US 12,190,254 B2
Chatbot for defining a machine learning (ML) solution
Alberto Polleri, London (GB); Sergio Lopez, London (GB); Marc Michiel Bron, London (GB); Dan David Golding, London (GB); Alexander Ioannides, London (GB); Maria del Rosario Mestre, London (GB); Hugo Alexandre Pereira Monteiro, London (GB); Oleg Gennadievich Shevelev, London (GB); Larissa Cristina Dos Santos Romualdo Suzuki, Wokingham (GB); Xiaoxue Zhao, London (GB); and Matthew Charles Rowe, Milton Keynes (GB)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Nov. 3, 2023, as Appl. No. 18/501,716.
Application 18/501,716 is a continuation of application No. 18/100,458, filed on Jan. 23, 2023, granted, now 11,847,578.
Application 18/100,458 is a continuation of application No. 16/893,193, filed on Jun. 4, 2020, granted, now 11,562,267, issued on Jan. 24, 2023.
Claims priority of provisional application 62/900,537, filed on Sep. 14, 2019.
Prior Publication US 2024/0070494 A1, Feb. 29, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/00 (2019.01); G06F 7/00 (2006.01); G06F 40/40 (2020.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); H04L 51/02 (2022.01)
CPC G06N 5/04 (2013.01) [G06F 40/40 (2020.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); H04L 51/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a user device, a first input;
predicting, using a computational technique, a type of desired result based on the first input;
identifying, using metadata associated with each machine-learning-model framework of a set of machine-learning-model frameworks, one or more machine-learning-model frameworks based on the predicted type of desired result, wherein the one or more machine-learning-model frameworks are of the set of machine-learning-model frameworks;
presenting, for each machine-learning-model framework of the one or more machine-learning-model frameworks, a representation of a corresponding machine-learning-model architecture on a display, wherein one or more machine-learning-model architectures are presented;
receiving a second input identifying a selection of a particular machine-learning-model architecture of the one or more machine-learning-model architectures;
receiving a third input identifying a data source for generating a machine learning architecture;
receiving a fourth input identifying one or more constraints for the machine learning architecture;
generating code for a machine learning model based at least in part on the second input identifying the selection of the particular machine-learning-model architecture, the third input identifying the data source, and the fourth input identifying the one or more constraints; and
storing the generated code in a memory.