US 11,934,298 B2
Defect prediction operation
Ahmedali Durga, Vadodara (IN); and Saket Gurukar, Yavatmal (IN)
Assigned to DevFactory FZ-LLC, Dubai Media (AE)
Filed by DevFactory FZ-LLC, Dubai (AE)
Filed on Jul. 1, 2021, as Appl. No. 17/365,145.
Application 17/365,145 is a continuation of application No. 15/463,071, filed on Mar. 20, 2017, granted, now 11,086,761.
Prior Publication US 2021/0349809 A1, Nov. 11, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/36 (2006.01); G06F 11/00 (2006.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01)
CPC G06F 11/3668 (2013.01) [G06F 11/008 (2013.01); G06F 11/3604 (2013.01); G06F 11/3616 (2013.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01)] 9 Claims
OG exemplary drawing
 
1. A computer-implementable method for predicting a defect within a computer program comprising:
accessing a code base of the computer program, the code base of the computer program comprising a plurality of computer program files;
analyzing a commit of the computer program to identity a risk value of a likelihood of a defect occurrence within each of the plurality of files of the computer program; and
calculating a defect prediction metric for each of the plurality of computer programs, the defect prediction metric providing an objective measure of defect prediction for a plurality of files of the computer program, wherein calculating the defect prediction metric comprises:
correlating the risk value with a time at which the defect occurrence is likely to appear with an exponential decay function to generate the defect prediction metric, wherein the risk value is a value within a range of risk values, a low risk value is at least 10 times lower than a high risk value, each of the risk values is calculated using the decay function and based on a commit time of each computer program, each of the risk values is linked to one of a set of particular times of a next defect of the computer program associated with the risk value, and the linkage of each of the risk values to the particular times correlates to the decay function; and
providing the defect prediction metric for use in mitigating risk associated with the defect predictions for the computer program.