摘要
本文介绍了工单文本分类的理论和应用,并对文本分析的分词、机器学习、深度学习等技术方法进行了描述。基于预训练BERT模型提出了95598客服工单自动分类的方法,设计了电力客服工单自动分类的流程,最后通过一个实际的案例对算法模型进行校验,并与传统的文本挖掘方法进行了对比。算例的结果表明,所使用的工单分类算法能显著提高分类的准确性,在分类效率上也较高。
This paper introduces the theory and application of the text classification of work orders.Describes technical methods such as word segmentation,machine learning,deep learning,etc.Method of automatic classification of 95598 work orders based on pre-trained BERT model.Finally,the model is compared with multiple traditional text classification models in an example.Results indicate that the proposed defect text classification model can significantly increase accuracy with considerable efficiency.
作者
任莹
Ren Ying(Kunming Enersun Technology Co.Ltd,Kunming 650217)
出处
《云南电力技术》
2020年第1期2-7,11,共7页
Yunnan Electric Power