臺灣博碩士論文加值系統

現今各種社群現今隨著Facebook Messenger、Line、Telegram以及Slack等通訊平台的日益發展，越來越多使用者花在其之上的時間已遠遠超過使用其他APP的時間。這樣的變化使得提供於通訊平台上(如Facebook、line、slack等)之上之的對話機器人(Chatbot)與日俱增，也相對帶起許多建置對話機器人的工具以及平台也應運而生，；然而，但目前目前的工具與平台在對話流程控制、對話規則管理、外部服務雙向整合等實務面之支援較為缺乏，造成對話機器人開發與維護的困難。若以現有之工具或平台去建置與維護具備複雜對話流程、外部服務雙向串接、以及語意分析功能之對話機器人，開發者將無可避免地需進行繁複的腳本設計甚或額外程式的開發，大幅增加了建置與維護上的複雜度大部分的工具通常僅專注於單一功能之上。對於一個需要整合NLP (Natural Language Processing)語意分析、外接服務擴充、對話易於管理等多項項特點的對話機器人，則必須自行整合其他服務來實現，造成建置上的困難度。因此，為解決上述議題，本研究提出一個基於流程引擎之對話機器人(Chatbot)框架，我們稱之為FCF (Flow-based Chatbot Framework)。FCF以Node-Red為主要開發平台，讓使開發者能快速建置滿足大部分商務情境的對話機器人，同時提供視覺化的建置介面以及流程導向開發之概念，來降低建置上的難易度。FCF並藉由串接Api.ai支援NLP語意分析，並以及制定服務串接標準格式來同時支援NLP語意分析以及達到與外部服務雙向整合之外接服務擴充的功能。此外而為了達到模組擴充的特點，我們亦額外開發了架設一個線上平台ChatBotChatbot Market，讓建置者可以在上面發佈與搜尋分享並取用現成的對話應用流程，達成Flow as a Service (FaaS)之效益。在實驗部分在本研究的最後，我們以透過一個手機選購對話機器人為例，深入比較FCF與並和Api.ai與Red Bot這兩個既有已有的對話機器人建置工具來做比較，實驗結果證實來說明此FCF方法相較其他兩個工具框架可有效降低聊天機器人所具有開發與維護之複雜度。

Nowadays, more and more ChatBotChatbots are dependent built onon those social platforms like Facebook, line, and slack. Accordingly growing day by day, but also more and moremany tools and online platforms for building ChatBotChatbots have been constructed and widely usedappeared one after another., However, these tools or platforms are not able to fully support the control of chat flow, the management of conversations, and bi-directional Web service integration. but they usually focus on a single function. If a userwe want plans to build a ChatBotChatbot with complex chat flows, an ability of integrating Web APIs, and a capability of that has NLP (Natural Language Processing) analysis、external service expansion and simple dialogue management features, the user must to write complex conversation scripts and even a lot of additional codesintegrate other services, which caused difficulties in building; It causes the development and maintenance difficult and costly.. Therefore, to address the above issues, we propose a novel approach, referred to as FCF (Fflow-based Chatbot Fframework). that FCF was developed built on the Node-Red platform. It not only to provide builders can quickly build a business ChatBot, but also to to provide a visual and flow-based construction interface environment for Chatbot design. FCF allows Chatbot developers to quickly build Chatbots for business contexts in a visualized wayand flow-oriented concept to reduce the difficulty of building. We FCF also relies on theuse Api.ai APIs to support NLP analysis and the newly-deviseddevelop a service concatenation datastandard format for service webhook to support NLPallow bidirectional and external service extensionsintegration. For the feature of the service module expansion, In addition, to realize “Flow as a Service (FaaS)”, wwe also set up a n online platform ChatBotChatbot Market for Chatbot developers builders to share publish and access find established the chat flows. At the end of the studyFor the experiments, we preparedused a transaction “buy smartphones” example to be as a testbed to compare FCF with two existing ChatBotChatbot building tools, Api.ai and Red Bot. ,E xperiment results demonstrate that FCF outperforms these tools in terms of reduced complexity of development and maintenanceto explain our framework have the advantage of operation and efficiency.

目錄
摘要 I
Abstract II
目錄 III
圖目錄 IV
表目錄 VI
第一章 緒論 7
1-1 引言 7
1-2 動機 7
1-3 論文架構 8
第二章 背景知識與相關文獻 9
2-1 Node.js 9
2-2 Node Package Manager (NPM) 9
2-3 Node-Red 9
2-4 Red Bot 10
2-5 HuBot 10
2-6 RiveScript 11
2-7 Cleverscript 11
2-8 Api.ai 12
2-9 Webhook 12
2-10 JSON 13
第三章 基於流程引擎之對話機器人框架 14
3-1 需求分析 14
3-2 核心架構與概念圖 14
3-2-1 NodeRed-Based Chatbot Framework 15
3-2-2 Service Webhook 25
3-2-3 Chatbot Market 27
第四章 系統測試與實驗 29
4-1 FCF安裝 29
4-2 Api.ai設置 29
4-3 實驗：手機選購對話機器人 32
第五章 結論與未來研究方向 41
參考文獻 42

參考文獻

[1]
Md. Shahriare Satu, Md. Hasnat Parvez and且 Shamim-AI-Mamun, “Review of integrated applications with AIML based chatbot,” 2015.
[2]
Fernando A. Mikic, Juan C. Burguillo, Martín Llamas, Daniel A. Rodríguez and且 Eduardo Rodríguez, “CHARLIE: An AIML-based Chatterbot which Works as an Interface among INES and Humans,” 2009.
[3]
Api.ai. [線上]. Available: https://api.ai/.
[4]
RiveScript. [線上]. Available: https://www.rivescript.com/.
[5]
HuBot. [線上]. Available: https://hubot.github.com/.
[6]
Cleverscript. [線上]. Available: http://www.cleverscript.com/.
[7]
Node-Red. [線上]. Available: https://nodered.org/.
[8]
Layla El Asri, Hannes Schulz, Shikhar Sharma, Jeremie Zumer, Justin Harris, Emery Fine, Rahul Mehrotra and且 Kaheer Suleman, “FRAMES: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems,” 2017.
[9]
Node.js. [線上]. Available: https://nodejs.org/en/.
[10]
NPM. [線上]. Available: https://www.npmjs.com/.
[11]
RedBot. [線上]. Available: http://red-bot.io/.
[12]
About Webhooks - Github Help. [線上]. Available: https://help.github.com/articles/about-webhooks/.
[13]
Facebook for developers - Webhook Reference. [線上]. Available: https://developers.facebook.com/docs/messenger-platform/webhook-reference.
[14]
Line Messaging API - Webhooks. [線上]. Available: https://devdocs.line.me/en/#webhooks.
[15]
Node-RED Library. [線上]. Available: https://flows.nodered.org/.
[16]
FCF. [線上]. Available: https://github.com/Spicdev/node-red-contrib-FCF-ChatBot.
[17]
Hamid R. Motahari Nezhad, “Cognitive Assistance at Work,” 2015.