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...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Patent |
Language | English |
Published |
01.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |