US 12,236,211 B2
Providing resolution suggestions in a program development tool
Filipe Guerreiro Assunção, Lisbon (PT); João Pedro Gonçalves Lages, Lisbon (PT); and António Manuel De Carvalho Dos Santos Alegria, 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 Aug. 10, 2023, as Appl. No. 18/232,654.
Application 18/232,654 is a continuation of application No. 17/399,975, filed on Aug. 11, 2021, granted, now 11,782,681.
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 2024/0036829 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/71 (2018.01); G06F 8/20 (2018.01); G06F 8/38 (2018.01); G06F 8/61 (2018.01); G06F 16/906 (2019.01); G06F 16/953 (2019.01); G06N 5/022 (2023.01); G06N 5/04 (2023.01); G06F 8/33 (2018.01); G06F 11/07 (2006.01)
CPC G06F 8/20 (2013.01) [G06F 16/906 (2019.01); G06F 16/953 (2019.01); G06N 5/022 (2013.01); G06N 5/04 (2013.01); G06F 8/33 (2013.01); G06F 11/079 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
tracking user interactions and states of a program development tool utilized to develop an application including by:
tracking a plurality of time windows of a user interaction session, and
for each of at least a portion of the plurality of time windows, determining a set of features;
providing input features including the determined set of features associated with the tracked user interactions and the states to a trained machine learning model to determine a prediction result associated with user progression in developing the application;
in response to a determination that the prediction result at least meets a threshold, providing one or more resolution suggestions; and
outputting the one or more resolution suggestions to further train the machine learning model.