Shopping Chatbot based on Complex Task Structure and Consumption Need

• Main Authors: Chen-AnWang, 王振安
• Other Authors: Wen-Hsiang Lu
• Format: Others
• Language: en_US
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/e9vcnn

碩士 === 國立成功大學 === 資訊工程學系 === 107 === Nowadays, many people can buy things online without going out. In Taiwan, auction sites, such as Ruten, PC-HOME, are well-known. Many people buy what he or she wants through online channels. Some functions, like the searching bar, common searching words, products categories, …, is very useful. However, we can’t get the advices and recommends via online shopping. When we go outside to buy things, we often get advice from sellers. However, if we buy things online, we can only search data by ourselves. So, we want to create a shopping chatbot to provide users some advices when they are shopping. We propose the ATCN model, Activity-Task-Consumption Need model, to train the data using shopping articles. ATCN model is based on complex structure, in which there are four layers. We use four database tables, which produced by ATCN model, to build the shopping chatbot. We have two experiments, one is to evaluate the performance of task extraction and the other is to evaluate the performance of related task prediction. We think the shopping chatbot will be more convenient soon. We can use less time and effort in shopping.