Artificial Intelligence for Communications and Networks. Second EAI International Conference, AICON 2020, Virtual Event, December 19-20, 2020, Proceedings

Research Article

An OOV Recognition Based Approach to Detecting Sensitive Information in Dialogue Texts of Electric Power Customer Services

Download
81 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-69066-3_52,
        author={Xiao Liang and Ningyu An and Ning Wu and Yunfeng Zou and Lijiao Zhao},
        title={An OOV Recognition Based Approach to Detecting Sensitive Information in Dialogue Texts of Electric Power Customer Services},
        proceedings={Artificial Intelligence for Communications and Networks. Second EAI International Conference, AICON 2020, Virtual Event, December 19-20, 2020, Proceedings},
        proceedings_a={AICON},
        year={2021},
        month={7},
        keywords={Out-of-vocabulary Sensitive word recognition HowNet Word embedding Electric power customer services},
        doi={10.1007/978-3-030-69066-3_52}
    }
    
  • Xiao Liang
    Ningyu An
    Ning Wu
    Yunfeng Zou
    Lijiao Zhao
    Year: 2021
    An OOV Recognition Based Approach to Detecting Sensitive Information in Dialogue Texts of Electric Power Customer Services
    AICON
    Springer
    DOI: 10.1007/978-3-030-69066-3_52
Xiao Liang1, Ningyu An1, Ning Wu2, Yunfeng Zou2, Lijiao Zhao1
  • 1: Global Energy Interconnection Research Institute Co. Ltd., Artificial Intelligence on Electric Power System State Grid Corporation Joint Laboratory (GEIRI)
  • 2: State Grid Jiangsu Electric Power Co., Ltd. Marketing Service Center

Abstract

Sensitive word recognition technology is of great significance to the protection of enterprise privacy data. In electric power custom services systems, the dialogue texts recording the conversational information between electric power customers and the customer services staffs contain some sensitive information of electric power customers. However, the colloquialism and synonyms in dialogue texts often make sensitive information recognition more difficult. In this paper, we proposed an out-of-vocabulary (OOV) approach for recognizing sensitive words in the dialogue texts of electric power customer services. We combine the semantic similarity based on word embeddings and structural semantic similarity based on HowNet for recognizing sensitive OOV words in the dialogue texts. The related experiments were made, and the experimental results show that our method has higher recognition accuracy in comparison with the popular approaches.