Welcome!

Machine Learning Authors: Pat Romanski, Yeshim Deniz, Liz McMillan, Elizabeth White, Zakia Bouachraoui

Related Topics: @ThingsExpo, Machine Learning , Artificial Intelligence

@ThingsExpo: Article

To Bot, or Not to Bot | @ThingsExpo #AI #IoT #M2M #MachineLearning

Understanding Chat Bots

I developed a bot.  Last weekend I opened the website https://rundexter.com/bot and developed a bot, which I then integrated with Twilio for messaging.  I named it BeccaBot after our daughter.  Just to be clear, her name is Becca, not Bot. It was a bot designed purely to freak-out our daughter.  It was highly successful.  Here are some things I learned.

You tell the bot to look for specific words or even phrases and then act upon them in specified ways.  You can answer with text, or a website link, or an image, etc.  You can ask for a name, and program the bot to remember the name. For example:

User: Hello

Bot: Hi, what's your name?

User: Becca

Bot: Hello Becca!

Bot: I've been reading your Facebook page and see you were in Seattle recently with Claire.

That last part I added just to freak-out my daughter - a father's prerogative. The bot was not programmed to read her Facebook page, although it's possible if Facebook made that API and granted permission.

You can delay sending responses so the bot looks slow at typing - like a human.  You can lead the human by asking for choices:

Bot: Would you like to learn "more information", or "exit" now?

More sophisticated bots can integrate with all kinds of APIs so they can reference the weather at your location, traffic conditions, and even news headlines, etc.  Simply by referencing connected data and inserting it into conversations.

Bot: In what city and state do you reside?

User: Chicago, Illinois

Bot: I noticed it has been raining in Chicago this morning.  Perhaps that is the reason traffic was so bad.

Bot: Heh!  What about the Cubs victory last night!?

I learned you can create multiple topic trees like - Default Conversation, Problems/Complaints, Resources, Weather, Survey Questions, etc.  As you are developing a conversation between the user and the bot you can turn down various topic trees, and then return to the main script.

More advanced bots can access sophisticated algorithms that allow you to reference all kinds of databases, calculations and processes to provide answers to questions.

User: What is my mortgage payout for my 104 Main Street home?

Bot: As of March 15th your payout is $124,675, that includes the payment received on March 13th, but does not include any payments that might have arrived yesterday.

Bot: What about Da Bears last Sunday?

What I learned during my little bot-prank exercise on our daughter is that bots are scripts - scripts with algorithms, which can request, save and insert data.

I learned that voice-based chat-bots convert audio words into text, which the underlying text based bot can use. The audio word recognition and audio word feedback is simply another layer on the chat-bot solution stack.

I learned sentiment layers could be added. Layers that recognize particular words as "angry," "frustrated," "happy," "sad," "glad," etc. Each of these words can help the bot respond in a different and more appropriate way.

User:  I am NEVER doing business with you again, you knucklehead!

Bot: Having looked into your account and payment history, I can tell you we don't want your business either.

Bot: By the way, is your wife available to speak? She is much nicer.

I learned sensors, sharing data in real-time, can add reality to the conversation.

Bot:  You have been opening the refrigerator a lot lately - 67% more than usual.

Bot: Summer's coming and the elastic in your Speedos do have limits.

Today, Bots are only as smart as the developer making them.  In my case there was no concern that singularity would evolve or erupt from my efforts.  Although I did achieve the level of creepy according to my daughter who spent 10 minutes texting with the BeccaBot as it explained to her how wonderful I am.

I invite you to watch my latest short video on digital technology trends and strategies:

Download the full report with charts and data sources here.

Follow Kevin Benedict on Twitter @krbenedict

More Stories By Kevin Benedict

Kevin Benedict serves as the Senior Vice President, Solutions Strategy, at Regalix, a Silicon Valley based company, focused on bringing the best strategies, digital technologies, processes and people together to deliver improved customer experiences, journeys and success through the combination of intelligent solutions, analytics, automation and services. He is a popular writer, speaker and futurist, and in the past 8 years he has taught workshops for large enterprises and government agencies in 18 different countries. He has over 32 years of experience working with strategic enterprise IT solutions and business processes, and he is also a veteran executive working with both solution and services companies. He has written dozens of technology and strategy reports, over a thousand articles, interviewed hundreds of technology experts, and produced videos on the future of digital technologies and their impact on industries.

CloudEXPO Stories
With more than 30 Kubernetes solutions in the marketplace, it's tempting to think Kubernetes and the vendor ecosystem has solved the problem of operationalizing containers at scale or of automatically managing the elasticity of the underlying infrastructure that these solutions need to be truly scalable. Far from it. There are at least six major pain points that companies experience when they try to deploy and run Kubernetes in their complex environments. In this presentation, the speaker will detail these pain points and explain how cloud can address them.
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-centric compute for the most data-intensive applications. Hyperconverged systems already in place can be revitalized with vendor-agnostic, PCIe-deployed, disaggregated approach to composable, maximizing the value of previous investments.
When building large, cloud-based applications that operate at a high scale, it's important to maintain a high availability and resilience to failures. In order to do that, you must be tolerant of failures, even in light of failures in other areas of your application. "Fly two mistakes high" is an old adage in the radio control airplane hobby. It means, fly high enough so that if you make a mistake, you can continue flying with room to still make mistakes. In his session at 18th Cloud Expo, Lee Atchison, Principal Cloud Architect and Advocate at New Relic, discussed how this same philosophy can be applied to highly scaled applications, and can dramatically increase your resilience to failure.
Machine learning has taken residence at our cities' cores and now we can finally have "smart cities." Cities are a collection of buildings made to provide the structure and safety necessary for people to function, create and survive. Buildings are a pool of ever-changing performance data from large automated systems such as heating and cooling to the people that live and work within them. Through machine learning, buildings can optimize performance, reduce costs, and improve occupant comfort by sharing information within the building and with outside city infrastructure via real time shared cloud capabilities.
As Cybric's Chief Technology Officer, Mike D. Kail is responsible for the strategic vision and technical direction of the platform. Prior to founding Cybric, Mike was Yahoo's CIO and SVP of Infrastructure, where he led the IT and Data Center functions for the company. He has more than 24 years of IT Operations experience with a focus on highly-scalable architectures.