Machine Learning-Assisted Code Generation in Directed Acyclic Graph-Driven Notebook Environment

An application receives, in a code cell connected to a plurality of cells in a graph structure, a natural language command to generate code. The application determines, using directed edges of the graph structure, a set of precedent cells from which the code cell depends. The application inputs into...

Full description

Saved in:
Bibliographic Details
Main Authors McCardel, Barry Ryan, Colgrove, Caitlin Royden, Bischof, Bryan Edward, Storr, Adam Joseph, Lorince, Jared, Miller, Isidore
Format Patent
LanguageEnglish
Published 01.08.2024
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An application receives, in a code cell connected to a plurality of cells in a graph structure, a natural language command to generate code. The application determines, using directed edges of the graph structure, a set of precedent cells from which the code cell depends. The application inputs into a machine learning model the natural language command and values from the set of precedent cells pertaining to the code, and receives, as output from the machine learning model, generated code. The application updates the code cell to include the generated code.
Bibliography:Application Number: US202418426098