US 12,223,316 B2
Architecture discovery
Hugo Miguel Ferrão Casal Da Veiga, Lisbon (PT); António Manuel de Carvalho dos Santos Alegria, Lisbon (PT); and Rui Valdemar Pereira Madaleno, Lisbon (PT)
Assigned to OutSystems—Software em Rede, S.A., (PT)
Filed by OutSystems—Software em Rede, S.A., Linda-a-Velha (PT)
Filed on Jan. 9, 2024, as Appl. No. 18/408,122.
Application 18/408,122 is a continuation of application No. 17/399,983, filed on Aug. 11, 2021, granted, now 11,922,137.
Claims priority of provisional application 63/110,330, filed on Nov. 5, 2020.
Claims priority of provisional application 63/117,895, filed on Nov. 24, 2020.
Claims priority of provisional application 63/117,899, filed on Nov. 24, 2020.
Prior Publication US 2024/0143285 A1, May 2, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/20 (2018.01); G06F 8/10 (2018.01); G06F 8/34 (2018.01); G06F 8/41 (2018.01); G06F 8/72 (2018.01); G06F 8/75 (2018.01); G06F 16/31 (2019.01); G06F 18/21 (2023.01); G06F 18/2113 (2023.01); G06F 40/284 (2020.01); G06N 3/04 (2023.01)
CPC G06F 8/75 (2013.01) [G06F 8/10 (2013.01); G06F 8/34 (2013.01); G06F 8/423 (2013.01); G06F 8/433 (2013.01); G06F 8/72 (2013.01); G06F 16/319 (2019.01); G06F 18/2113 (2023.01); G06F 18/2178 (2023.01); G06F 40/284 (2020.01); G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
training a machine learning model to predict to which one among a plurality of program architecture layer classifications a program code component module belongs, including by:
forming a training dataset, wherein:
the training dataset includes a training program code component module and an assignment of the training program code component module to a program architecture layer classification included in the plurality of program architecture layer classifications;
the program architecture layer classification included in the plurality of program architecture layer classifications identifies a functionality within a computer program that the training program code component module performs;
the plurality of program architecture layer classifications includes a first layer corresponding to a first architectural role and a second layer corresponding to a second architectural role; and
using the training dataset to train the machine learning model; and
outputting the trained machine learning model.