IP Library Granted Patent US 12681973
Granted Patent B1
US 12681973 · App. 18/678,937 · Granted Jul 14, 2026

Agreement renewal framework

Inventors: Hiral Shah (Palo Alto, CA); Shaheen Umer (Menlo Park, CA); Ramachandra Kota (Kirkland, WA); Shubham Gupta (Sunnyvale, CA); Dipam Haresh Vasani (San Francisco, CA); Shreeya Singh Dhakal (Bothell, WA); Cong Minh Phan (Renton, WA); Ashwath Saran Mohan (San Ramon, CA); Joshua Katowitz (San Diego, CA); Anthony Shalagin (Jersey City, NJ); Celine Beck (Montreal, CA); Jennifer Park (New York, NY)
Assignee: Docusign, Inc.
G06F16/338G06F16/3344G06F30/27G06F40/166G06Q50/18G06F16/168
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12681973
App. No.
18/678,937
Granted
Jul 14, 2026
Kind
B1
Abstract

A method, a system, and a computer program product for determining renewal of agreement documents. A first machine learning model is used to generate one or more portions of a document. Each portion of the document is associated with a predetermined subject. A query is generated using the predetermined subject. The query and one or more definitions of one or more attributes are provided to a second machine learning model. At least one attribute and a value assigned to the attribute are received from the second machine learning model. The value is extracted from one or more portions and assigned to the attribute. A graphical user interface displaying the attribute and the value assigned to the attribute is generated.

Claims (15)

1 . A computer-implemented method, comprising:

selecting, using at least one processor, a first machine learning model from a plurality of first machine learning models based on receiving a task associated with an electronic document, the first machine learning model has been trained to perform the task;

applying, using the at least one processor, the selected first machine learning model to the electronic document to extract one or more portions from the electronic document, each portion in the one or more portions of the electronic document is associated with a predetermined subject;

generating, using the at least one processor, a query using the predetermined subject;

providing, using the at least one processor, the query and one or more definitions of one or more attributes to a second machine learning model;

receiving, using the at least one processor, from the second machine learning model, at least one attribute in the one or more attributes and a value assigned to the at least one attribute, wherein the value is extracted from the one or more portions and assigned to the at least one attribute; and

generating, using the at least one processor, a graphical user interface displaying the at least one attribute and the value assigned to the at least one attribute.

2 . The method of claim 1 , wherein the query is a natural language representation query.

3 . The method of claim 1 , wherein the electronic document includes at least one of the following: a legal document, a non-legal document, and any combinations thereof.

4 . The method of claim 3 , wherein the one or more portions include at least one of the following: a page in the electronic document, a clause in the electronic document, a paragraph in the electronic document, a sentence in the electronic document, a phrase in the electronic document, a text in the electronic document, and any combination thereof.

5 . The method of claim 1 , wherein the one or more portions include at least one of the following: a text, an audio, a video, an image, a table, and any combination thereof.

6 . The method of claim 1 , wherein at least one of the first and second machine learning models includes at least one of the following: a large language model, at least one generative artificial intelligence model, and any combination thereof.

7 . The method of claim 1 , wherein the electronic document is an electronic agreement document having a predetermined expiration date and the predetermined subject is associated with a renewal of the electronic agreement document.

8 . The method of claim 7 , wherein the at least one attribute includes at least one of the following: a renewal term of the electronic agreement document, a renewal notice period of the electronic agreement document, a term of the electronic agreement document, and any combination thereof.

9 . The method of claim 8 , wherein the value assigned to the at least one attribute includes time.