Suchen und Finden
Service
Building an Enterprise Chatbot - Work with Protected Enterprise Data Using Open Source Frameworks
Abhishek Singh, Karthik Ramasubramanian, Shrey Shivam
Verlag Apress, 2019
ISBN 9781484250341 , 399 Seiten
Format PDF, OL
Kopierschutz Wasserzeichen
Mehr zum Inhalt
Building an Enterprise Chatbot - Work with Protected Enterprise Data Using Open Source Frameworks
Table of Contents
5
About the Authors
12
About the Technical Reviewer
15
Acknowledgments
16
Introduction
18
Chapter 1: Processes in the Banking and Insurance Industries
20
Banking and Insurance Industries
20
A Customer-Centric Approach in Financial Services
25
Benefits from Chatbots for a Business
28
Chatbots in the Insurance Industry
29
Automated Underwriting
31
Instant Quotations
32
AI-Based Personalized Experience
32
Simplification of the Insurance Buying Process
32
Registering a Claim
32
Finding an Advisor
32
Answering General Queries
33
Policy Status
33
Instant Notifications
33
New Policy or Plan Suggestions
33
Conversational Chatbot Landscape
33
Summary
36
Chapter 2: Identifying the Sources of Data
38
Chatbot Conversations
38
General Conversations
39
Specific Conversations
39
Training Chatbots for Conversations
40
Self-Generated Data
41
Customer Interactions
42
Phone
43
Emails
43
Chat
43
Social Media
43
Customer Self-Service
44
Mobile
44
Customer Service Experts
44
Open Source Data
45
Crowdsourcing
45
Personal Data in Chatbots
46
Introduction to the General Data Protection Regulation (GDPR)
48
Data Protected Under the GDPR
48
Data Protection Stakeholders
49
Customer Rights Under the GDPR
49
Chatbot Compliance to GDPR
51
Summary
52
Chapter 3: Chatbot Development Essentials
53
Customer Service-Centric Chatbots
53
Business Context
54
Policy Compliance
56
Security, Authentication, and Authorization
57
Accuracy of User Input Translation to Systems
59
Chatbot Development Approaches
60
Rules-Based Approach
61
Advantages of the Menu-Based Approach
62
Disadvantages of the Menu-Based Approach
63
AI-Based Approach
63
Advantages of the AI-Based Approach
64
Disadvantages of the AI-Based Approach
65
Conversational Flow
65
Key Terms in Chatbots
67
Utterance
67
Intent
68
Entity
68
Channel
69
Human Takeover
69
Use Case: 24x7 Insurance Agent
70
Summary
71
Chapter 4: Building a Chatbot Solution
72
Business Considerations
72
Chatbots vs. Apps
73
Growth of Messenger Applications
74
Direct Contact vs. Chat
74
Business Benefits of Chatbots
75
Cost Savings
75
Customer Experience
76
Success Metrics
77
Customer Satisfaction Index
77
Completion Rate
77
Bounce Rate
78
Managing Risks in Chatbots Service
78
Third-Party Channels
78
Impersonation
79
Personal Information
79
Confirmation Check
80
Generic Solution Architecture for Private Chatbots
80
Workflow Description
81
Key Features
84
Technology Stack
85
Maintenance
85
Summary
86
Chapter 5: Natural Language Processing, Understanding, and Generation
87
Chatbot Architecture
89
Popular Open Source NLP and NLU Tools
92
NLTK
93
spaCy
93
CoreNLP
95
gensim
96
TextBlob
97
fastText
98
Natural Language Processing
98
Processing Textual Data
99
Reading the CSV File
99
Sampling
100
Tokenization Using NLTK
101
Word Search Using Regex
101
Word Search Using the Exact Word
102
NLTK
103
Normalization Using NLTK
103
Noun Phrase Chunking Using Regular Expressions
104
Named Entity Recognition
108
spaCy
110
POS Tagging
110
Dependency Parsing
112
Dependency Tree
113
Chunking
115
Named Entity Recognition
116
Pattern-Based Search
118
Searching for Entity
120
Training a Custom NLP Model
120
CoreNLP
122
Tokenizing
123
Part-of-Speech Tagging
123
Named Entity Recognition
124
Constituency Parsing
124
Dependency Parsing
126
TextBlob
126
POS Tags and Noun Phrase
127
Spelling Correction
127
Machine Translation
128
Multilingual Text Processing
129
TextBlob for Translation
129
POS and Dependency Relations
129
Named Entity Recognition
131
Noun Phrases
132
Natural Language Understanding
132
Sentiment Analysis
133
Polarity
133
Subjectivity
134
Language Models
134
Word2Vec
135
Neural Network Architecture
137
Using the Word2Vec Pretrained Model
138
Performing Out-of-the-Box Tasks Using a Pretrained Model
142
Word Pair Similarity
144
Sentence Similarity
144
Arithmetic Operations
145
Odd Word Out
146
fastText Word Representation Model
147
Information Extraction Using OpenIE
149
Topic Modeling Using Latent Dirichlet Allocation
152
Collection of Documents
152
