US 11,809,805 B2
Using machine learning to predict performance of secure documents
Soroush Salehian, Kirkland, WA (US); William Pittman, Seattle, WA (US); John Barcellos, Seattle, WA (US); Santiago Szuchmacher, Seattle, WA (US); Chris Marshall, Shoreline, WA (US); Jeong Woo Chang, Mercer Island, WA (US); and Dylan Ray Häs, Seattle, WA (US)
Assigned to DocuSign, Inc., San Francisco, CA (US)
Filed by DocuSign, Inc., San Francisco, CA (US)
Filed on Feb. 28, 2022, as Appl. No. 17/682,859.
Application 17/682,859 is a continuation of application No. 17/067,558, filed on Oct. 9, 2020, granted, now 11,301,616.
Prior Publication US 2022/0180042 A1, Jun. 9, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/00 (2020.01); G06F 40/106 (2020.01); G06V 30/40 (2022.01); G06N 20/00 (2019.01); G06F 21/62 (2013.01); G06F 40/186 (2020.01); G06F 40/216 (2020.01); G06F 18/21 (2023.01)
CPC G06F 40/106 (2020.01) [G06F 18/2193 (2023.01); G06F 21/6209 (2013.01); G06F 40/186 (2020.01); G06F 40/216 (2020.01); G06N 20/00 (2019.01); G06V 30/40 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
detecting that a requesting user is transmitting a request to a recipient user to perform one or more tasks with respect to a secure document;
in response to detecting that the requesting user is transmitting the request, determining a probability that the recipient user fails to complete the transmitted request by applying a machine learned model trained on features and completion data associated with historical secure documents to features of the secure document;
in response to determining the probability, identifying a plurality of action recommendations associated with the determined probability, determining a value of probability associated with each action recommendation in the plurality of action recommendations, and selecting, based on a comparison of the value of probability associated with each action recommendation to a threshold value, one or more action recommendations in the plurality of action recommendations configured to, when performed, improve a likelihood of the recipient user completing the request; and
presenting the selected one or more action recommendations to the requesting user, and displaying the value of probability associated with each of the selected one or more action recommendations exceeding the threshold value.