跳到主要內容

臺灣博碩士論文加值系統

(100.28.227.63) 您好!臺灣時間:2024/06/22 00:20
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:郭冠廷
研究生(外文):KUO,KUAN-TING
論文名稱:智慧語音自動受理服務及配置系統
論文名稱(外文):Intelligent voice automatic acceptance service and deployment system
指導教授:游正義林正堅林正堅引用關係
指導教授(外文):YU,CHENG-YILIN,CHENG-JIAN
口試委員:陳政宏洪士程
口試委員(外文):CHEN,CHENG-HUNGHORNG,SHIH-CHENG
口試日期:2020-07-16
學位類別:碩士
校院名稱:國立勤益科技大學
系所名稱:資訊工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:42
中文關鍵詞:自然語言分析語音辨識語音客服長短期記憶關鍵字提取分類
外文關鍵詞:The natural language analysisThe pronunciation identificationThe pronunciation guest takeThe long short-term memoryThe key words extractionThe classification
相關次數:
  • 被引用被引用:0
  • 點閱點閱:134
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著資訊通訊技術的持續發展,電話通訊服務從已往的人工接聽客戶服務到現在的互動式語音應答(Interactive Voice Response, IVR),現今已被廣泛地應用在各行各業,如金融、電信、電商、公共事業…等,電話通訊服務的應用已經是不可取代。
在本研究中針對消防救災救護中人員報案輔助案件分析的方式開發出了一套智慧語音自動受理服務及配置系統,採用自然語言處理技術 (Natural Language Processing, NLP),對消防報案的語音內容透過Google語音辨識引擎轉化為文字資訊,並將文字資訊以前處理的方式進行語意分析、斷詞、詞性標記、關鍵字提取來找出重要特徵,再運用長短期記憶模型 (long short-term memory, LSTM)對關鍵字進行決策分析,最後系統將依決策分析的結果來配置消防案件的類別及出勤車輛,並傳遞訊息告知受理救災救護的執勤員以達到輔助之效果。
實驗中使用了混和矩陣的方式來驗證系統中語音辨識及語音分析的準確率,由計算後的結果可以知道準確率的結果均在90%左右。

Along with the news communication technology continually development, the telephone communication service serves from the previously artificial answering customer to the present interaction type pronunciation reply (Interactive Voice Response, IVR), nowadays widely has been applied in all the various trades and occupations, like the finance, the telecommunication, electricity business, the non-profit organization and so on, the telephone communication service application already might not substitute.
Rescued the personnel in this research in view of the fire disaster relief to report the way which the assistance case analyzed to develop a set of wisdom pronunciation to accept the service and the disposition system automatically, the way which used the natural language processing technology (Natural Language Processing, NLP) the pronunciation content which reported to the fire prevention penetrates the Google pronunciation identification engine to transform as the writing information, the system writing information before processes carries on again the meaning analysis, breaks the word, the lexical category mark, the key words extraction discovers the important characteristic, again utilized the long short-term memory model (long short-term memory, LSTM) carries on the decision analysis to the key words, the final system will depend on the decision analysis the result to dispose the fire case the category and the going out on duty vehiclesAnd transmits the news impartation to accept the disaster relief to rescue performs duties to achieve effect of the assistance.
In the experiment used the blending matrix way to confirm in the system the pronunciation identification and the analysis of speech sound rate of accuracy, might know the rate of accuracy after the computation result the result about 90%.

摘要 I
Abstract II
致謝 IV
目錄 V
圖目錄 VII
表目錄 VIII
第一章 緒論 1
1.1 研究動機 1
1.2 文獻探討 2
第二章 研究方法 8
2.1 研究說明 8
2.2 語音來源整合系統 10
2.3 自動接聽語音辨識系統 15
2.4 建構關鍵字自動提取與任務分類演算法 23
2.5 服務分配系統 33
第三章 實驗結果 35
第四章 結論與未來工作 38
參考文獻 39

