A method of automatic program correction based on knowledge graph

Abstract

The invention discloses a method for automatically correcting a program based on a knowledge graph, which includes the following steps: S1. Obtain open source code on the network, analyze the acquired source code through a code knowledge graph construction program, and generate a code knowledge graph; S2 . Write a skeleton program that allows missing or errors; S3. Analyze the skeleton program through the code completion program, use the code knowledge graph to correct and supplement the skeleton program, and obtain a complete program that is normally executed. The invention can automatically trim problematic skeleton programs to obtain complete programs, and has the characteristics of simplifying program writing, improving program writing efficiency and reducing manual labor.

Description

technical field [0001] The invention relates to an automatic program correction method, in particular to a program automatic correction method based on a knowledge map. Background technique [0002] At present, the automatic development technology of program design is changing from the original component-based, model-driven method to the deep learning-based, semantic-driven method. At present, there are existing methods to generate the required program fragments through natural language processing. However, these methods require the large-scale computing support of neural networks, and there is no unified standard. The logical structure, construction method and automated practical application of the code knowledge graph are not It has not been well solved, and can not provide a complete programming method. Programmers need to be very rigorous when writing programs, and there must be no defects and errors. Once there is a problem in writing the program, it cannot run normally...

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