摘 要：随着机器学习和深度学习方法在各个领域的发展和运用，越来越多的行业开始探索本行业的智能化发展之路，利用海量的数据，结合人工智能的优势，优化业务，如何使用海量的数据是智能化的关键。在海量的数据中，文本是一个庞大群体，不同类型的文本由于其本身结构的不同，在处理方面也有不同的策略。因此，针对移动客服对话文本的特点，文章提出了一种考虑句子结构的文本建模方法。
关键词：海量数据；智能化；建模方法
中图分类号：TP391.1 文献标识码：A 文章编号：2096-4706（2020）03-0033-03
A Text Modeling Method of Mobile Customer Service Dialogue Considering Sentence Structure
ZHONG Jian
（China Mobile Group Sichuan Co.，Ltd.，Chengdu 610041，China）
Abstract：With the development and application of machine learning and deep learning methods in various fields，more and more industries begin to explore the intelligent development of the industry，using massive data，combining the advantages of artificial intelligence，optimizing business，how to use massive data is the key to intelligent. In the massive data，text is a huge group. Different types of text have different strategies in processing because of their own structure. Therefore，according to the characteristics of mobile customer service dialogue text，this paper proposes a text modeling method considering sentence structure.
Keywords：massive data；intelligence；modeling methods
参考文献：
[1] MIKOLOV T，SUTSKEVER I，CHEN K，et al. Distributed representations of words and phrases and their compositionality [C]//Advances in neural information processing systems，2013：3111-3119.
[2] LE Q，MIKOLOV T.Distributed representations of sentences and documents [C]//International conference on machine learning，2014：1188-1196.
[3] DEVLIN J，CHANG M W，LEE K，et al. Bert：Pre-training of deep bidirectional transformers for language understanding [J].arXiv preprint arXiv：1810.04805，2018.
作者简介：钟建（1969-），男，汉族，四川成都人，高级工程师，硕士研究生，研究方向：移动网络的建设维护和优化。