Automatic program correction method based on knowledge graph

Abstract

The invention discloses an automatic program correction method based on a knowledge graph, and the method comprises the following steps: S1, obtaining an open source code on a network, carrying out the analysis of the obtained source code through a code knowledge graph construction program, and generating a code knowledge graph; s2, writing a skeleton program which allows missing or errors to occur; and S3, analyzing the skeleton program through a code completion program, and correcting and supplementing the skeleton program by utilizing the code knowledge graph to obtain a normally executed complete program. According to the invention, a defective skeleton program can be automatically trimmed to obtain a complete program, and the method has the characteristics of simplifying programming,improving programming efficiency and reducing manual labor amount.

Description

technical field [0001] The present invention relates to a method for automatically correcting programs, in particular to a method for automatically correcting programs based on knowledge graphs. Background technique [0002] At present, the automation development technology of program design is changing from the original componentized and model-driven method to the deep learning-based and semantic-driven method. At present, there are already existing methods for generating required program fragments through natural language processing. However, these methods require large-scale computing support of neural networks, and there is no unified standard. The logical structure, construction methods, and automated practical applications of code knowledge graphs are not It has not been solved well, and it cannot provide a complete programming method. Programmers need to be very rigorous when writing programs, and there must be no gaps or mistakes. Amendment, programming is complex, ...

AI Technical Summary

Problems solved by technology

At present, there are already existing methods for generating required program fragments through natural language processing. However, these methods require large-scale computing support of neural networks, and there is no unified standard. The logical structure, construction methods, and automated practical applications of code knowledge graphs are not It has not been solved well, and it cannot provide a complete programming method. Programmers need to be very rigorous when writing programs, and there must be no gaps or mistakes. Correction, programming is complicated, cumbersome, inefficient, and labor-intensive

[0003] Therefore, the existing program processing has the problems of complex writing, low efficiency, and large amount of manual labor.

Images