US 12,307,211 B2
Using machine learning models to analyze contractual terms and clauses in a legal contract, to recommend edits, and to make changes to a workflow
Cai GoGwilt, San Francisco, CA (US); Jennifer S. S. Monteleone, Kirkland, WA (US); Adam Weber, San Francisco, CA (US); Yujiao Zhang, San Mateo, CA (US); Angela Kou, Sugar Land, TX (US); Vidya Ravikumar, San Ramon, CA (US); Kevin Verdieck, Oakland, CA (US); Wolfgang Van HellicksonSabelhaus, San Francisco, CA (US); Katherine Vilhena, Oakland, CA (US); Peter Nam That Ton, Milpitas, CA (US); Nilay Amit Sadavarte, San Francisco, CA (US); Sumuk Rao, Fremont, CA (US); Jean-Marc Soumet, Sunnyvale, CA (US); and Alexander S. Gillmor, Norton, MA (US)
Assigned to IRONCLAD, INC., San Francisco, CA (US)
Filed by Ironclad, Inc., San Francisco, CA (US)
Filed on Feb. 29, 2024, as Appl. No. 18/591,776.
Application 18/591,776 is a continuation of application No. 18/467,363, filed on Sep. 14, 2023, granted, now 11,960,849.
Claims priority of provisional application 63/482,574, filed on Jan. 31, 2023.
Claims priority of provisional application 63/375,683, filed on Sep. 14, 2022.
Prior Publication US 2024/0202467 A1, Jun. 20, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/56 (2020.01); G06F 40/166 (2020.01)
CPC G06F 40/56 (2020.01) [G06F 40/166 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a computing device, a contract document comprising a plurality of clauses;
providing at least a first portion of the contract document as input to an extractive language model that is configured to classify legal clauses of a contract document as one or more types of clauses, wherein the first portion of the contract document comprises a first clause;
determining, using the extractive language model, a classification for the first portion of the contract indicating that the first clause is of a first type of clause, of the one or more types of clauses;
providing at least the first portion of the contract document and the determined classification for the first portion of the contract document as input to a generative language model that is configured to determine suggested edits to a contract document based on a plurality of pre-configured rules corresponding to the one or more types of clauses;
determining, using the generative language model, a suggested edit to the contract document based on a difference between at least one contract term of the first portion of the contract document and a specified contract term of a first pre-configured rule corresponding to the first type of clause; and
generating, by the computing device, output data generated based on the determined classification for the first portion of the contract document and the suggested edit to the contract document, wherein the output data comprises an indication of the first portion of the contract document, the first type of clause, and the suggested edit to the contract document.