API information retrieval method for natural language form and based on lecture note and Stack Overflow

Abstract

The invention belongs to the field of information retrieval, and discloses an API information retrieval method for natural language form and based on lecture notes and Stack Overflow. The method comprises: constructing an API-KI library of API and knowledge items and performing extraction, the API-KI library comprising API and lecture segment API-segment pairs, API and question and answer sheet API-Q&A pairs; analyzing the questions in the natural language form, and obtaining potential APIs corresponding to the questions; identifying related API-KI using a relative identification mode TDML; performing potential APIs with related API-KI pair to generate a candidate list, carrying out descending sorting on the candidate list according to a sorting strategy, and finally returning the sorted API-KI list as a question answer. According to the retrieval method provided by the invention, information of API lecture and SO is integrated, the retrieval precision is effectively improved, and moreuseful API related knowledge can be provided for developers.

Description

technical field [0001] The invention belongs to the field of information retrieval, and in particular relates to an API information retrieval method based on handouts and Stack Overflow oriented to natural language. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] Most of the existing methods are based on full-text search, such as using the VSM-based Lucene full-text search engine package to search and match keywords directly in the document library based on natural language questions, and using the neural network-based Word2Vec word vector model can be very good The contextual relationship between words is mined, so the question and the document can be represented by word vectors, and then the results can be returned according to the similarity between the two. In addition, the CK method uses the conceptual knowledge of the software field in the source code to recommend API-related documents by extra...

AI Technical Summary

Problems solved by technology

Not only is the retrieval method inefficient, but processing the two types of data separately may return irrelevant results

[0009] (2) The existing methods do not dig deep into the information of the semantic layer of the question, and the method based on keyword matching is likely to cause the loss of a large amount of useful information, which eventually leads to the loss of retrieval accuracy

Especially in the form of natural language, the question may not directly contain the API name, and the meth

Images