US 12,033,196 B2
Accelerated invoicing using predictive freight events
Krishnasuri Narayanam, Bangalore (IN); Pankaj Satyanarayan Dayama, Bangalore (IN); and Yedendra Shrinivasan, Scarsdale, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Sep. 21, 2021, as Appl. No. 17/480,173.
Prior Publication US 2023/0096163 A1, Mar. 30, 2023
Int. Cl. G06Q 30/04 (2012.01); G06F 16/27 (2019.01); G06Q 10/0631 (2023.01); G06N 20/00 (2019.01); G06Q 10/083 (2024.01); G06Q 10/0831 (2023.01); G06Q 20/38 (2012.01)
CPC G06Q 30/04 (2013.01) [G06F 16/27 (2019.01); G06Q 10/06315 (2013.01); G06N 20/00 (2019.01); G06Q 10/0831 (2013.01); G06Q 10/0838 (2013.01); G06Q 20/389 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
a processor that, when executing instructions stored in a memory, is configured to:
iteratively train an artificial intelligence (AI) model comprising a neural network by executing the neural network on actual events of historical shipments and predicted events of the historical shipments to generate a trained AI model:
query, via an application programming interface (API), a blockchain ledger for attributes of a shipment by a carrier from an origin location to a destination location;
predict, via the trained AI model, one or more future milestone events that will occur during the shipment based on the attributes of the shipment retrieved from querying the blockchain ledger;
identify that the shipment requires processing;
in response to the identification, call a smart contract to execute invoice generation, wherein the processor is further configured to:
receive the one or more future milestone events from the trained AI model;
predict, via the trained AI model, a value of charges based on the one or more future milestone events by a first logic of the smart contract;
determine accuracy of the prediction of the value of the charges by a second logic of the smart contract;
in response to the determination of the accuracy of the prediction of the value of the charges, generate, via the smart contract, a plurality of accelerated e-invoices during the shipment, where the plurality of accelerated e-invoices are based on and correspond to one or more milestone events that have already occurred and the predicted one or more future milestone events;
store the plurality of accelerated e-invoices on the blockchain ledger;
execute a plurality of payments corresponding to the plurality of accelerated e-invoices before the shipment reaches the destination; and
display information associated with the shipment by a user interface.