Patent · US Active

Pull request risk prediction for bug-introducing changes

US11645188B1 · kind B1 · utility

1Cited by

7References

20Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Amar Prakash Azad · Bengaluru, IN
Harshit Kumar · Delhi, IN
Raghav Batta · Ossining, US
Michael Elton Nidd · Zürich, CH
Larisa Shwartz · Scarsdale, US
Pritam S. Gundecha · San Jose, US
Alberto Giammaria · Austin, US

Key dates

Filing date	Nov 16, 2021
Grant date	May 9, 2023
Priority date	—
Expiry date	Nov 16, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06F11/3608
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

In an approach to risk prediction for bug-introducing changes, a computer retrieves one or more historic pull requests. A computer determines a unique file linking for each file included in the historic pull requests. A computer generates a file risk dataset. A computer performs chronological partitioning on the file risk dataset. A computer determines bug-introducing changes in the file risk dataset. A computer computes a collaborative file association between two or more of the files in the file risk dataset. A computer labels each of the files in the file risk dataset with an associated risk of introducing a bug. A computer generates a labelled file risk inducing ground truth dataset. A computer inputs the labelled file risk inducing ground truth dataset to a file risk prediction model. A computer extracts pull request features from the historic pull requests. A computer generates a pull request risk prediction model.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.