整合聊天機器人與語音對話機器人: 打造K12數位學習助理;E-Learning Assistant in K12 Academy: Integrating Chatbot and Voice Dialogue Robot

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/77659

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/77659

Title:	整合聊天機器人與語音對話機器人: 打造K12數位學習助理;E-Learning Assistant in K12 Academy: Integrating Chatbot and Voice Dialogue Robot
Authors:	趙啟雲;CHAO, CHI-YUN
Contributors:	資訊工程學系
Keywords:	機器學習;隱馬可爾科夫模型;數位學習;詞向量神經網路;Machine learning;E-Learning;word2vec neural network;hidden Markovkov model
Date:	2018-07-26
Issue Date:	2018-08-31 14:51:56 (UTC+8)
Publisher:	國立中央大學
Abstract:	近年來數位學習越來越流行，因為數位學習有著能隨時隨地地進行學習的優點，相較於過去傳統教室老師對學生的教育學習者也可以針對自己的學習狀況，學生可以更加隨性調整學習進度，可以有效地增加學習上的效率。一個好的數位學習平台，線上老師客服是必不可少的，但由於龐大的使用客群，使用真人老師全天候的服務所有的學生成本非常高，因此我們開發了人工智慧教學助理系統，可以隨時隨地在社交通訊軟體上分擔線上老師客服的工作:為學生解決課業上的問題、解決學生數位平台的操作問題。為了更方便學生使用，我們甚至可以透過語音對話機器人，直接用語音對話方式為學生提供服務，提供更完善的數位學習環境。本文提出的聊天機器人是一個檢索式模型，先藉由隱馬可爾科夫模型(Hidden Markov Model)將使用者的輸入分詞後，除去常用詞，提取出關鍵字，再將關鍵字透過詞向量化模型(Word2Vec Model)比對各個資料庫中定義好的對話主題的相似度，以此實做對使用者對話的關鍵字提取以及分類功能。 ;In recent years, E-Learning has become more and more popular because of being able to let students learn anytime and anywhere. Compared with traditional classroom learning, students can adjust their learning more casually according to their own learning conditions. It can increase the efficiency of their learning. For a good e-learning platform, on-line tutor service is need. But hiring human tutors will cost a lot due to large number of students in whole time use. Therefore, we develop a chatbot system to share some of the work of human tutors: solve problems in the course for students and provide FAQ of the operation in the e-learning platform. It can even provide service to students via voice dialogue robots. With our system, students can get a more complete e-learning environment. The chatbot proposed in this paper is a retrieval-based model. After the user′s input is segmented by the Hidden Markov Model to get the keywords, and the keywords are transmitted through the Word2vec model. The Word2Vec Model compares the similarity of the conversation topics defined in each database to achieve keyword extraction and classification for user conversations
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	134	View/Open

社群 sharing

Loading...