ABSTRACT
The power grid enterprise has established various electronic service channels to provide better services to the electric power customers, whose online requests are handled by the customer service personnel. The paper proposes the design of the intelligent robot of online customer services by adopting a variety of mature artificial intelligence technologies to enable more convenient and better service experience to the customers. The functional design of the intelligent robot engine is described first with business guidance rule management, engine support, knowledge graph support, service channel support, and operation management support, which could be the essential component of the collaborative channel management platform in the online channel management system. The working mechanism of the intelligent robot engine is elaborated, where the workflow is illustrated to provide the automatic online customer service and the corresponding business guidance rules are described, taking the ones for the electricity quantity inquiry as example. The electric power knowledge graph is established to locate the keywords of the electric power business consultation in the business request from the customers where the deep bidirectional LSTM-CRF model is adopted with word embeddings. The advantages of the intelligent robot engine are analyzed respectively from perspectives of the customers, the personnel and the power grid enterprise, the key points of developing and improving the engine in the future are finally discussed.
- Lin, H., Fang, X. M., Yuan, B., Ouyang, H., 2019. Research and design of business platform strategy for multi-channel customer services in internet of things in electricity. Distribution & Utilization, 6, pp 39--45.Google Scholar
- Zhao, G. D, Zhang, C. J., Ouyang, H., Hong, Y., 2019. Research on architecture design of multi-channel operation support platform based on business middle platform. Distribution & Utilization, 6, pp 67--71.Google Scholar
- Pu, X. C., 2013. Electric power marketing business and management. Electric Power Press.Google Scholar
- Liu, Q., 2015. Power market marketing management (3rd Edition). Electric Power Press.Google Scholar
- Qiu, T. Q., 2018. Internet plus power marketing service. Shanghai University of Finance and Economics Press.Google Scholar
- Tang, W. S., Ouyang, H., Liu, Y. X., Wang, F. E., 2014. Design and implementation of electric power marketing general data platform based on IEC61970/61968. Electric Power Information and Communication Technology, 10, pp 89--94.Google Scholar
- Lin, H., Zhao, J. K., Jiao, Y., Cao, J., Ouyang, H., Fang, H. W., Yuan, B., 2017. Research on building an innovative electric power marketing business application system based on cloud computing and microservices architecture technologies. IEEE 2nd International Conference on Cloud Computing and Big Data Analysis, pp 246--253.Google Scholar
- Han, X. P., Liu, K., Hou, L., 2018. Knowledge graph development report. Language and Knowledge Computing of Chinese Information Processing Society of China.Google Scholar
- Eddy, S. R., 1996. Hidden markov models. Current opinion in structural biology, 6 (3), pp 361--365.Google Scholar
- Kapur, J. N., 1989. Maximum-entropy models in science and engineering. John Wiley & Sons.Google Scholar
- Lafferty, J., McCallum, A., Pereira, F. C. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proceedings of International Conference on Machine Learning, pp 282--289.Google ScholarDigital Library
- Huang, Z., Xu, W., Yu, K., 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv:1508.01991.Google Scholar
- Lample, G., Ballesteros, M., Subramanian, S., 2016. Neural Architectures for Named Entity Recognition. Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 260--270.Google ScholarCross Ref
- Chiu, J. P., Nichols, E., 2016. Named entity recognition with bidirectional lstm-cnns. Transactions of the Association for Computational Linguistics, pp 357--370.Google ScholarCross Ref
- Zhai, F., Potdar, S., Xiang, B., Zhou, B., 2017. Neural models for sequence chunking. Proceedings of Association for the Advance of Artificial Intelligence, pp 3365--3371.Google ScholarCross Ref
- Mikolov, T., Chen, K., Corrado, G., Dean, J., 2013. Efficient estimation of word representations in vector space. Proceedings of the International Conference on Learning Representations, pp 1--12.Google Scholar
- Word2vec, https://code.google.com/archive/p/word2vec/Google Scholar
- Goodfellow, I., Bengio, Y., Courville, A., 2017. Deep Learning. People's Post and Telecommunications Press, pp 248--250.Google Scholar
- Zheng, S., Wang, F., Bao, H., Hao, Y., Zhou, P., Xu, B., 2017. Joint extraction of entities and relations based on a novel tagging scheme. Proceedings of Association for Computational Linguistics, pp 1227--1236.Google ScholarCross Ref
- Zhou, P., Zheng, S., Xu, J., Qi, Z., Bao, H., Xu, B., 2017. Joint extraction of multiple relations and entities by using a hybrid neural network. Proceedings of Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, Springer, pp 135--146.Google ScholarCross Ref
- Devlin, J., Chang, M. W., Lee, K., Toutanova, K., 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805.Google Scholar
- Yang, Z. L., Dai, Z. H., Yang, Y. M., Carbonell, J., Salakhutdinov, R., 2019. XLNet: Generalized autoregressive pretraining for language understanding. arXiv:1906.08237.Google Scholar
Index Terms
- Research on Intelligent Robot Engine of Electric Power Online Customer Services Based on Knowledge Graph
Recommendations
Addressing the What and How of Online Services: Positioning Supporting-Services Functionality and Service Quality for Business-to-Consumer Success
With the continued growth of business-to-consumer (B2C) e-business, online vendors are providing an increasing array of services that support and enhance their core products or services. For example, Amazon.com does not just sell books; it also enhances ...
On the role of knowledge graphs in explainable AI
The current hype of Artificial Intelligence (AI) mostly refers to the success of machine learning and its sub-domain of deep learning. However, AI is also about other areas, such as Knowledge Representation and Reasoning, or Distributed AI, i.e., areas ...
Knowledge Graph Construction and Intelligent Application Based on Enterprise-level Big Data of Nuclear Power Industry
AbstractThis paper is based on the needs of nuclear power business, combined with big data processing, deep learning, natural language processing and other related technologies and algorithms to design an intelligent architecture. This architecture ...
Comments