A template-based software defect automatic question and answer method

Abstract

The invention discloses a template-based software defect automatic question and answer method, and belongs to the field of software maintenance, and the method comprises the steps: firstly, extractingan entity relationship triple from a bug corpus, and obtaining a natural language mode; Then determining an entity relationship in the triple; Acquiring a query template corresponding to the naturallanguage mode; Replacing an entity in the question q proposed by the user with an entity type to obtain a question q '; Comparing and searching the entity type in the q'with the entity type in the natural language mode, and calculating the similarity; Obtaining an SPARQL query mode of the question q according to the similarity and the entity in the question q; And finally, searching and executingthe SPARQL query mode of the question q on the entity relation graph constructed by the bug report, thereby obtaining the answer of the question q. According to the method, natural language semantic understanding is carried out through the template, the understanding effect is good, template matching is carried out based on the entity type, the search space is greatly reduced, and the efficiency of software defect automatic question answering is improved.

Description

technical field [0001] The invention belongs to the field of software maintenance, in particular to a template-based automatic question answering method for software defects. Background technique [0002] In order to solve some new software defects they encounter, software developers and maintainers usually need to use search engines and software defect libraries to answer questions about software defect-related information. However, search engines generally express retrieval needs with the combination logic of keywords, and users’ retrieval needs are often complex and special. Search engines cannot understand user intentions in detail and accurately, and naturally cannot retrieve answers that satisfy users. Moreover, most of these software defect databases use traditional relational database-based search methods. Although the search results contain a large amount of information and attributes of software defects, these information and attributes are often not very relevant ...

AI Technical Summary

Problems solved by technology

However, search engines generally express retrieval requirements with the combination logic of keywords, and users’ retrieval requirements are often complex and special. Search engines cannot understand user intentions in detail and accurately, and naturally cannot retrieve answers that satisfy users.

Moreover, most of these software defect databases use traditional relational database-based search methods. Although the search results contain a large amount of information and attributes of software defects, these information and attributes are often not very relevant to the problems you want to know. , cannot help itself well to fix new software bugs

In addition, the search method of software defect information in search engines and software defect databases is to directly use keyword matching technology, which has a large search space and is very time-consuming, and the search results obtained only by keyword retrieval are not accurate.

This question-and-answer method makes it difficult for searchers to find the information they really need, which is time-consuming and labor-intensive.

Images