深度学习在运营商固网存量业务保障方面的研究及应用

Research and Application of Deep Learning in Operators' Fixed Broadband Service Guarantee

使用人工智能中的深度学习人工神经网络及机器学习决策树技术,对用户固网存量业务进行预测,并且对每个影响固网业务质量的变量进行重要度排名,以期提高运营商维系客户的效率和精准度,并且优化用户在使用固网业务时的体验。验证表明,人工智能技术在生产环境中可以帮助客服人员进行有效的客户维系。最后,因为人工智能技术在通信领域生产环境的应用属于初期阶段,还存在许多的问题需要改进,包含数据的"干净"、完整程度及建模时候的数据清洗整理难度等。

It explores the application of deep learning and machine learning technology to predict the user’s fixed broadband off-grid behavior, and ranks the importance of each variable that affects the fixed broadband quality, in order to improve the efficiency and accuracy of operators to maintain customers, and to improve user experience. Verification shows that artificial intelligence technology can help customer service to maintain the customer. Finally, because the application of artificial intelligence technology in the communication field is in its infancy, there are still many problems that need to be improved, including the"cleanness"of the data, the completeness and the difficulty of data cleaning during modeling.