{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:41:23Z","timestamp":1760146883297,"version":"build-2065373602"},"reference-count":40,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sanming University","award":["22YG11S"],"award-info":[{"award-number":["22YG11S"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This paper proposes using a web crawler to organize website content as a dialogue tree in some domains. We build an intelligent customer service agent based on this dialogue tree for general usage. The encoder-decoder architecture Seq2Seq is used to understand natural language and then modified as a bi-directional LSTM to increase the accuracy of the polysemy cases. The attention mechanism is added in the decoder to improve the problem of accuracy decreasing as the sentence grows in length. We conducted four experiments. The first is an ablation experiment demonstrating that the Seq2Seq + Bi-directional LSTM + Attention mechanism is superior to LSTM, Seq2Seq, Seq2Seq + Attention mechanism in natural language processing. Using an open-source Chinese corpus for testing, the accuracy was 82.1%, 63.4%, 69.2%, and 76.1%, respectively. The second experiment uses knowledge of the target domain to ask questions. Five thousand data from Taiwan Water Supply Company were used as the target training data, and a thousand questions that differed from the training data but related to water were used for testing. The accuracy of RasaNLU and this study were 86.4% and 87.1%, respectively. The third experiment uses knowledge from non-target domains to ask questions and compares answers from RasaNLU with the proposed neural network model. Five thousand questions were extracted as the training data, including chat databases from eight public sources such as Weibo, Tieba, Douban, and other well-known social networking sites in mainland China and PTT in Taiwan. Then, 1000 questions from the same corpus that differed from the training data for testing were extracted. The accuracy of this study was 83.2%, which is far better than RasaNLU. It is confirmed that the proposed model is more accurate in the general field. The last experiment compares this study with voice assistants like Xiao Ai, Google Assistant, Siri, and Samsung Bixby. Although this study cannot answer vague questions accurately, it is more accurate in the trained application fields.<\/jats:p>","DOI":"10.3390\/info15120818","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T07:42:18Z","timestamp":1734680538000},"page":"818","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Design and Implementation of an Intelligent Web Service Agent Based on Seq2Seq and Website Crawler"],"prefix":"10.3390","volume":"15","author":[{"given":"Mei-Hua","family":"Hsih","sequence":"first","affiliation":[{"name":"Department of Product Design, School of Arts and Design, Sanming University, Sanming 365004, China"}]},{"given":"Jian-Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"QSAN Technology, Inc., Taipei City 114, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7716-7306","authenticated-orcid":false,"given":"Chen-Chiung","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Tatung University, Taipei City 104, Taiwan"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1093\/mind\/LIX.236.433","article-title":"Computing Machinery and Intelligence","volume":"LIX","author":"Turing","year":"1950","journal-title":"Mind"},{"key":"ref_2","unstructured":"Epstein, R., Roberts, G., and Beber, G. (2009). The Anatomy of A.L.I.C.E., Springer. Parsing the Turing Test."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100659","DOI":"10.1016\/j.websem.2021.100659","article-title":"Intelligent Software Web Agents: A Gap Analysis","volume":"71","author":"Kirrane","year":"2021","journal-title":"J. Web Semant."},{"key":"ref_4","unstructured":"Mashaabi, M., Alotaibi, A., Qudaih, H., Alnashwan, R., and Al-Khalifa, H. (2022). Natural Language Processing in Customer Service: A Systematic Review. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Huang, C. (2021, January 15\u201317). The Intelligent Agent NLP-based Customer Service System. Proceedings of the 2021 2nd International Conference on Artificial Intelligence in Electronics Engineering (AIEE \u201821), Phuket, Thailand.","DOI":"10.1145\/3460268.3460275"},{"key":"ref_6","unstructured":"Winograd, T. (1971). SHRDLU, MIT. MIT AI Technical Report 235."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/365153.365168","article-title":"ELIZA\u2014A Computer Program for the Study of Natural Language Communication between Man and Machine","volume":"9","author":"Weizenbaum","year":"1966","journal-title":"Commun. ACM"},{"key":"ref_8","unstructured":"Chen, G., Liu, R., Chen, R., and Fu, C.C. (2024, January 22\u201324). A Historical Review of the Key Technologies for Enterprise Brand Impact Assessment. Proceedings of the 2024 International Conference on Applied Economics, Management Science and Social Development (AEMSS 2024), Luoyang, China."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"LeCun, Y. (2019, January 11\u201317). Deep Learning Hardware: Past, Present, and Future. Proceedings of the 2019 IEEE International Solid-State Circuits Conference\u2014(ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC.2019.8662396"},{"key":"ref_10","unstructured":"(2021, June 18). Rasa: Open Source Conversational AI\u2014Rasa. Available online: https:\/\/rasa.com."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding Structure in Time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_13","unstructured":"Sutskever, I., Vinyals, O., and Le, Q.V. (2014). Sequence to Sequence Learning with Neural Networks. arXiv."