US 11,720,964 B2
System and method for natural language order fill
Senthilkumar Subramaniam, Tiruppur (IN); Jyoti Roy, Bangalore (IN); Tushar Agrawal, Bangalore (IN); Prajod Kumbalaparambil Ramanunni, Singapore (SG); and Vijayasingam Thanasekaran, Singapore (SG)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMorgan Chase Bank, N.A., New York, NY (US)
Filed on Apr. 5, 2021, as Appl. No. 17/222,511.
Claims priority of application No. 202111007384 (IN), filed on Feb. 22, 2021.
Prior Publication US 2022/0270170 A1, Aug. 25, 2022
Int. Cl. G06Q 40/00 (2023.01); G06Q 40/04 (2012.01); G06F 40/20 (2020.01); G06N 3/04 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 40/04 (2013.01) [G06F 40/20 (2020.01); G06N 3/04 (2013.01); G06N 20/00 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A method for implementing a natural language order fill module by utilizing one or more processors and one or more memories, the method comprising:
building a machine learning model configured to learn different trading ticket fields per product and asset class, business terms, and nomenclature;
training, by a processor of the one or more processors, the machine learning model to auto-fill, in real-time, ticket order entry details data as a user types, via an input device, into the free-form text box;
configuring, by the processor, a free-form text box to receive, from the input device, user input data corresponding to trade details of a particular trade;
implementing neural networks algorithm to interpret and extract key trade details data from the user input data corresponding to the trade details of the particular trade regardless of text structure of the user input data; and
implementing, by the processor, a bi-directional long short term memory (LSTM) model that utilizes all previously entered text to predict and automatically fill in corresponding trading ticket fields in real-time, as the user inputs, via the input device, the user input data into the free-form text box, based on the key trade details data.