Method and system for embedding hyperlinks in legal documents

Abstract

A method for embedding hyperlinks in legal documents. The method can include receiving input including docx and PDF documents, converting the input into text, parsing the converted text by pattern recognition, and generating an output of a parent PDF document containing attached documents with hyperlinks, the hyperlinks identifying between the attached documents.

1 - 20 . (canceled) 
     
     
         21 . A method comprising:
 receiving an input including a first document and a second document;   determining a citation convention based at least in part on content of the first document and content of the second document, the citation convention associated with the first document and including one or more characters consistent between a first citation in the first document and a second citation in the first document;   parsing the content of the first document based at least in part on the citation convention to identify a third citation, the third citation referring to a portion of the content of the second document;   converting at least a portion of the third citation in the first document to a selectable portion; and   responsive to a selection of the selectable portion, transitioning a user from a position of the third citation in the first document to a position of the portion of the content of the second document.   
     
     
         22 . The method as recited in  claim 21 , further comprising:
 identifying a portion of the content of the first document associated with the third citation.   
     
     
         23 . The method as recited in  claim 22 , further comprising:
 receiving, a request for supporting details associated with the portion of the content of the first document;   identifying the supporting details for the portion of the content of the first document in text of the second document;   generating a summary of the text of the second document; and   presenting the summary.   
     
     
         24 . The method as recited in  claim 22 , further comprising:
 determining a correspondence between the portion of the content of the first document and the portion of the content of the second document indicate by the third citation;   determining an accuracy rating associated with the portion of the content of the first document based at least in part on the correspondence; and   inserting the accuracy rating as an overlay to the first document.   
     
     
         25 . The method as recited in  claim 21 , further comprising:
 parsing the portion of the second document;   identifying numbers on pages of the portion of the second document differs from Bate stamp numbers associated with the second document; and   renumbering the pages of the portion of the second document based at least in part on the Bate stamp numbers.   
     
     
         26 . The method as recited in  claim 21 , further comprising:
 generating a combined document based at least in part on the first document and the second document.   
     
     
         27 . The method as recited in  claim 21 , further comprising:
 determining relevant text associated with the third citation; and   visually marking text of the second document corresponding to the relevant text.   
     
     
         28 . The method as recited in  claim 21 , further comprising:
 parsing content of the first document based at least in part on the citation convention to identify a fourth citation, the fourth citation referring to a portion of content of a third document;   converting at least a portion of the fourth citation in the first document to a second selectable portion; and   responsive to a selection of the second selectable portion, transitioning a user from a position of the fourth citation in the first document to a position of the portion of the content of the third document.   
     
     
         29 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause one or more computing devices to perform operations comprising:
 receiving, from a client device, a first document;   receiving, from the client device, a second document, the first document referencing the second document;   parsing text of the first document based at least in part on a citation convention to identify a third citation, the third citation referencing content of the second document;   determining a bounding box associated with the third citation; and   converting a portion of the third citation to a selectable portion, the first portion of the third citation within the bounding box and the selectable portion to transition the user from a first position in first document to a second position in the second document, the second position associated with the content of the second document indicated by the third citation.   
     
     
         30 . The one or more non-transitory computer-readable media as recited in  claim 29 , wherein the operations further comprise:
 determining relevant text of the second document associated with the third citation; and   visually marking text of the second document corresponding to the relevant text.   
     
     
         31 . The one or more non-transitory computer-readable media as recited in  claim 29 , wherein the operations further comprise:
 identifying a portion of the content of the first document associated with the third citation; and   visually marking the portion of the content of the first document.   
     
     
         32 . The one or more non-transitory computer-readable media as recited in  claim 31 , wherein the operations further comprise:
 receiving, a request for supporting details associated with the portion of the content of the first document;   identifying the supporting details for the portion of the content of the first document in text of the second document;   generating a summary of the text of the second document; and   presenting the summary.   
     
     
         33 . The one or more non-transitory computer-readable media as recited in  claim 31 , wherein the operations further comprise:
 determining a correspondence between the portion of the content of the first document and the portion of the content of the second document indicate by the third citation;   determining an accuracy rating associated with the portion of the content of the first document based at least in part on the correspondence; and   inserting the accuracy rating as an overlay to the first document.   
     
     
         34 . The one or more non-transitory computer-readable media as recited in  claim 29 , wherein the operations further comprise:
 parsing the portion of the second document;   identifying numbers on pages of the portion of the second document differs from Bate stamp numbers associated with the second document; and   renumbering the pages of the portion of the second document based at least in part on the Bate stamp numbers.   
     
     
         35 . The one or more non-transitory computer-readable media as recited in  claim 29 , wherein the operations further comprise:
 parsing content of the first document based at least in part on the citation convention to identify a fourth citation, the fourth citation referring to a portion of content of a third document;   converting at least a portion of the fourth citation in the first document to a second selectable portion; and   responsive to a selection of the second selectable portion, transitioning a user from a position of the fourth citation in the first document to a position of the portion of the content of the third document.   
     
     
         36 . The one or more non-transitory computer-readable media as recited in  claim 29 , wherein the operations further comprise:
 receiving, from the client device, the citation convention, the citation convention including the one or more characters consistent between a first citation in the first document and a second citation in the first document.   
     
     
         37 . A method comprising:
 receiving, at a server system from a computing device, a first document;   receiving, at the server system from the computing device, a second document, the first document referencing the second document;   parsing the first portion of the first document to identify a third citation to the second document; and   converting at least a portion of the third citation to a selectable portion; and   in response to a user selection of the selectable portion, transitioning the user from a first position in the first document to a second position in the second document, the second position indicated by the third citation.   
     
     
         38 . The method as recited in  claim 37 , further comprising generating combined content maintained in a structure based at least in part on the first document and the second document and wherein the second position is a position within the combined content. 
     
     
         39 . The method as recited in  claim 37 , further comprising:
 identifying a portion of the content of the first document associated with the third citation; and   visually marking the portion of the content of the first document.   
     
     
         40 . The method as recited in  claim 37 , further comprising:
 receiving, a request for supporting details associated with a portion of the content of the first document;   identifying the supporting details for the portion of the content of the first document in text of the second document;   generating a summary of the text of the second document; and   presenting the summary.