Advertisement

A Chatbot Design Method Using Combined Model for Business Promotion

  • Jie Zhang
  • Hao HuangEmail author
  • Guan GuiEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 517)

Abstract

The combination of commercial development and artificial intelligence services becomes more and more important. Chatbot is considered one of the effective techniques by using information retrieval (IR) and natural language processing (NLP). In this paper, we collect a series of business-promoted chat data and conduct a series of cleanup and classification of these data sets. Since the speech of different people is random, the similarity is calculated by using a combination of the retrieval model and the generated model, and then the final answer is generated using long-short term memory (LSTM) training and prediction. Finally, we use the TF-IDF weighting method to improve the dialog. Experimental results show that the proposed method can communicate with humans and answer real-time questions.

Keywords

Chatbot NLP LSTM TF-IDF 

References

  1. 1.
    Vargas-Vera, M., Lytras, M.D.: AQUA: hybrid architecture for question answering services. IET Softw. 4(6), 418–433 (2010)CrossRefGoogle Scholar
  2. 2.
    Abdul-kader, S.A.: Question answer system for online feedable new born chatbot. In: 2017 Intelligent Systems Conference (IntelliSys), pp. 863–869 (2017)Google Scholar
  3. 3.
    Su, M.-H., Wu, C.-H., Huang, K.-Y., Hong, Q.-B., Wang, H.-M.: A chatbot using LSTM-based multi-layer embedding for elderly care. In: 2017 International Conference on Orange Technologies (ICOT), pp. 70–74 (2017)Google Scholar
  4. 4.
    Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2042–2050 (2014)Google Scholar
  5. 5.
    Quarteroni, S., Manandhar, S.: Designing an interactive open-domain question answering system. Nat. Lang. Eng. 15(1), 73–95 (2009)CrossRefGoogle Scholar
  6. 6.
    Grangier, D., Keshet, J., Bengio, S.: Discriminative keyword spotting. Speech Commun. 51(4), 317–329 (2009)CrossRefGoogle Scholar
  7. 7.
    Spärck Jones, K.: A statistical interpretation of term specificity and its retrieval. J. Doc. 28(1), 11–21 (1972)Google Scholar
  8. 8.
    Guo, A., Yang, T.: Research and improvement of feature words weight based on TFIDF algorithm. In: Proceedings of 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2016), pp. 415–419 (2016)Google Scholar
  9. 9.
    Hochreiter, S., Schmidhuber, J.J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  10. 10.
    Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764–1772 (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.College of Telecommunication and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations