AMENDMENT TRACKING IN AN ONLINE DOCUMENT SYSTEM
An online document system can allow users to track various amendments made over time and corresponding to an original document. The online document system accesses the original document comprising a plurality of content sections and a set of amendment documents each comprising one or more amendments to the original document. The online document system applies a machine-learned model to the original document and the set of amendment documents to identify, for each amendment, a content section of the plurality that corresponds to the amendment and a type of amendment corresponding to the amendment. The online document system generates an amended original document comprising the plurality of content sections modified to include each amendment. The online document system displays the amended original document by displaying each of the plurality of content sections and, in conjunction with each content section, any amendments corresponding to the content section are highlighted.
1 - 20 . (canceled)
21 . A computer implemented method, comprising:
receiving, using at least one processor, a first document and a second document, the second document including one or more amendments to the first document, the first document including a plurality of first characters, and the second document including a plurality of second characters;
applying, using the at least one processor, a machine learning model to the first and second documents to identify a content section in a plurality of content sections corresponding to at least one amendment in the one or more amendments in the second document and a type of amendment corresponding to the at least one amendment, the machine learning model identifying the content section and the type of amendment based on at least one first character in the plurality of first characters and at least one second character in the plurality of second characters;
generating, using the at least one processor, an amended first document based on the first document and including the at least one amendment corresponding to the identified content section identified by the machine learning model; and
generating, using the at least one processor, a graphical user interface displaying the amended first document and indicating the at least one amendment and the identified type of the at least one amendment in the amended first document.
22 . The method of claim 21 , wherein identification of the content section includes
comparing the at least one first character to one or more listings of commonly-used characters corresponding to characters used in the plurality of content sections in the first document;
generating, based on the comparing, a listing of one or more content sections in the plurality of content sections in the first document;
comparing the at least one second character to the generated listing of the one or more content sections; and
identifying the content section in the second document based on the comparing of the at least one second character to the generated listing of the one or more content sections.
23 . The method of claim 21 , wherein identification of type of amendment includes
comparing the at least one second character to one or more listings of commonly-used characters corresponding to one or more types of amendments; and
identifying the type of amendment in the second document based on the comparing of the at least one second character to the one or more listings of commonly-used characters corresponding to the one or more types of amendments.
24 . The method of claim 21 , further comprising determining, using the machine learning model, a first probability indicating a likelihood of the identified content section in the second document having the at least one second character is related to a content section in the first document having the at least one first character.
25 . The method of claim 23 , further comprising determining, using the machine learning model, a second probability indicating a likelihood of the amendment in the second document having the at least one second character is the identified type of amendment.
26 . The method of claim 21 , further comprising
receiving a plurality of second documents, the plurality of second documents including the one or more amendments to the first document, the plurality of second documents including the plurality of second characters;
applying the machine learning model to the plurality of second documents to identify one or more content sections corresponding to a plurality of amendments in the plurality of second documents and one or more types of amendments corresponding to the plurality of amendments, the machine learning model identifying the one or more content sections and the one or more types of amendments based on the at least one first character and the at least one second character in the plurality of second characters in the plurality of second documents;
generating the amended first document based on the first document and including the plurality of amendments corresponding to the identified one or more content sections identified by the machine learning model; and
generating the graphical user interface displaying the amended first document.
27 . The method of claim 21 , wherein the type of amendment includes at least one of the following: an addition amendment, a substitution amendment, a deletion amendment, a modification amendment, and any combinations thereof.
28 . The method of claim 21 , wherein the displaying the amended first document includes displaying, within the graphical user interface, adjacent to the at least one amendment, information about the at least one amendment, the information including at least one of: an identifier of the second document, the type of amendment, a timing identifier corresponding to the second document, and any combinations thereof.
29 . A system, comprising:
at least one processor circuitry; and
at least one non-transitory storage media storing instructions, that when executed by the at least one processor, cause the at least one processor circuitry to perform operations including
receive a first document and a second document, the second document including one or more amendments to the first document, the first document including a plurality of first characters, and the second document including a plurality of second characters;
apply a machine learning model to the first and second documents to identify a content section in a plurality of content sections corresponding to at least one amendment in the one or more amendments in the second document and a type of amendment corresponding to the at least one amendment, the machine learning model identifying the content section and the type of amendment based on at least one first character in the plurality of first characters and at least one second character in the plurality of second characters;
generate an amended first document based on the first document and including the at least one amendment corresponding to the identified content section identified by the machine learning model; and
generate a graphical user interface displaying the amended first document and indicating the at least one amendment and the identified type of the at least one amendment in the amended first document.
