US 11,748,554 B2
Amendment tracking in an online document system
Surendra Kumar Chilamkurthi, Naperville, IL (US); Heidi Robin Lyons, Madison, WI (US); Anirudha Vedavyasa Murthy Bharadwaj, Chicago, IL (US); Shivi Singh Verma, Issaquah, WA (US); Aaron Eugene Preston Jackson Wilde, Portland, OR (US); and Cynthia Rosser, San Francisco, CA (US)
Assigned to DOCUSIGN, INC., San Francisco, CA (US)
Filed by DocuSign, Inc., San Francisco, CA (US)
Filed on Jul. 30, 2021, as Appl. No. 17/390,748.
Prior Publication US 2023/0033563 A1, Feb. 2, 2023
Int. Cl. G06F 17/00 (2019.01); G06F 40/169 (2020.01); G06F 40/295 (2020.01); G06N 20/00 (2019.01); G06V 30/14 (2022.01)
CPC G06F 40/169 (2020.01) [G06F 40/295 (2020.01); G06N 20/00 (2019.01); G06V 30/1444 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A method comprising:
accessing, by an online document system, an original document comprising a plurality of content sections;
accessing, by the online document system, a set of amendment documents each comprising one or more amendments to the original document;
applying, by the online document system, a machine-learned model to the original document and the set of amendment documents, the machine-learned model configured to identify, for each amendment document of the set of amendment documents, a content section of the plurality of content sections corresponding to each amendment of the one or more amendments and a type of amendment corresponding to each amendment of the one or more amendments, wherein the machine-learned model is trained using a training set of labeled documents that include labeled original documents and corresponding labeled amendment documents, each labeled original document in the training set comprising a plurality of training content sections at least one of which is labeled to indicate presence of an amendment, and each labeled amendment document in the training set comprising one or more training amendments at least one of which is labeled to indicate a corresponding content section of the corresponding labeled original document and further labeled to indicate a type of the training amendment;
generating, by the online document system, an amended original document comprising the plurality of content sections modified to include each amendment corresponding to each content section identified by the machine-learned model based on the type of amendment identified by the machine-learned model; and
displaying, by the online document system within a document interface, 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 highlighted within the document interface.