US 11,875,138 B2
System and method for matching integration process management system users using deep learning and matrix factorization
Daniel Schwartz, Marlton, NJ (US); and Michael J. Morton, Morrisville, NC (US)
Assigned to BOOMI, LP, Chesterbrook, PA (US)
Filed by BOOMI, INC., Round Rock, TX (US)
Filed on Jul. 13, 2020, as Appl. No. 16/927,295.
Prior Publication US 2022/0012022 A1, Jan. 13, 2022
Int. Cl. G06F 8/34 (2018.01); G06N 3/08 (2023.01); G06F 8/35 (2018.01); G06F 3/048 (2013.01); G06Q 30/0202 (2023.01)
CPC G06F 8/34 (2013.01) [G06F 3/048 (2013.01); G06F 8/35 (2013.01); G06N 3/08 (2013.01); G06Q 30/0202 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An information handling system operating an integration process user matching system comprising:
a network interface device receiving a plurality of execution logs recording data for tracking selections of integration process visual elements by a plurality of users for developing integration processes;
a processor generating a user/visual element interaction matrix based on a plurality of counts of integration process visual element selections;
the processor inputting the user/visual element interaction matrix into a trained neural network to generate an optimized user preference embedding matrix and an optimized visual element embedding matrix;
the processor determining a latent feature user preference value for increasing accuracy of preferences in user feedback by incorporating negative feedback from the plurality of users for each of the plurality of integration process visual elements based on the optimized user preference embedding matrix and the optimized visual element embedding matrix;
the processor identifying a subset of matching users associated with latent feature user preference values for one of the plurality of integration process visual elements falling within a preset range of each other as matching users; and
the network interface device transmitting identification of the subset of matching users and identification of the one of the plurality of integration process visual elements to at least one matching user.