the age of conversational agents
TRANSCRIPT
The age of conversational interfaces
Drop Your Picture HereHi, we are faction xyz
We are an applied A.I. service provider
http://www.faction.xyz - @factionxyz
Difficult to ignore the conversational opportunityWith billions of users exchanging messages and interacting with each other over messaging platforms, a business can no longer ignore the potential and opportunity of getting hands-on with “chat bots”.
Over 94% understandingTechnology maturity
New and improved methods for natural language understanding have produced unprecedented levels of accuracy in understanding and dealing with natural language.
Channel maturity
With over 1 billion users, exchanging over 60 billion messages per day on Facebook and WhatsApp, and spending over 1 hour per day on messaging platforms,
Over 60 billion messages / day
A brief history of conversational agentsPersonal assistants, virtual agents, chat bots or conversational agents. However you want to call this technology, they all hint for the need for humans to interact with machines in a more natural and frictionless manner when dealing with complex interactions.
1966, ELIZA by MIT AI Labs
1972, PARRY by Stanford University
1988, Jabberwacky by Rollo Carpenter
1992, Dr. Sbaitso by Creative Technology
1995, ALICE by Richard Wallace
2006, Watson by IBM2008, Siri by Apple
2012, Google Now by Google
2015, Alexa by Amazon
2015, Cortana by Microsoft
1950Alan Turing on Computing Machinery and Intelligence
1957Noam Chomsky on Syntactic Structures
1969Roger Schank on conceptual dependency theory for NLU
1970William Woods on augmented transition networks
1990sGeneral use of machine learning boosts NLP methods
> 2006Use of deep learning, increased CPU and data
Building the frictionless customer experienceA seamless user experience between machine and human is the general objective for any company that is using technology to scale their business or deliver a competitive service to their constituents.
While mobile has trumped web in terms of usability by using tactile interfaces, conversational interfaces might trump mobile by using natural language.
The evolution of shrinking interfaces
Size of a roomMainframe
Fits in your handSmartphone
Fits in a bagDesk & Laptops
Fits on your wristWearables
Pervasive interfacesInvisibles
The types of conversational interfaces
DedicatedMessaging
Voice HUBsAppliances
IntegratedSmartphone
Existing ChannelsTraditional
The conversational channel strategy
The types of conversations
AGENTGeneys, etc.
SOCIALSparkCentral, etc.
INTELLIGENTChatlayer, etc.
One to one manual conversations
between user and agent
Supporting users through social
channels
Using A.I. to automate
conversations
Drop Your Picture Here
The support business caseLowering the support cost through natural language processing (NLP) and automating the
conversation, so that the bulk of the load is handled by automated and intelligent platforms. Built on ROI. Reach an ROI in less than a year (*), making a positive business case.
Drop Your Picture Here
The user experience & brand caseIncrease brand visibility and proximity through new and innovative conversational user
experiences. Reduce churn, increase conversions or raise brand awareness. Built on vision.
Top 5 learnings of having built over dozens of botsSome of our learnings over the past five years, condensed in five bullet points.
The UI elements of a conversation is text
Narrow now. Expand later.
Develop a personality without the uncanny valley
Is it faster through a click or just a gimmick?
Sometimes people want to talk to … people
The components of a successful chatbot
UIVoice, SMS, Facebook, …
AINLP, NLG, Context, …
SIBackend, API, …
Develop a fitting channel for your user
Use a context-aware natural language processing engine
Integrate into data and intelligent
backends
Using chatlayer to build a successful interfaceSelecting a solid enterprise platform to build a versatile and intelligent conversational interface is a key differentiator when formulating a conversational strategy.
Use a context-aware natural language processing (NLP) to build enterprise graded conversational solutions.
Features:• Design conversational flows in a graphical interface• Train the NLP engine in a user friendly manner• Handle context-aware conversations• …
Conversational platform:Chatlayer
The Artificial Intelligence state of affairs
Intents, entities, and flows.
Inside an NLP engine
Contact Us
Address:
Faction XYZRijnkaai 37 Bus 192000 Antwerp
Phone:+32 3 500 87 09
Mail:[email protected]