All Things Techie With Huge, Unstructured, Intuitive Leaps

The Birth of a Car-Selling Monkey --The Evolutionary Cycles of My Chatbot


Honest John is evolving, and it's not taking millions of years. Honest John is my chatbot that will sell cars either online or on at dealership kiosk. This side project of mine started when friends of mine wanted my help in buying a new car, and they had a bad experience with a high-pressure car salesman who was a stranger to the truth. My friend had said that she would rather negotiate with a computer and that is how Honest John was born.

I fired up my Software Development Kit, opened a framework, and it wasn't hard to get some running code quickly. Unfortunately, the earliest of version of Honest John was quite stupid. He was merely a parrot. And if you stumped him with a question that he didn't understand, he would give an innocuous reply and ask a random question. Obviously we had a long way to go.




The conversation was quite two-dimensional. I was using AIML which is Artificial Intelligence MarkUp Language. The way that it works, is that it recognizes a predicate in the input text, searches through its library for that predicate and spits out a response. The first task on my part was to add some humanity and politesse to it. You can't expect to sell something to a human unless you act like a human yourself. So I had extensive edits to the AIML to make it more human.


The personalization of the conversation was necessary. To do that, I had to write a user object that remembered things about who the chatbot was talking to. Honest John had to remember if he was talking to a woman or a man, and the person's name. It was functional now, but it was like stick figures talking to each other.

Before I went further into a more human chatbot, it needed some smarts. Most chatbots out there are incapable of logic and error correction. If Honest John were to negotiate, he would need to evaluate arithmetic expressions so that he could talk money and price. He needed to be date/time aware. He needed to have logic to recognize if a bid was lower than the previous one, and needed to react appropriately. Even though there are wonderful recursive elements in AIML, this sort of stuff was way to complex for AIML to handle.


So the answer was to intercept the inputs and AIML outputs, and send them to a parser that would determine if the conversation needed remediation by an Arithmetic Logic Unit or a plain old Logic Unit in the code. Luckily this was easy to do, because my framework is a J2EE (Java Enterprise Edition) framework that is capable of complex actions like creating any objects, stuffing them with data and holding them in memory for easy access. Because of unique, time-aware Java classes and multi-threading, I could take the conversation, dissect it and send it to appropriate parsers which kicks a new thread to do some work on each element, wait for the response, and finally spit out a response to the user that is intelligent. The other element that most chatbots do not have, is that they can record the conversation history, but they cannot traverse it, regress to a certain point in the past, and understand past statements. I had to create a live chat record in memory, along with meta-data and logic to correct those faults. In the middle of a negotiation, if things got off the rails, the chatbot could go back to the last point of agreement and start again from there.

Now we were getting somewhere. We had the beginnings of a bot that could negotiate. However we still had the problem of sophistication -- it was just two stick figures talking to each other. Humans need emotions and empathy, and bots need to live in that domain too -- however artificial it may be.


The Holy Grail of mixing digital smarts with the human milieu was first appreciated, understood and defined by Alan Turing, when he devised the Turing Test, in which a human could not detect that they were talking to a computer. That requires an EQ and an IQ (an Emotional Quotient as well as an Intelligence Quotient). Honest John doesn't even pretend to be able to pass a Touring Test. But the conversation has to become more three-dimensional in human terms.

Understanding emotion in the user and reacting to it, is the beginning of artificial personality. This is important to Honest John in the selling process.



Suppose that in the middle of negotiating, Honest John detected that the user was getting angry, bored or any other negative emotion that would be the thin edge of the wedge in precluding a sale -- after all, his whole job is to sell cars. The chatbot would need to have the detection circuits to understand that. More importantly, Honest John would need to take remedial action, and either soften or harden his tone. Moreover, he would need to alter the negotiation strategy, either becoming more or less hard-nosed depending on the specifics.

For that reason, Honest John needs to have several strategy processes defined, and they all relate to pre-defined personality aspects. Honest John needs to adjust the tone of the negotiations. To do that, not only does he require the right words, but also the right actions. If the negotiation price is in the ball-park of a sale, and he detects that the user may walk, Honest John needs to sell the car. If he is not in the ballpark of a selling price, he either needs to adjust his negotiating increments depending on the temperament displayed by the human on the other side of the screen. He must be capable of being "fuzzy".

So all in all, Honest John needs to have a range of sophisticated behaviors before I let him out in the wild, I am working on it. He does have AI networks built into the stream of things. He has such Natural Language Processing (NLP) tricks like Bag-of-Words and other algorithms to help him decipher things. I think that the tools are all in place in Honest John innards. All that I need to do, is integrate them, expand them and polish them. Who knows, you may meet Honest John one day in a showroom or online, and you will remember his evolutionary history.

IoT, Formula 1 Racing, Mercedes Team ... and Me !!



I am honored to be chosen as winner  of #tatacommsf1prize and one of three grand prize finalists in the Formula 1 Connectivity Innovation (Connected Operations) Challenge for the F1 Mercedes Petronas AMG Racing Team tech supplier.

 My proposed solution brings a new innovative slant to the IoT of Formula One Racing, and I look forward to meeting Lewis Hamilton in Abu Dhabi for the final F1 race of the year, where I present my solution.  Thanks to Tata Communications, the infrastructure supplier to the Mercedes team for this incredible opportunity and the trip to Abu Dhabi.

I look forward to having my connectivity solution possibly make an impact on the future of F1 Racing.  This is a major thrill.   http://www.pressreleasemanager.co.uk/viewPressRelease.asp?ID=2D1942F4-BDEC-4951-BBEA-C6A00A8D53AA