A user comment recommendation method based on code cloning technology

Abstract

A user review recommendation method based on code cloning technology, which combines code cloning technology and user review recommendation algorithm to provide reasonable and effective reviews for newly developed software or software lacking user reviews. The main process is as follows: First, collect a large amount of code clone data, use AST and Word2Vec to process the code pairs in the data set and express them as vectors, and then perform CNN model training and storage based on the vectors; secondly, collect and preprocess the data in the user comment stage. The user forms a code pair based on the code input by the plug-in and the code used for comment recommendation. The code pair is expressed as a vector using the same processing method as the code cloning stage; finally, the similarity value is predicted based on the vector and the saved CNN model, and finally the user The entered code snippets provide reasonably valid user reviews. The invention solves the problem that the application software does not have enough effective user comments, and provides more effective information for further upgrading and improvement of the software.

Description

technical field [0001] The invention belongs to the technical field of user comment recommendation methods, in particular to a user comment recommendation method based on code cloning technology, and is especially suitable for applications that use more user comments for further improvement and promotion. Background technique [0002] With the development of computer technology, the degree of informatization and intelligence of human society has become popular, and computer software as its core is widely used in the national economy and daily life. With the continuous expansion of software scale, more and more researchers have paid more and more attention to the improvement and promotion of software functions based on user reviews in recent years. Further better guidance. However, many application software do not have enough user reviews, and application software lacking user reviews will hinder the development of the field of software engineering technology. [0003] As a...

AI Technical Summary

Problems solved by technology

Although the first type of problem has been solved, the second type of challenge has not received enough attention

Many researchers are devoted to the purification of user reviews rather than expansion. In fact, not enough user reviews will seriously affect the development of developers in the technical field of improving product quality through users' real experience.

Images