| 基于Word2Vec和决策树的故障定位技术 |
| |
| 引用本文： | 王露露,陈军华. 基于Word2Vec和决策树的故障定位技术[J]. 上海师范大学学报(自然科学版), 2024, 53(2): 223-227 |
| |
| 作者姓名： | 王露露 陈军华 |
| |
| 作者单位： | 上海师范大学 信息与机电工程学院, 上海 201418 |
| |
| 摘 要： | 利用Word2Vec方法对Java源代码进行深层语义编码,生成文件级和行级的语义向量,并将其用作输入数据来训练决策树模型,以实现精确的文件级别和行级别故障定位,优化故障检测过程,构建一个综合文件级别与行级别分析的高效故障定位框架. 实验结果表明：该模型在各项目中的故障定位准确率均高于83%.
|
| 关 键 词： | 故障定位 语义表示 Word2Vec 决策树 |
| 收稿时间： | 2023-12-25 |
Fault location technology based on Word2Vec and decision tree |
| |
| WANG Lulu,CHEN Junhua. Fault location technology based on Word2Vec and decision tree[J]. Journal of Shanghai Normal University(Natural Sciences), 2024, 53(2): 223-227 |
| |
| Authors: | WANG Lulu CHEN Junhua |
| |
| Affiliation: | College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China |
| |
| Abstract: | Word2Vec technology was utilized to perform deep semantic encoding on Java source code, generating file-level and line-level semantic vectors. These vectors were used as input data to train the decision tree model, aiming to achieve precise file-level and line-level fault location and to optimize the fault detection process. An efficient fault localization framework was constructed by this method which integrated file-level and line-level analysis. The experimental results showed that the fault localization accuracy of the model in all projects was higher than 83%. |
| |
| Keywords: | fault location semantic representation Word2Vec decision tree |
|
| 点击此处可从《上海师范大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《上海师范大学学报(自然科学版)》下载免费的PDF全文 |
