Research On Multi-source Information Fusion Based Api Knowledge Graph Construction And Application

API(Application Programming Interface)plays a very important role in software development.A survey shows that 87%of developers often use APIs to solve different programming problems.In order to find an effective API,94%of developers often use the API reference documents Q&A websites,forums and etc.to obtain relevant knowledge.However,this method is not accurate,and developers need to further filter useful API knowledge from the search results.API-related knowledge is usually scattered among multiple information sources,such as API reference documentation,Q&A forum and other unstructured texts that contain API-related knowledge,which is not conducive to API query and retrieval.However,most of the existing API knowledge graph construction uses a single information source,and it is difficult to ensure the completeness and accuracy of the retrieved API knowledge.To this end,this paper proposes an API knowledge graph construction method based on multi-source information fusion to improve the efficiency of API retrieval.API reference documentation describes the function and structure of the API from the designer's perspective,while Stack Overflow provides the purpose and use scenarios of the API from user's perspective.API reference documentation and Stack Overflow complement each other,and they can provide support for API query and retrieval together.By analyzing API reference documentation,API entities and domain concepts entities can be extracted,and their relationships can be constructed.By using Stack Overflow website,Q&A entities and API concepts entities can be extracted and their relationships between them can be constructed.On this basis,these two kinds of information are fused to construct a multi-source API knowledge graph to realize API recommendation based on knowledge graph.To verify the method in this paper,the API knowledge graph constructed in this paper is evaluated from two aspects:the accuracy of knowledge extraction and the effectiveness of recommended applications.The experimental results show that API recommendation based on multisource information fusion improves the effectiveness and efficiency of API recommendation.