Please use this identifier to cite or link to this item:
Title: Inquiry chatbot with cloud computing
Authors: Sathish Jayabalan
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Abstract: The project aims to provide an efficient solution to replace the traditional call center model which is widely used in the industries. Traditional call centers are labor intensive and are unable to handle variable throughput efficiently. This is due to its fixed bandwidth to handle incoming calls. The proposed solution will have the call center infrastructure built using Amazon Web Services. The cloud services provider enables the development of the various components of a call center. Amazon Lex service will provide the Natural Language Understanding and Automatic Speech Recognition which allows developer to build lifelike conversational bots which provides highly engaging user interactions. The project will be implemented in 2 phases. First phase consists of the building conversational chatbot on Alexa-enabled devices using Alexa Custom Skills Kit. Second phase includes the integration of the Amazon Connect (cloud-based contact center) directly to the Lex Bot. Interactions with AWS NoSQL Database Service (DynamoDB) and Simple Notification Service (SNS) will be implemented in both phases. From the project, the factors affecting the accuracy of the chatbot, to match user’s utterance to their intent, were established. These factors mainly depend on the quantity and diversity of the enumeration values provided by the developer for the sample utterances.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
FYP Final Report2.47 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 16, 2024

Download(s) 50

Updated on Jun 16, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.