US 12,277,527 B2
Carrier path prediction based on dynamic input data
Ioannis Martinos, Athens (GR); Dimitrios Tasoulis, Athens (GR); Michail Epitropakis, Athens (GR); Roussos Paschopoulos, Athens (GB); and Emilio Frazzoli, Boston, MA (US)
Assigned to Signal Ocean Ltd, London (GB)
Filed by Signal Ocean Ltd, London (GB)
Filed on Nov. 2, 2023, as Appl. No. 18/500,949.
Application 18/500,949 is a continuation of application No. 17/228,452, filed on Apr. 12, 2021, granted, now 11,810,058.
Application 17/228,452 is a continuation of application No. 16/000,641, filed on Jun. 5, 2018, granted, now 10,977,605, issued on Apr. 13, 2021.
Prior Publication US 2024/0062149 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/00 (2019.01); G06Q 10/0835 (2023.01); H04L 67/10 (2022.01); B63B 79/40 (2020.01); G06F 16/29 (2019.01)
CPC G06Q 10/08355 (2013.01) [H04L 67/10 (2013.01); B63B 79/40 (2020.01); G06F 16/29 (2019.01)] 25 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining a set of carrier information for individual identifiable vessels;
forming a plurality of skeleton scenario paths for the individual identifiable vessels from the set of carrier information, wherein each skeleton scenario path of the plurality of skeleton scenario paths for the individual identifiable vessels is defined by one or more anchor points;
selecting a first portion of a plurality of target paths corresponding to a first portion of the skeleton paths;
assigning attributes to the first portion of the plurality of target paths, wherein an attribute associated with individual target paths is based on a determined probability that the individual target path is a correct travel path for the identifiable vessel; and
generating a ranked list of the plurality of target paths for the individual identifiable vessels based on application of a scoring function, wherein the scoring function is at least in part based on the attributes.