30 . The system of claim 29 , wherein identification of the content section includes
comparing the at least one first character to one or more listings of commonly-used characters corresponding to characters used in the plurality of content sections in the first document;
generating, based on the comparing, a listing of one or more content sections in the plurality of content sections in the first document;
comparing the at least one second character to the generated listing of the one or more content sections; and
identifying the content section in the second document based on the comparing of the at least one second character to the generated listing of the one or more content sections.
31 . The system of claim 29 , wherein identification of type of amendment includes
comparing the at least one second character to one or more listings of commonly-used characters corresponding to one or more types of amendments; and
identifying the type of amendment in the second document based on the comparing of the at least one second character to the one or more listings of commonly-used characters corresponding to the one or more types of amendments.
32 . The system of claim 29 , wherein the operations further comprise determine, using the machine learning model, a first probability indicating a likelihood of the identified content section in the second document having the at least one second character is related to a content section in the first document having the at least one first character.
33 . The system of claim 32 , wherein the operations further comprise determine, using the machine learning model, a second probability indicating a likelihood of the amendment in the second document having the at least one second character is the identified type of amendment.
34 . The system of claim 29 , wherein the operations further comprise
receive a plurality of second documents, the plurality of second documents including the one or more amendments to the first document, the plurality of second documents including the plurality of second characters;
apply the machine learning model to the plurality of second documents to identify one or more content sections corresponding to a plurality of amendments in the plurality of second documents and one or more types of amendments corresponding to the plurality of amendments, the machine learning model identifying the one or more content sections and the one or more types of amendments based on the at least one first character and the at least one second character in the plurality of second characters in the plurality of second documents;
generate the amended first document based on the first document and including the plurality of amendments corresponding to the identified one or more content sections identified by the machine learning model; and
generate the graphical user interface displaying the amended first document.
35 . The system of claim 29 , wherein the type of amendment includes at least one of the following: an addition amendment, a substitution amendment, a deletion amendment, a modification amendment, and any combinations thereof.
36 . The system of claim 29 , wherein the displaying the amended first document includes displaying, within the graphical user interface, adjacent to the at least one amendment, information about the at least one amendment, the information including at least one of: an identifier of the second document, the type of amendment, a timing identifier corresponding to the second document, and any combinations thereof.
37 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor circuitry, cause the at least one programmable processor circuitry to perform operations comprising:
receive a first document and a second document, the second document including one or more amendments to the first document, the first document including a plurality of first characters, and the second document including a plurality of second characters;
apply a machine learning model to the first and second documents to identify a content section in a plurality of content sections corresponding to at least one amendment in the one or more amendments in the second document and a type of amendment corresponding to the at least one amendment, the machine learning model identifying the content section and the type of amendment based on at least one first character in the plurality of first characters and at least one second character in the plurality of second characters;
generate an amended first document based on the first document and including the at least one amendment corresponding to the identified content section identified by the machine learning model; and
generate a graphical user interface displaying the amended first document and indicating the at least one amendment and the identified type of the at least one amendment in the amended first document.
38 . The computer program product of claim 37 , wherein identification of the content section includes
comparing the at least one first character to one or more listings of commonly-used characters corresponding to characters used in the plurality of content sections in the first document;
generating, based on the comparing, a listing of one or more content sections in the plurality of content sections in the first document;
comparing the at least one second character to the generated listing of the one or more content sections; and
identifying the content section in the second document based on the comparing of the at least one second character to the generated listing of the one or more content sections.
39 . The computer program product of claim 37 , wherein identification of type of amendment includes
comparing the at least one second character to one or more listings of commonly-used characters corresponding to one or more types of amendments; and
identifying the type of amendment in the second document based on the comparing of the at least one second character to the one or more listings of commonly-used characters corresponding to the one or more types of amendments.
40 . The computer program product of claim 37 , wherein the operations further comprise
determine, using the machine learning model, a first probability indicating a likelihood of the identified content section in the second document having the at least one second character is related to a content section in the first document having the at least one first character; and
determine, using the machine learning model, a second probability indicating a likelihood of the amendment in the second document having the at least one second character is the identified type of amendment.