data structure for each change set;   constructing an XML changes document with each hierarchical internal data structure created for the updated snapshot document; and   analyzing the XML changes document to generate a bill representation by determining a template model from a template library to synthesize the XML changes document; and   presenting the bill representation to a legislature of a jurisdiction in a format required by the jurisdiction.   
     
     
         7 . The method of  claim 6 , the method further comprising receiving the at least one provision of law to be included in the snapshot document from input received through a graphical user interface, wherein a search is conducted for the at least one provision of law through the graphical user interface, further wherein the at least one provision of law is selected through the graphical user interface, and further wherein the at least one provision of law is inserted into the snapshot document through the graphical user interface. 
     
     
         8 . The method of  claim 6 , wherein the at least one insertion or deletion to the snapshot document is made in-line in-context to the text of the provision of law. 
     
     
         9 . The method of  claim 6 , wherein the change set metadata includes at least one of a description of a legal effect to be accomplished by the change set, a dependency of the change set, or effectivity rules for the change set. 
     
     
         10 . The method of  claim 6 , wherein each change set includes all insertions and deletions having a same legal effect. 
     
     
         11 . The method of  claim 6 , wherein the formalized legal reference is determined based on a legal citation for the provision of law. 
     
     
         12 . The method of  claim 6 , wherein synthesizing the XML changes document includes mapping the hierarchical internal data structure to the determined template model. 
     
     
         13 . The method of  claim 12 , wherein the mapping structures a set of jurisdiction specific language to the changes created in the updated snapshot document. 
     
     
         14 . A system for bill synthesis, the system comprising:
 a processor;   a graphical user interface; and   a non-transitory computer readable medium programmed with computer readable code that upon execution by the processor causes the processor to:
 create a snapshot document, wherein the snapshot document includes at least one provision of law to be changed and a formalized reference to an original location for each provision of law to be changed; 
 receive changes to the snapshot document to create an updated snapshot document, wherein the updated snapshot document includes at least one insertion or at least one deletion to each provision of law to be changed, at least one change set, and change set metadata for the at least one change set, wherein each deletion and each insertion is assigned to at least one change set; 
 analyze the updated snapshot document based on extracting and enumerating each change set and change set metadata and enumerating each addition and each deletion belonging to the change set to create a hierarchical internal data structure for each change set; 
 construct an XML changes document with each hierarchical internal data structure created for the updated snapshot document; and 
 analyze the XML changes document to generate a bill representation by determining a template model from a template library to synthesize the XML changes document; and 
 present the bill representation to a legislature of a jurisdiction in a format required by the jurisdiction. 
   
     
     
         15 . The of  claim 14 , wherein the processor is further instructed to receive the at least one provision of law to be included in the snapshot document from input received through the graphical user interface, wherein a search is conducted for the at least one provision of law through the graphical user interface, further wherein the at least one provision of law is selected through the graphical user interface, and further wherein the at least one provision of law is inserted into the snapshot document through the graphical user interface. 
     
     
         16 . The system of  claim 14 , wherein the at least one insertion or deletion to the snapshot document is made in-line in-context to the text of the provision of law. 
     
     
         17 . The system of  claim 14 , wherein the change set metadata includes at least one of a description of a legal effect to be accomplished by the change set, a dependency of the change set, or effectivity rules for the change set. 
     
     
         18 . The system of  claim 14 , wherein each change set includes all insertions and deletions having a same legal effect. 
     
     
         19 . The system of  claim 14 , wherein the formalized legal reference is determined based on a legal citation for the provision of law. 
     
     
         20 . The system of  claim 14 , wherein synthesizing the XML changes document includes mapping the hierarchical internal data structure to the determined template model, further wherein the mapping structures a set of jurisdiction specific language to the changes created in the updated snapshot document.