US 11,887,045 B2
Determining resource requirements
Sunil Kumar Chinnamgari, Bangalore (IN); and Abhishek Sanwaliya, Bangalore (IN)
Assigned to Maersk A/S, Copenhagen (DK)
Appl. No. 17/793,967
Filed by Maersk A/S, Copenhagen (DK)
PCT Filed Feb. 4, 2021, PCT No. PCT/EP2021/052690
§ 371(c)(1), (2) Date Jul. 20, 2022,
PCT Pub. No. WO2021/160514, PCT Pub. Date Aug. 19, 2021.
Claims priority of application No. 202000173 (DK), filed on Feb. 12, 2020.
Prior Publication US 2023/0066889 A1, Mar. 2, 2023
Int. Cl. G06Q 10/083 (2023.01); G06Q 10/04 (2023.01)
CPC G06Q 10/0838 (2013.01) [G06Q 10/04 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for determining future resource requirements in a given location, the method comprising the steps of:
obtaining transaction data, the transaction data indicative of past resource use at a plurality of locations, which includes the give location;
training at least one machine learning model based on a set of parameters by:
determining a distribution of resources associated with the transaction data;
generating a machine learning kernel based on the set of parameters, the machine learning kernel being arranged to output an estimated distribution of resources over the plurality of locations; and
refining and validating the machine learning kernel based on a comparison between the distribution and the estimated distribution of the resources;
generating a density map of the resources for the plurality of locations based on the at least one trained machine learning model; and
sending the density map to a control system for determining future resource requirements in the given location.