Loading Libraries and Defining Stopwords
153
Removing Common Words and Tokenizing
153
Removing Words That Appear Infrequently
153
Saving the Training Data as a Dictionary
154
Generating the Bag of Words
155
Training the Model Using LDA
155
Natural Language Generation
157
Markov Chain-Based Headline Generator
158
Loading the Library
159
Loading the File and Printing the Headlines
159
Building a Text Model Using Markovify
160
Generating Random Headlines
160
SimpleNLG
161
Loading the Library
162
Tense
162
Negation
163
Interrogative
163
Complements
164
Modifiers
164
Prepositional Phrases
165
Coordinated Clauses
165
Subordinate Clauses
166
Main Method
167
Printing the Output
167
Deep Learning Model for Text Generation
168
Loading the Library
171
Defining the Training Data
171
Data Preparation
172
Creating an RNN Architecture Using a LSTM Network
178
Defining the Generate Text Method
180
Training the RNN Model
181
Generating Text
184
Applications
184
Topic Modeling Using spaCy, NLTK, and gensim Libraries
185
Tokenizing and Cleaning the Text
186
Lemmatization
187
Preprocessing the Text Method for LDA
187
Reading the Training Data
188
Bag of Words
189
Training and Saving the Model
189
Predictions
190
Gender Identification
191
Loading the NLTK Library and Downloading the Names Corpus
191
Loading the Male and Female Names
192
Common Names
192
Extract Features
193
Randomly Splitting into Train and Test
193
Training the Model
194
Model Prediction
194
Model Accuracy
194
Most Informative Features
195
Document Classification
195
Loading Libraries
196
Reading the Dataset into the Categorized Corpus
196
Computing Word Frequency
197
Checking the Presence of Frequent Words
198
Training the Model
199
Most Informative Features
199
Intent Classification and Question Answering
200
Intent Classification
200
Setting tensorflow as the Back End
201
Building the Model
201
Classifying the Intent
203
Question Answering
204
Building the Model
204
Context and Question
204
Serving the DeepPavlov Model
206
Summary
207
Chapter 6: A Novel In-House Implementation of a Chatbot Framework
209
Introduction to IRIS
210
Intents, Slots, and Matchers
211
Intent Class
213
IntentMatcherService Class
214
The getIntent Method of the IntentMatcherService class
217
Intent Classification Service
220
General Query Intent
220
Matched Intent Class
221
Slot Class
223
IRIS Memory
228
Long- and Short-Term Sessions
228
Long-Term Attributes
228
Short-Term Attributes
229
The Session Class
229
Dialogues as Finite State Machines
235
State
237
Shields
238
Transition
239
State Machine
240
Building a Custom Chatbot for an Insurance Use Case
246
Creating the Intents
249
CustomNumericSlot
250
BooleanLiteralSlot
254
AccTypeSlot
255
IPinSlot
256
AlphaNumericSlot
257
IrisConfiguration
259
Adding States
261
Shields
263
DontHaveAccTypeShield
263
DontHaveQuoteDetailsShield
264
HaveAccTypeShield
265
HaveClaimIdShield
265
HaveQuoteDetailShield
266
Adding Execute Methods
266
Exit State
267
FindAdvisorState
267
GetAccountBalanceState
268
GetAccTypeState
269
GetClaimIdState
271
AskForQuote State
272
GetQuote State
275
Start State
278
GeneralQuery State
278
Adding State Transitions
281
Managing State
287
Exposing a REST Service
289
ConversationRequest
289
ConversationResponse
290
ConversationService
290
ConversationController
293
Adding a Service Endpoint
293
Summary
294
Chapter 7: Introduction to Microsoft Bot, RASA, and Google Dialogflow
296
Microsoft Bot Framework
296
Introduction to QnA Maker
297
Introduction to LUIS
305
Introduction to RASA
307
RASA Core
309
RASA NLU
310
Introduction to Dialogflow
311
Summary
316
Chapter 8: Chatbot Integration Mechanism
318
Integration with Third-Party APIs
318
Market Trends
319
Stock Prices
325
Weather Information
331
Connecting to an Enterprise Data Store
336
Integration Module
340
Demonstration of AskIris Chatbot in Facebook Messenger
353
Account Balance
353
Claim Status
354
Weather Today
355
Frequently Asked Questions
356
Context Switch Example
357
Summary
359
Chapter 9: Deployment and a Continuous Improvement Framework
360
Deployment to the Cloud
360
As a Stand-Alone Spring Boot JAR on AWS EC2
361
As a Docker Container on AWS EC2
364
As an ECS Service
367
Smart IRIS Alexa Skill Creation in Less Than 5 Minutes
372
Continuous Improvement Framework
383
Intent Confirmation (Double-Check)
384
Predict Next Intent
386
A Human in the Loop
388
Summary
390
Index
391