Neural networks to identify source code
Search elements are extracted from requirement definitions of a requirement management tool for managing a project. The search elements may be extracted using natural language processing. The search elements are used to identify source code from source code repositories. Machine learning correlates the requirement definitions to source code subject matter. The extracted source code is confirmed by a stakeholder of the requirement management tool.
1. A computer-implemented method for searching source code using definitions for requirements comprising:
extracting search elements from requirement definitions of a requirement management tool for managing a project;
matching the search elements to identify source code from source code repositories, wherein machine learning correlates the requirement definitions to source code subject matter, the matching of search elements to identify source code comprises an artificial intelligence based solution fetcher that uses a naive Bayes classifier to classify code as completely matched or semi matches to the requirement definitions in combination with a Kernel density estimation to increase the accuracy of the naive Bayes classifier; and
confirming the source code that is matching the search elements meets the requirement definitions of the requirement management tool.
2. The computer-implemented method of claim 1 , wherein the extracting search elements from the requirement definitions comprises natural language processing.
3. The computer-implemented method of claim 1 , wherein the source code repositories comprises an internal repository managed by a stakeholder that is managing the requirement management tool.
4. The computer-implemented method of claim 1 , wherein the source code repositories comprises an external open source repository having a data source that is not managed by a stakeholder that is managing the requirement management tool.
5. The computer-implemented method of claim 1 further comprising updating the requirement definitions to include a list of source code search results for the source code that matched the search elements meeting the requirement definitions of the requirement management tool.
6. The computer-implemented method of claim 3 , wherein the internal repository is updated to include the source code that matched the search elements meeting the requirement definitions of the requirement management tool.
7. The computer-implemented method of claim 1 further comprising creating an internal knowledge database including historical data illustrating the source code that matched the search elements meeting the requirement definitions of the requirement management tool, wherein the historical data contributes to training during machine learning.
8. A system for searching source code using definitions for requirements comprising:
a hardware processor; and
a memory that stores a computer program product, which, when executed by the hardware processor, causes the hardware processor to:
extract search elements from requirement definitions of a requirement management tool for managing a project;
match the search elements to identify source code from source code repositories, wherein machine learning correlates the requirement definitions to source code subject matter and the match of the search elements to identify source code comprises an artificial intelligence based solution fetcher that uses a naive Bayes classifier to classify code as completely matched or semi matches to the requirement definitions in combination with a Kernel density estimation to increase the accuracy of the naive Bayes classifier; and
confirm the source code that is matching the search elements meets the requirement definitions of the requirement management tool.
9. The system of claim 8 , wherein the extract search elements from the requirement definitions comprises natural language processing.
10. The system of claim 8 , wherein the source code repositories comprises an internal repository managed by a stakeholder that is managing the requirement management tool.
11. The system of claim 8 , wherein the source code repositories comprises an external open source repository having a data source that is not managed by a stakeholder that is managing the requirement management tool.
12. The system of claim 8 further comprising updating the requirement definitions to include a list of source code search results for the source code that matched the search elements meeting the requirement definitions of the requirement management tool.
13. The system of claim 10 , wherein the internal repository is updated to include the source code that matched the search elements meeting the requirement definitions of the requirement management tool.
14. A computer program product for searching source code using definitions for requirements comprising a computer readable storage medium having computer readable program code embodied therewith, the program instructions executable by a processor to cause the processor to:
extract, using the processor, search elements from requirement definitions of a requirement management tool for managing a project;
match, using the processor, the search elements to identify source code from source code repositories, wherein machine learning correlates the requirement definitions to source code subject matter, and the match of the search elements to identify source code comprises an artificial intelligence based solution fetcher that uses a naive Bayes classifier to classify code as completely matched or semi matches to the requirement definitions in combination with a Kernel density estimation to increase the accuracy of the naive Bayes classifier; and
confirm, using the processor, the source code that is matching the search elements meets the requirement definitions of the requirement management tool.
15. The computer program product of claim 14 , wherein the extracting search elements from the requirement definitions comprises natural language processing.