The Silicon Review - Best Business Review Magazine 10 Best Startups of the Year 2019 Asia | Page 47

generation smart applications where
your data lives: whether on-premise
or in the intelligent cloud. Give
your customers innovative ways to
interact flawlessly with your product
by building advanced voice and
text-based conversational interfaces
powered by the Triniti AI.
Gain an in-depth
understanding of user
conversations with machine
learning
In natural conversation colloquiums,
abbreviations, acronyms and the like
are more common than is perfect
grammar and syntax. Provide
examples of what customers may say
during typical interactions with your
product and let Triniti’s intelligent AI
algorithms learn the true meaning.
Triniti is smart enough to:
•
•
•
•
•
recognise and comprehend
intent,
interpret discourse and
reactions,
extract entities and identify
pragmatics,
analyse feelings and emotions,
A whole lot more.
The Speciality of the
Company
Context Sensitive Spelling
Correction & Acronym
Expansion
Corrects misspelt words based on
user’s input. Knows not to correct
names, nicknames etc. Expand and
normalises acronyms like “acc” to
account, “xfer” to transfer. It is able to
standardise forms like “CreditCard” to
Credit Card.
Intent Classification
Auto-Calibrating Classifier that is
tolerant of differences in instances of
training data across intents, able to
differentiate between FAQ and non-
FAQ intelligently and detect adversity.
Sentiment & Profanity
Detection
It is able to detect if the user’s
current input is positive, neutral or
negative. The Products are also able
to detect if the user is being abusive
and able to respond appropriately.
Entity & Modifier Extraction
“We build
active
intelligence
culture,
contextual,
predictive &
personalised
experience
at every level
of customer
journey.”
Highly Trainable with trainable entity
linking and Auto-Calibrating features.
It is able to extract entities with high
precision and confidence. Extracts
and links Modifiers like “from” and
“to” to related entities. Also, it is able
to extract modifiers that modify the
complete intent, such as “minimum”
in “Minimum Balance”.
Smalltalk
It responds to most commonly-used
‘small-talk’ or ‘chit-chat’ that users
have with bots.
Engage
Personalise engagements
with customers via predictive
conversational offers.
SR
JANUARY 2019
47