},{"key":"ref_14","unstructured":"Xiao, T., and Zhu, J. (2023). Introduction to Transformers: An NLP Perspective. arXiv."},{"key":"ref_15","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv."},{"key":"ref_16","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6\u201312). Language Models Are Few-Shot Learners. Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS \u201820), Vancouver, BC, Canada. Article 159."},{"key":"ref_17","unstructured":"AIML.com (2021, June 18). What Are the Limitations of Transformer Models?. Available online: https:\/\/aiml.com\/what-are-the-drawbacks-of-transformer-models\/."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.jnca.2004.01.001","article-title":"Learnable Topic-Specific Web Crawler","volume":"28","author":"Rungsawang","year":"2005","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_19","unstructured":"Baeza-Yates, R., and Ribeiro-Neto, B. (1999). Modern Information Retrieval, ACM Press."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1145\/324133.324140","article-title":"Authoritative Sources in a Hyperlinked Environment","volume":"46","author":"Kleinberg","year":"1999","journal-title":"J. ACM (JACM)"},{"key":"ref_21","unstructured":"Lee, T.B. (1998). Semantic Web, World Wide Web Consortium."},{"key":"ref_22","unstructured":"Kim, S.M., and Ha, Y.G. (2016, January 18\u201320). Automated Discovery of Small Business Domain Knowledge Using Web Crawling and Data Mining. Proceedings of the 2016 International Conference on Big Data and Smart Computing (BigComp), Hong Kong, China."},{"key":"ref_23","unstructured":"W3C (2021, June 18). RDF\u2014Semantic Web Standards. Available online: http:\/\/www.w3.org\/RDF\/."},{"key":"ref_24","unstructured":"W3C (2021, June 18). OWL\u2014Semantic Web Standards. Available online: http:\/\/www.w3.org\/2001\/sw\/wiki\/OWL."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100359","DOI":"10.1016\/j.dajour.2023.100359","article-title":"An Intelligent Chatbot Design and Implementation Model Using Long Short-Term Memory with Recurrent Neural Networks and Attention Mechanism","volume":"9","author":"Choudhary","year":"2023","journal-title":"Decis. Anal. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"151","DOI":"10.33693\/2313-223X-2024-11-1-151-161","article-title":"Development of a Web Application for Intelligent Analysis of Customer Reviews Using a Modified seq2seq Model with an Attention Mechanism","volume":"11","author":"Budaev","year":"2024","journal-title":"Comput. Nanotechnol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"123660","DOI":"10.1109\/ACCESS.2021.3110143","article-title":"Enhancements of Attention-Based Bidirectional LSTM for Hybrid Automatic Text Summarization","volume":"9","author":"Jiang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xie, T., Ding, W., Zhang, J., Wan, X., and Wang, J. (2023). Bi-LS-AttM: A Bidirectional LSTM and Attention Mechanism Model for Improving Image Captioning. Appl. Sci., 13.","DOI":"10.3390\/app13137916"},{"key":"ref_29","unstructured":"Su, G. (2021, June 18). Seq2seq Pay Attention to Self-Attention. 3 October 2018. Available online: https:\/\/bgg.medium.com\/seq2seq-pay-attention-to-self-attention-part-1-%E4%B8%AD%E6%96%87%E7%89%88-2714bbd92727."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., and Manning, C.D. (2015). Effective Approaches to Attention-based Neural Machine Translation. arXiv.","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Graves, A. (2012). Supervised Sequence Labelling with Recurrent Neural Networks, University of Toronto. Computer Science.","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Alfattni, G., Peek, N., and Nenadic, G. (2021). Attention-based Bidirectional Long Short-Term Memory Networks for Extracting Temporal Relationships from Clinical Discharge Summaries. J. Biomed. Inform., 123.","DOI":"10.1016\/j.jbi.2021.103915"},{"key":"ref_33","unstructured":"Wikipedia (2021, June 18). Depth-First-Search. Available online: https:\/\/zh.wikipedia.org\/wiki\/Depth-First-Search."},{"key":"ref_34","unstructured":"Wikipedia (2021, June 18). Dialogue Tree. Available online: https:\/\/en.wikipedia.org\/wiki\/Dialogue_tree."},{"key":"ref_35","unstructured":"Borges, J.L. (2018). Garden of Forking Paths, Penguin Books."},{"key":"ref_36","unstructured":"(2021, June 18). Taiwan Water Company, Available online: https:\/\/www.water.gov.tw\/mp.aspx?mp=1."},{"key":"ref_37","unstructured":"(2021, June 18). Introduction to Rasa Open Source & Rasa Pro, RasaNLU. Available online: https:\/\/rasa.com\/docs\/rasa\/nlu-training-data\/."},{"key":"ref_38","unstructured":"GitHub (2021, June 18). Chinese_Chatbot_Corpus. Available online: https:\/\/github.com\/codemayq\/chinese_chatbot_corpus."},{"key":"ref_39","unstructured":"(2021, June 18). GitHub. Seq2Seq. Available online: https:\/\/github.com\/google\/seq2seq."},{"key":"ref_40","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2021, June 18). Attention Is All You Need. Cornell University, 16 December 2017. Available online: https:\/\/arxiv.org\/pdf\/1706.03762.pdf."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/12\/818\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:56:13Z","timestamp":1760115373000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/12\/818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["info15120818"],"URL":"https:\/\/doi.org\/10.3390\/info15120818","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2024,12,20]]}}}