客服聊天機器人之設計與實作：以LED室內照明產業為例

Design and Implementation of Chatbot on Customer Service:Take an example of LED Indoor Lighting Industry

賴玉民(Yu-Min Lai)

指導教授 ： 皮世明

中原大學/商學院/資訊管理研究所/碩士(2020年)

https://doi.org/10.6840/cycu202000072

摘要

科技技術的快速進步發展，大數據和人工智能機器人被廣泛應用於各個領域。機器人這個名詞己經慢慢走入了我們的生活中，也應用在各種產業中，而各公司及企業間互相競爭，不單單只有在實体通路的服務銷售，已經擴展到網路的平台媒合，而「顧客關係管理」的相關議題，一直以來都是許多公司企業非常注重的策略方向；在早期的LED照明產業中，一般消費者所接觸的服務人員，都是以販售業務人員或工程服務人員，作為技術的支援或客服對應。但隨著科技進步，社群媒體與即時通訊軟體的普及發展，相較其它產業都已建置客服聊天機器人(Chatbot)，例如在金融業、教育、電子商務、旅遊業等…而傳統產業還是使用電話語音作為客戶服務，還並未將其導入。
本研究目的針對台灣國內LED室內照明產業，以消費者常詢問相關LED照明知識、相關商品的介紹，並提供消費者24小時都可以詢問相關問題，作為LED室內照明客服機器人所學習資料庫範本，實作建立一支Linebot LED室內照明客服機器人。
本研究提出開發者根據需求分析，以公司近年來常見客服問題(FAQ)作為對話資料庫，使用近3年的作為優先選擇，在使用者介面編排，需要簡單清楚分類，讓消費者容易使用，不能太過於複雜，而讓每個人都能容易使用。

關鍵字

客服機器人 ； 任務導向型對話 ； LED照明機器人

並列摘要

The technical technology fast progress development, big data and artificial intelligence robots are widely used in various fields. The term robot has slowly entered our lives, and is also used in various industries, and companies and enterprises compete with each other, not only in the sales of services in physical channels, but also expanded to the network platform. The related issues of "customer relationship management" have always been a strategic direction that many companies attach great importance to; in the early LED lighting industry, the service personnel contacted by ordinary consumers were mainly sales business personnel or engineering Service staff, as technical support or customer service correspondence. However, with the advancement of technology, the popularization and development of social media and instant messaging software, compared with other industries, have established Chatbot on customer service, such as finance, education, e-commerce, tourism, etc... While traditional industries are still Using phone voice as customer service has not yet imported it.
The purpose of this study is to target the domestic LED indoor lighting industry in Taiwan. Consumers often ask about related LED lighting knowledge and related product introductions, and provide consumers with 24 hours to ask related questions as a model database for learning LED indoor lighting customer service robots. Implement a Linebot LED indoor lighting customer service robot.
This study proposes that developers analyze the needs of the company and use the company's common customer service questions (FAQs) as a dialogue database in recent years. The most recent three years have been used as the preferred choice. The user interface layout needs to be simple and clear to make it easy for consumers to use. It shouldn’t be too complicated to make it easy for everyone to use.

並列關鍵字

LineBot ； Task-Oriented Dialogue ； LED Chatbot

參考文獻

1. Argal, A., Gupta, S., Modi, A., Pandey, P., Shim, S., Choo, C. (2018). Intelligent travel chatbot for predictive recommendation in echo platform. In 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 176-183). IEEE.

2. Augello, A., Gentile, M., Weideveld, L., Dignum, F. (2016).A model of a social chatbot. In Intelligent Interactive Multimedia Systems and Services 2016 (pp. 637-647). Springer, Cham.

3. Cui, L., Huang, S., Wei, F., Tan, C., Duan, C., Zhou, M. (2017). Superagent: A customer service chatbot for e-commerce websites. In Proceedings of ACL 2017, System Demonstrations(pp. 97-102).

4. Huang, J., Zhou, M., Yang, D. (2007).Extracting Chatbot Knowledge from Online Discussion Forums. In IJCAI(Vol. 7, pp. 423-428).

5. Huber, B., McDuff, D., Brockett, C., Galley, M., Dolan, B. (2018).Emotional dialogue generation using image-grounded language models. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (p. 277). ACM.