Building an Enterprise Chatbot, 1st ed. Work with Protected Enterprise Data Using Open Source Frameworks

Langue : Anglais

Auteurs : Singh Abhishek, Ramasubramanian Karthik, Shivam Shrey

Couverture de l’ouvrage Building an Enterprise Chatbot

Résumé
Sommaire
Biographie
Commentaire

Explore the adoption of chatbots in business by focusing on the design, deployment, and continuous improvement of chatbots in a business, with a single use-case from the banking and insurance sector. This book starts by identifying the business processes in the banking and insurance industry. This involves data collection from sources such as conversations from customer service centers, online chats, emails, and other NLP sources. You?ll then design the solution architecture of the chatbot. Once the architecture is framed, the author goes on to explain natural language understanding (NLU), natural language processing (NLP), and natural language generation (NLG) with examples.

In the next sections, you'll design and implement the backend framework of a typical chatbot from scratch. You will also explore some popular open-source chatbot frameworks such as Dialogflow and LUIS. The authors then explain how you can integrate various third-party services and enterprise databases with the custom chatbot framework. In the final section, you'll discuss how to deploy the custom chatbot framework on the AWS cloud.

By the end of Building an Enterprise Chatbot, you will be able to design and develop an enterprise-ready conversational chatbot using an open source development platform to serve the end user.

What You Will Learn

Identify business processes where chatbots could be used
Focus on building a chatbot for one industry and one use-case rather than building a ubiquitous and generic chatbot
Design the solution architecture for a chatbot
Integrate chatbots with internal data sources using APIs
Discover the differences between natural language understanding (NLU), natural language processing (NLP), and natural language generation (NLG)
Work with deployment and continuous improvement through representational learning

Who This Book Is For

Data scientists and enterprise architects who are currently looking to deploy chatbot solutions to their business.

Chapter 1: Processes in the Banking and Insurance Industry

The chapter will focus on explaining some core process within the banking and insurance industry that is suitable for a chatbot application.

No of pages: 30

Chapter 2: Identifying the Sources of Data

This chapter will discuss sources of data for conversation and action-based event triggers for a chatbot. Conversation courses would be from customer service centers, online chats, emails and other NLP sources, while action sources are customer account details and more personalize data.

No of pages: 30

Chapter 3: Mining Intents from the Data Sources

This chapter will discuss how to build a business-specific intent engine for chatbots.

No of pages: 30

Chapter 4: Building a Business Use-Case

This chapter will focus on how to identify the right business process to introduce chatbots. It will also discuss how to look at some of the metrics of success and RoI given a chatbot is deployed.

No of pages: 30

Chapter 5: Natural Language Processing (NLP)

Chapter Goal: This chapter focusses on processing and understanding natural language through the computer algorithm. It also introduces how to prepare data for applying the NLP algorithms. We will use Stanford CoreNLP, NLTK, gensim, OpenIE tools to explore and model.

No of pages: 80

Sub - topics

Introduction: Question & answering, information extraction, sentiment analysis, Machine translation,

Text processing: Regex, tokenization, normalization – lower case, lemmatization, stemming (Porters Algorithm), sentence segmentation

Converting text to features: Syntactical parsing – dependency grammar, PoS, entity parsing – phrase detection, topic modeling, statistical features – TF-IDF, word embeddings

Classification – spam filter using naïve Bayes, sentiment analysis using SVM on Lexicon and text feature.

NLP Tools – nltk, genism, openIE, CoreNLP

Chapter 6: Building Chatbots Using Popular Platforms

For general purpose chatbots, publicly available cloud services can be used to deploy chatbots faster and without any DevOps overhead. We shall discuss some of the major chatbot development platforms available in the market.

No of pages: 50

Sub-Topics

Microsoft Bot framework with LUIS

Google’s DialogFlow

Amazon Lex with Lambda

Bottr, Chatfuel and others

Open framework RASA and Botpress

Chapter 7: Deployment and Continuous Improvement Framework

In this chapter we shall discuss and implement a custom built chatbot . We will discuss designing and implementing state machines and their different state transitions, and how they are critical to maintain the context of user utterance as well as in defining the chat flow using sessions that contains long term and short-term attributes.

No of pages: 50

Sub-topics:

Public endpoint creation

Intent engine development and deployment as API

Building state machine

Integration with Facebook messenger

Deployment of chatbot on AWS

Logging

Mining conversation log to improve intent engine

Recommending similar/next questions, pushing information based on needs prediction

Abhishek Singh is on a mission to profess the de facto language of this millennium, the numbers. He is on a journey to bring machines closer to humans, for a better and more beautiful world by generating opportunities with artificial intelligence and machine learning. He leads a team of data science professionals solving pressing problems in food security, cyber security, natural disasters, healthcare, and many more areas, all with the help of data and technology. Abhishek is in the process of bringing smart IoT devices to smaller cities in India so that people can leverage technology for the betterment of life.

He has worked with colleagues from many parts of the United States, Europe, and Asia, and strives to work with more people from various backgrounds. In 7 years at big corporations, he has stress-tested the assets of U.S. banks at Deloitte, solved insurance pricing models at Prudential, and made telecom experiences easier for customers at Celcom, and core SaaS Data products at Probyto. He is now creating data science opportunities with his team of young minds.

He actively participates in analytics-related thought leadership, authoring, public speaking, meetups, and training in data science. He is a staunch supporter of responsible use of AI to remove biases and fair use of AI for a better society.

Abhishek completed his MBA from IIM Bangalore, a B.Tech. In Mathematics and Computing from IITGuwahati, and a PG Diploma in Cyber Law from NALSAR University, Hyderabad.

Karthik Ramasubramanian has over seven years of practice and leading Data Science and Business Analytics in Retail, FMCG, E-Commerce, Information Technology for a multi-national and two unicorn startups. A researcher and problem solver with a diverse set of experience in the data science lifecycle, starting from a data problem discovery to creating a data science prototype/product.

On the descriptive side of data s

Concepts are explained using use-cases from the banking and insurance sector

Deploys a complete in-house built chatbot using open source stacks

Covers popular chatbot frameworks such as Microsoft LUIS and Google Dialogflow