Mais conteúdo relacionado Semelhante a Enhance customer experience with Conversational Interfaces (20) Mais de Amazon Web Services (20) Enhance customer experience with Conversational Interfaces1. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Enhance customer experience with
Conversational Interfaces
Johan Esbjörner
Technical Lead HQV CCOE
Husqvarna
@taraw
Tara E. Walker
Sr. Technical Evangelist
Amazon Web Services
2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
The What & Why of Conversational Interfaces
Ins and Outs of Amazon Lex
Putting Conversational Interfaces to Work: Husqvarna Group
3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What & Why of Conversational
Interfaces
4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
“What we need now is to be able to simply talk with our
devices. That's why I believe it's finally time for the
conversational user interface, or "CUI."
This is the interface of the future, made even more
necessary as computing propagates beyond laptops,
tablets and smartphones to cars, thermostats, home
appliances,and now even watches ... and glasses.”
~ Ron Kaplan (via WIRED magazine), Lead-Nuance Communications' NLU R&D
Lab, Professor of Linguistics at Stanford University, former CTO of Powerset
5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Why Conversational Interface Access
On-demand
Accessible
Efficient
Natural
6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Developer challenges
Conversational interfaces need to combine a large number of
sophisticated algorithms and technologies
Speech
recognition Language
understanding
Business logic
Disparate
systems
Authentication
Messaging
platforms
Scale Testing
Security
Availability
Mobile
7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Considerations when building Conversation Interfaces
• Understand the conversation flow
• What information do you need from the conversation
• What is the intent/goal of the conversation
• Validate your input
• Handle errors gracefully
• Add clarification prompts if required
• Test, test and more testing
• Understand Metrics after your bot or conversational
interface is deployed in production
8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
“Alexa, What Is Amazon Lex?”
9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Text and speech language understanding: powered by the
same technology as Alexa
Enterprise Ready: connect to enterprise systems via SaaS
connectors; Versioning and alias support
Build once and deploy to multiple platforms
Designed for builders: efficient and intuitive tools to build
conversations; Scales automatically
Amazon Lex - Overview
Continuous Learning: monitor and improve your bot
10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Hello Amazon Lex
Amazon Lex
Graphical User
Interface
Conversational
Interface
Built-In Integration
with Slack, Messenger, & Twilio
11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Text and speech language understanding
Speech
recognition
Natural language
understanding
Powered by the same deep learning technology as Alexa
12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Multi-platform
Mobile
Messaging
Platforms Web IoT
SDKs: iOS & Android
Mobile Hub
Facebook, Twilio
SMS and Slack
SDKs: Java, JavaScript, Python,
CLI, .NET, Ruby on Rails,
PHP, Go
Integrated with AWS
IoT via AWS Lambda
Build once and deploy to multiple platforms
13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Technology
Amazon Lex
Automatic Speech
Recognition (ASR)
Natural Language
Understanding (NLU)
Same technology that powers Alexa
Amazon Cognito CloudTrail CloudWatch
AWS Services
Action
AWS Lambda
Authentication &
Monitoring
Speech
API
Language
API
Fulfillment
End Users
Developers
Console
SDK
Intents,
Slots,
Prompts,
Utterances
Input:
Speech
or Text
Multi-Platform Clients:
Mobile, IoT,
Web, Chat
API
Output:
Speech (via Amazon Polly TTS)
or Text
14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Key Concepts
Utterances
Spoken or typed phrases that
invoke your intent
BookHotel
Intents
An intent performs an action in
response to natural language user input
Slots
Slots are input data required to
fulfill the intent
Fulfillment
Fulfillment mechanism for your
intent
15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Example: “Book a hotel”
Book Hotel
Stockholm
“Book a Hotel in
Stockholm”
Automatic Speech
Recognition
Hotel Booking
Stockholm
Natural Language
Understanding
Intent/Slot
Model
UtterancesHotel Booking
City Stockholm
Check In May 14th
Check Out May 16th
“Your hotel is booked for
May 14th”
Amazon Polly
Confirmation: “Your hotel
is booked for May 14th”
“Can I go ahead
with the booking?
a
in
16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Slot elicitation
Check In
5/14/2018
City
Stockholm
I would like to book a hotel
Sure, which city will you
be traveling to?
