Automated breakpoint creation

Patent metadata

Field	Value
Publication number	US-11176019-B2
Application number	US-202016837275-A
Country	US
Kind code	B2
Filing date	Apr 1, 2020
Priority date	Apr 1, 2020
Publication date	Nov 16, 2021
Grant date	Nov 16, 2021

Abstract

Methods, systems, and computer program products for automated breakpoint creation using machine learning are provided. Aspects include obtaining a bug report for a software and source code for the software and analyzing the bug report to determine a bug type for the bug report, where analyzing the bug report includes using a bug type labeling model. Aspects also include analyzing the source code to identify a code snippet in the source code based on the bug type, where analyzing the source code includes using a source code detection model. Aspects further include inserting a breakpoint in the source code at the code snippet.

First claim

What is claimed is:

1. A computer-implemented method for automated breakpoint creation using machine learning, the computer-implemented method comprising:
obtaining a set of closed bug reports for a software and source code for the software and an associated source code change set;
analyzing the set of closed bug reports to identify a bug type for the bug report, where analyzing the bug report includes using a bug type labeling model, wherein the bug type labeling model is a machine learning model that is trained based on a text bug description of a bug in the source code extracted from the set of closed bug reports;
analyzing the source code to identify a code snippet in the source code that matches the closest to the identified bug type based on the bug type, where analyzing the source code includes using a source code detection model, wherein the source code detection model is a machine learning model trained using the source code change set associated with the set of closed bug reports; and
automatically inserting a breakpoint in the source code at the identified code snippet to identify the code snippet to a user debugging the source code.

2. The method of claim 1 , wherein the bug type labeling model is trained using an unsupervised language model to represent bug descriptions extracted from the set of closed bug reports using feature vectors.

3. The method of claim 1 , wherein the bug type labeling model is trained using one or more clustering machine learning techniques.

4. The method of claim 1 , wherein the source code detection model is trained using deep learning machine learning techniques.

5. The method of claim 1 , wherein the source code detection model is used to assign a predicted bug type to each code snippet of the source code.

6. The method of claim 5 , wherein the source code detection model is configured to match a closest predicted bug type to the bug type.

7. The method of claim 1 , wherein the source code detection model is trained using closed issue descriptions that include a description of errors found by a developer and associated code change set that solved the errors.

8. A system for automated breakpoint creation using machine learning, the system comprising:
a processor communicatively coupled to a memory, the processor configured to:
obtain a set of closed bug reports for a software and source code for the software and an associated source code change set;

analyze the set of closed bug reports to identify a bug type for the bug report, where analyzing the bug report includes using a bug type labeling model, wherein the bug type labeling model is a machine learning model that is trained based on a text bug description of a bug in the source code extracted from the set of closed bug reports;
analyze the source code to identify a code snippet in the source code that matches the closest to the identified bug type based on the bug type, where analyzing the source code includes using a source code detection model, wherein the source code detection model is a machine learning model trained using the source code change set associated with the set of closed bug reports; and
automatically insert a breakpoint in the source code at the identified code snippet to identify the code snippet to a user debugging the source code.

9. The system of claim 8 , wherein the bug type labeling model is trained using an unsupervised language model to represent bug descriptions extracted from the set of closed bug reports using feature vectors.

10. The system of claim 8 , wherein the bug type labeling model is trained using one or more clustering machine learning techniques.

11. The system of claim 8 , wherein the source code detection model is trained using deep learning machine learning techniques.

12. The system of claim 8 , wherein the source code detection model is used to assign a predicted bug type to each code snippet of the source code.

13. The system of claim 12 , wherein the source code detection model is configured to match a closest predicted bug type to the bug type.

14. A computer program product for automated breakpoint creation using machine learning, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
obtaining a set of closed bug reports for a software and source code for the software and an associated source code change set;
analyzing the set of closed bug reports to identify a bug type for the bug report, where analyzing the bug report includes using a bug type labeling model, wherein the bug type labeling model is a machine learning model that is trained based on a text bug description of a bug in the source code extracted from the set of closed bug reports;
analyzing the source code to identify a code snippet in the source code that matches the closest to the identified bug type based on the bug type, where analyzing the source code includes using a source code detection model, wherein the source code detection model is a machine learning model trained using the source code change set associated with the set of closed bug reports; and
automatically inserting a breakpoint in the source code at the identified code snippet to identify the code snippet to a user debugging the source code.

15. The computer program product of claim 14 , wherein the bug type labeling model is trained using an unsupervised language model to represent bug descriptions extracted from the set of closed bug reports using feature vectors.

16. The computer program product of claim 14 , wherein the bug type labeling model is trained using one or more clustering machine learning techniques.

17. The computer program product of claim 14 , wherein the source code detection model is trained using deep learning machine learning techniques.

18. The computer program product of claim 14 , wherein the source code detection model is used to assign a predicted bug type to each code snippet of the source code.

Assignees

• IBM

Inventors

• Shao Liujia
• Luo Yan
• Xu Yan
• Fan Sibin

Classifications

• G06F11/3604 Primary

  Analysis of software for verifying properties of programs (testing of software G06F11/3668) · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06F18/23

  Clustering techniques · CPC title

• G06N3/082

  modifying the architecture, e.g. adding, deleting or silencing nodes or connections · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title