文章基本信息

标题：SamBot - Intelligent Conversational Bot for Interactive Marketing with Consumer-centric Approach
本地全文：下载
作者：Aditya Pradana ; Goh Ong Sing ; Yogan Jaya Kumar 等
期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2017
卷号：9
页码：265-275
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：Interactivity of corporate website is important as marketing products through it become popular. Moreover, the usage of Artificial Intelligence application is growing in many sectors. In order to improve the interactivity and effectiveness of corporate website in providing information, a conversational bot called SamBot is developed. As a part of Artificial Intelligence application, it can respond to users’ question and prolong the conversation with its intelligence. It is integrated to Samsung IoT Showcase website as the corporate website. SamBot contains the knowledge of Samsung marketing domain which is useful to deliver appropriate answer to the users’ questions. Its knowledge base includes Samsung promotion, Samsung product Frequently Asked Question, and general knowledge. In default, a conversational bot will generate random answers if matching knowledge cannot be found. In this research, the authors would like to overcome this problem by improving its knowledge maintenance capability either performed by botmaster or users. A function is added to support the knowledge maintenance process by botmaster, namely conversation log-based knowledge maintenance module. As to support consumer-centric knowledge approach, several features are developed such as random answer enhancement and consumer-centric learning capability. This will allow user to directly teach the bots a new knowledge. In addition, enhancement to reuse recently asked question as questions recommendation or autocomplete questions is developed in order to solve a problem where users need to be updated to current issues. With this enhancement, SamBot can give recommendation of questions for users to ask. All of the enhancements are measured using a world-wide Turing Test or Loebner Prize chatbot competition scoring system. The result shows that SamBot is capable of handling Samsung related questions very well with 26.4 points scored.
关键词：Artificial Intelligence; conversational bots; deep learning; AIML; marketing.