Chatbot workshop introduction.#digitized16

Voice, Natural Language, Notiﬁcations,
API, and Conversation
How we build and design
products in the future.

There are more than
three million apps
combined in all app stores
An average smartphone user
has 42 apps on his device
but spends 90% of his time
on only 9 or 10 of them.
Present problem
with UI

25% of apps are
only used once
and 75% of users leave
within the ﬁrst
three months.
The growth of mobile
and its app-centric world
has been the opposite of the web,
and there is no analog of PageRank
for mobile apps.

Messaging is the most
widely used application
on the mobile platform,
with chat-based apps
Already, more than
15% search queries
are made on Baidu
using Voice Input.

HISTORICAL EVOLUTION
The Story of New Platforms

PC
Each platform requires recreation
of the application layer, built and customized
to grow and scale the new platform.
Web Mobile

Time Mid-80’s
Clients Websites Mobile apps
Mid-90’s Mid-00’s
Applications
gestation phase growth phase
PC era
PC
Desktop
Web
Browser
Mobile
iOS, Android
Internet era
Mobile era
Key Product
& Companies
Paradigm
Platform

HYPER GROWTH PHASE
The shift is set to happen again

PAST PRESENT FUTURE
human to human human to machine machine to machine

Google Mind
Boston Dynamics-Atlas
virtual reality & drones
are just a glimpse
of things to come.

The primary interface
for interacting with apps
might not be the app itself.
The age of apps
as service layers

How does it work?
MACHINE LEARNING

MACHINE LEARNING
Supervised Unsupervised Adaptive

A model is prepared through a training process
where it is required to make predictions
and is corrected when those predictions
are wrong. The training process continues
until the model achieves a desired level
of accuracy on the training data.
Supervised machine learning
Classiﬁcation

Clustering
Learns patterns in input data when no speciﬁc output values are given.
Unsupervised machine learning

Learns by an indication of correctness at the end of some reasoning.
Environment
observation
Reward
Action
Adaptive/Reinforcement machine learning

A branch of machine learning based on a set of algorithms
that attempt to model high level abstractions in data by using
a deep graph with multiple processing layers, composed of
multiple linear and non-linear transformations.
Neural Networks & Deep Learning

The experiment started with a machine learning algorithm
and a database of over 10,000 songs from more than 100 rap artists.
The machine produces rap lyrics that rival
human-generated ones for their complexity of rhyme.
The words must ﬁrst be converted into phonemes.
Finding rhymes is then simply a question of scanning the phonemes
looking for similar vowels sounds
How machine Mines Rap Lyrics
and Writes Its Own

For a chance at romance I would love to enhance
But everything I love has turned to a tedious task
One day we gonna have to leave our love in the past
I love my fans but no one ever puts a grasp
I love you momma I love my momma – I love you momma
And I would love to have a thing like you on my team you take care
I love it when it’s sunny Sonny girl you could be my Cher
I’m in a love aﬀair I can’t share it ain’t fair
Haha I’m just playin’ ladies you know I love you.
I know my love is true and I know you love me too
Girl I’m down for whatever cause my love is true
This one goes to my man old dirty one love we be swigging brew
My brother I love you Be encouraged man And just know
When you done let me know cause my love make you be like WHOA
If I can’t do it for the love then do it I won’t
All I know is I love you too much to walk away though
Lyrics

CONVERSATIONAL UI
The rise of hybrid Interfaces

Command-line
The command line was the original
conversational interface.
You’d input a textual command,
hit enter, the computer would execute
the command and print the answer.

IRC
IRC already supported bots,
massive group chat quizzes,
polls and other types
of conversational applications

Each message
becomes a mini app
Blended interfaces, bringing the best of the command line
and GUI paradigms together.

OPERATOR
Companies like Operator
are leading the way,
designing rich experiences
their clients can interact with
directly, not by replying
simply with text.

First impressions & Expectations
“Take me to the moon, Bot!”

Introduce yourself
You only get one or two lines,
so keep it short and to the point.
Having no visible interface means:
This thing can do whatever I ask him,
so I’m going to ask him to make me
a sandwich.
I have no idea what I’m supposed
to do now, so I’m just going to freeze
and stare at the screen.

Meeting synced! Did you know I can also find
and book a conference room?
Ping! There is a meeting coming up in one hour.
Would you like me to order lunch for 3 people?
Once the first interactions
are successful, the robot can be
less verbose and more efficient.
Proactively suggest things to do.
Great! Find us some sushi!
Ping! There is a meeting coming up.
Would you like me to order lunch for 3?

Validating input
_Give hints _Aknowledge
Small please! Thanks. Great! Find us some sushi!
Ping! There is a meeting coming up.
Would you like me to order lunch for 3?
What size t-shirt are you?
We have small, medium, large.
Got it. Size small.
And what color would you like?

Explain what went wrong...
brlbrbl
gray
I’m sorry, “brbrbl”? Is that a color?
We have white, gray, brown.
What color would you like?
Cool! So a large gray t-shirt!

Awaiting critical input
Sometimes you need a piece of information
that you absolutely cannot proceed without.

Schedule a new meeting tomorrow?
Am I busy tomorrow?
To do my job, I need access
to your schedule.
Follow this link to connect
your calendar.
Seriously, you need to connect
your calendar here to enjoy
my scheduling superpowers.
I can’t wait to start working
on your schedule!
Please connect your calendar
so I can do my magic.

What you need to consider
BUSINESS CASES FOR BOTS

(Most valuable bot}
Start with looking at the overarching
business objectives.
_What are the business priorities this year?
_Acquisition?
_Retention?
_What KPIs can we identify to measure value?
_What point in the customer journey does this ﬁt?
YOUR MVB

_Brand guidelines
_Tone of voice
_Consumers have diﬀerent degrees of tolerance
_Script out anticipated conversations and review
_Decide how much of your UI
will be conversation driven rather than manual
_Quality NLP and some degree of AI
or machine learning.
_Lean on the universal UI
_Remember: GUIs > DOS
Conversational Design
Vs User Interface Design
Personality

_Store data securely and inline with any privacy agreements
_Don’t ever break Facebook or any other platforms’ guidelines
_Brand reputation can be fatal.
_Pick a solution that can scale up or down
quickly.
_Allow reprioritisation and user testing
to happen throughout the build
_Establish a group of testers
_Market your bot.
Security, Rules & Data
Scale
Development, Testing & Promotion

Chatbot workshop introduction.#digitized16

More Related Content

What's hot

Viewers also liked

Similar to Chatbot workshop introduction.#digitized16

More from Warply

Recently uploaded

Chatbot workshop introduction.#digitized16