[1]Rebecca W, Boren MSE, William C, and Moor PhD, “Integrating computers and telephones: Problems and possible solutions,” Computers & Industrial Engineering, Vol. 29, pp. 119-123, September 1995.
[2]Schroder. N, and Hruschka. H, ‘‘Investigating the effects of mailing variables and endogeneity on mailing decisions,’’ European Journal of Operational Research, Vol. 250, pp. 579–589, April 2016.
[3]Admas. D. A, Todd. P. A, and Nelson. R. R, ‘‘A comparative evaluation of the impact of electronic and voice mail on organizational communication,’’ Information & Management, Vol. 24, pp. 9–21, January 1993.
[4]Medhi. D, and Ramasamy. K, “Chapter 26 - VoIP Call Routing, ” Network Routing (Second edition), pp. 866-896, 2019.
[5]Schiller. S. Z, “CHAT for chat: Mediated learning in online chat virtual reference service,” Computers in Human Behavior, Vol. 65, pp. 651-665, December 2016.
[6]Wei. J. Seedorf. S, Lowry. P. B, Thum. C, and Schulz. T, ‘‘How increased social presence through co-browsing influences user engagement in collaborative online shopping,’’ Electronic Commerce Research and Applications, pp. 84–99, July–August 2017.
[7]Pozza. I. D, Goetz.O, and Sahut. J. M, ‘‘Implementation effects in the relationship between CRM and its performance,’’ Journal of Business Research, Vol. 89, pp. 391–403 August 2018.
[8]William Cohen, ‘‘Learning Rules that Classify E-Mail,’’ AAAI Spring Symposium on Machine Learning in Information Access, 1996.
[9]Rennie. J, "Automated E-mail Filtering", Special Interest Group on Data Mining and Knowledge Discovery, 2000.
[10]Reichheld, F. F, and Sasser, W. E, "Zero Defections: Quality Comes to Service", Harvard Business Review, pp.105-111, September-October, 1990.
[11]Cooper. E, "Improving FAQfinder's Performance: Setting Parameters by Genetic Programming", AAAI Spring Symposium on MLIA Technical Papers, 1996.
[12]M.Y. Li, and Judy C.R. Tseng, ‘‘Development of an Intelligent Network-based Customer Service System, ’’ 2001 Taiwan Academic Network Conference (TANET2001), pp. 24–26, October 2001.
[13]Kankanhalli. A, Charalabidis. Y, and Mellouli. S, ‘‘IoT and AI for Smart Government: A Research Agenda,’’ Government Information Quarterly, Vol. 36, pp. 304–309, April 2019.
[14]Wason. R, ‘‘Deep learning: Evolution and expansion,’’ Cognitive Systems Research, Vol. 52, pp. 701–708 December 2018.
[15]He. P, Zhang. S, and He. C, ‘‘Impacts of logistics resource sharing on B2C E-commerce companies and customers,’’ Electronic Commerce Research and Applications, Vol. 34, March–April 2019, 100820.
[16]Siamagka. N. T, Christodoulides. G, Michaelidou. N, and Valai. A, ‘‘Determinants of social media adoption by B2B organizations,’’ Industrial Marketing Management, Vol. 51, pp. 89–99, November 2015.
[17]Takeuchi. H, Masuda. S, Miyamoto. K, and Akihara. S, ‘‘Obtaining Exhaustive Answer Set for Q&A-based Inquiry System using Customer Behavior and Service Function Modeling,’’ Procedia Computer Science, Vol. 126, pp. 986–995, 2018.
[18]G. S. Kumar and G. Zayaraz, ‘‘Concept relation extraction using Naïve Bayes classifier for ontology-based question answering systems,’’ Computer and Information Sciences, vol.27, pp.13-24, January 2015.
[19]A. Mohasseb, M. b- El-Den and M. cocea, ‘‘Information Retrieval System and Machine Translation: A Review,’’ Question categorization and classification using grammar based approach,’’ Information Processing & Management, Vol.29, May 2018.
[20]K. F. McCoy, J. L. Arnott, L. Ferres, M-Oken and B. Roark, ‘‘Speech and Language processing as assistive technologies,’’ Computer Speech & Language, vol.27, PP.1143-1146, September 2013.
[21]Hochreiter. S, and Schmidhuber. J, ‘‘Long Short Term Memory, ’’ Neural computation, pp1735-1780, 1997.
[22]S. C. Kleen,"Representation of Events in Nerve Nets and Finite Automata," In C. E. Shannon & J. McCarthy (Eds.), pp.3-41, 1956.
[23]K. Thompson, "Regular Expression Search Algorithm," Communications of the ACM, pp.419-422, Jun.1968.
[24]F. Bodon and L. Ronyai," Trie: an alternative data structure for data mining algorithms, "Computers and Mathematics Institute, pp.739-751, 2003.
[25]Y. Cai, K. L. Judd, G. Thain and S. J. Wright, “SOLVING DYNAMIC PROGRAMMING PROBLEMS ON A COMPUTATIONALGRID,” Computational Economics, vol.45, pp,261-284, Feb.2014.
[26]R. Mihalcea and P. Tarau, "TextRank: Bringing Order into Text," In Proceed-ings of the 20st International Conferenceon Computational Linguis-tics, July.2004.
[27]S. Lai, L. Xu, K. Liu and J. Zhao, "Recurrent Convolutional Neural Networks for Text Classification", Association for the Advancement of Artificial Intelligence, pp.2267-2273, Jan.2015.
[28]T. Mikolov, K. Chen, G. Corrado and J. Dean, "Efficient Estimation of Word Representations in Vector Space," Computation and Language, pp.1-12, Jan.2013.
[29]T. Mikolov, K. Chen, G. Corrado and J. Dean, "Efficient Estimation of Word Representations in Vector Space," Computation and Language, pp.1-12, Jan.2013.
[30]J. Pennington, R. Socher and C. D. Manning," GloVe : Global Vectors for Word Representation," Conference on Empirical Methods in Natural Language Processing, vol.14,pp.1532-1543, Oct.2014.

電子全文 電子全文(網際網路公開日期:20250824)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top