US 12,333,467 B2
Method for controlling a process for handling a conflict and related electronic device
Sunil Kumar Chinnamgari, Bangalore (IN); Abhishek Sanwaliya, Bangalore (IN); Anagh Majumder, Bangalore (IN); and Sushma Rai, Bangalore (IN)
Assigned to Maersk A/S, Copenhagen K (DK)
Appl. No. 18/013,979
Filed by Maersk A/S, Copenhagen K (DK)
PCT Filed Jun. 30, 2021, PCT No. PCT/EP2021/068041
§ 371(c)(1), (2) Date Dec. 30, 2022,
PCT Pub. No. WO2022/008316, PCT Pub. Date Jan. 13, 2022.
Claims priority of application No. PA202070472 (DK), filed on Jul. 9, 2020.
Prior Publication US 2023/0289682 A1, Sep. 14, 2023
Int. Cl. G06Q 10/0631 (2023.01); G06Q 50/40 (2024.01)
CPC G06Q 10/06313 (2013.01) [G06Q 50/40 (2024.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method, performed by an electronic device, for controlling a process for handling a conflict, the method comprising:
receiving, at a first computer system, an electronic data conflict query from a second computer system, the first computer system comprising one or more processors;
identifying, by the one or more processors, and based on the electronic data conflict query, a first electronic data set, the first electronic data set comprising data associated with one or more of: a shipment system, a dispute resolution system, a customer system, or a case management system;
determining, by the one or more processors, a feature selection based on the first electronic data set;
determining, by the one or more processors and based on the feature selection, one or more parameters of a machine-learned predictive model, the predictive model comprising an ensemble model comprising a first machine-learned model and a second machine-learned model, the first machine-learned model and the second machine-learned model trained based on one or more iterative cycles of training, each cycle comprising generating a first output by the first machine-learned model, adjusting weights of the second machine-learned model based on errors associated with the first output, and generating a second output by the second machine-learned model based on the adjusted weights;
instantiating, by the one or more processors, the predictive model based at least in part on the one or more parameters;
identifying, by the one or more processors, based on the first data set and the predictive model, one or more conflict data patterns indicative of a conflict, the one or more conflict data patterns associated with one or more of: a data conflict between a first dimension and a second dimension of the first electronic data set; or a data conflict between the first electronic data set and a second electronic data set, the first electronic data set associated with the first computer system and the second electronic data set associated with the second computer system;
generating, by the one or more processors and based on the one or more conflict data patterns, a conflict result parameter and a confidence score associated with the conflict result parameter, the conflict result parameter associated with a predicted existence of the data conflict; and
based on the conflict result parameter and the confidence score, one or more of, by the one or more processors:
transmitting a conflict result to the second computer system;
resolving the data conflict; or
transmitting an approval request to an approval authority system.