Stockholm
What date do you want to
check in?
May 14th
17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Dialog management
I would like to book a hotel
Sure, which city will you
be traveling to?
Stockholm
What date do you want to
check in?
Tomorrow
… And for how many
nights is this for?
City
Simple Declarative Model
Check-In Date
Check-Out Date
Slots
Which city will you be traveling to?
What date do you want to check in?
How many nights is this for?
Prompts
Build Multi-turn Conversations
Easy Setup in Console
18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Customize conversations
I would like to book a hotel
Would you prefer to stay in
Downtown this time as well?
Yes
What date do you want to
check in?
May 14th
Sorry no availability. Would
a different location work?
Personalize conversation
based on user preferences
Validate user input and
re-prompt as necessary
19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Error handling
I want to …. {garbled} …..
Sorry can you please
repeat that?
I am having trouble understanding
Can you please say that again?
Sorry I am not able to
assist you at this time
Clarify by requesting user
to repeat
Uses a different
prompt every time
Hang up phrase to end the
conversation
20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Conversation context
Slot ValuesIntents Prompts ConfirmationsSession
Attributes
Slot Value
Slot Value
Conversation
Yes/No
Session
Attributes
Intent
Prompt
Lex maintains context by storing data throughout the conversation
Confirm
21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Dynamic conversation flow
Conversation
Session
Attributes
Second Intent
Switch Intents
First Intent
Session
Attributes
Conversation
Chain Intents
Takeout
Dine In
Dine In or
Take out?
Anything else
today?
Book a Car
22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Versioning and Alias support
AliasVersioning
• Supported for intents, slots,
and bots
• Enables multideveloper
environment
• Rollback to previous
versions
• Deploy different aliases to different
platforms
• Run different stacks for dev, stage and prod
environments
• Target different user groups with
different aliases
v1 v2 v3 latest
v1 Dev
v2 Stage
v3 Prod
23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Fulfillment & Response
AWS Lambda integration Return to Client
User input parsed to derive
intents and slot values.
Output returned to client for
further processing.
Intents and slots passed to
AWS Lambda function for
business logic
implementation.
24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Deployment Cycle
Save Build
Saving your bot
preserves the current
state on the server
Building your bot
creates versions that
you can test
Publish
Publishing your app will create a
version of your bot and provide an
alias to your clients
Test
Test your bot in a
chat window on the
console
25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex – Export to Alexa Skill
Amazon Lex
Chatbot schema
(JSON)
Alexa Skill
Export to Alexa
Skills Format
Import into Alexa
Skill Builder
26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex
Demo
27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Putting Conversational Interfaces to Work
Husqvarna Group
Johan Esbjörner
29. Market leadership – over 20 years of
innovation
Key robotic milestones
Connect Gen2
Automower Automower
Connect
Gen1
Solar
Mower
310, 315 450X
Generation 0 Generation 1
1995 1998 2003 2015
The Original
We created the
Robotic Mower
market
>1
million
20182011
Generation 2 Generation 3
Connect Gen3
PRO
2007
230ACX 260ACX 305
31. Automower smart home integrations
•Alexa & Google support, 2018 Q3 / Q4
– Basic features, start, stop, park & status.
– Will evolve based on what our customers requests
•Open API, 2018 Q4 / 2019 Q1
– API access for all developers
34. 1. A launched skill is locked for editing and a new
development version of the skill is created automatically.
Things to consider when deploying an
Alexa Skill
Same ARN is used in both Skills!
35. Things to consider when deploying an
Alexa Skill
3. Alexa Skills Kit CLI requires manual intervention for authorization
store ~/.ask/cli_config securely for reuse in docker etc.
2. Changes to a non versioned lambda function will affect the
live skill
orunless
Separate environments Lambda versioning & aliases
is used
37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Learn More @
https://aws.amazon.com/lex
Build your first bot!
✔
✔
✔
38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thank You!
Tara E. Walker
Sr. Technical Evangelist
Amazon Web Services
@taraw