Next Gen Customer Experience through Chatbots

With Artificial Intelligence (AI) revolutionizing all walks of business and social life, enterprises are plugging in conversational AI to enhance cross-channel customer experience.

Chatbots provide greater convenience than apps — access to services and information that is frictionless and natural. Gartner predicts that more than 50% enterprises will opt for chatbots as the preferred channel over traditional mobile apps.

Chatbots, designed to mimic human conversations, have progressed past the peak of Gartner hype cycle expectations and the trough of disillusionment and are heading towards enlightenment and productivity.

One of our customer K2 leverages chatbots into understanding business issues, like team performance.

Building blocks of chatbot

A chatbot consists of -

• a front-end interface which connects to a variety of channels such as Facebook Messenger, Slack, Skype etc.
• Natural Language Processing (NLP) to parse user messages
• conversational logic that is key in maintaining the state of conversation with user and may include API calls to perform back-end tasks

The first thing with chatbots is they need to understand the user input. The chatbot can achieve this through a basic technique of pattern matching or advanced intent classification technique that uses machine learning. A pattern matching technique needs a list of possible input patterns, that are easy to read and maintain. This sounds fine, but there’s a problem in that they are built manually and do not scale in real use cases.

An intent classification approach relies on machine learning techniques and you need a set of user utterances to train a classifier. Once it understands what the user is saying, it can generate a response, based on the current input and context of the conversation.

Chatbots comes with different level of intelligence

The way chatbots respond to users depends on the level of its intelligence. The simplest way is to have a predefined conversation flow with scripted response for each user input. Most of the chatbots conversations that we have today are based on such predefined flows and while they get the job done, they’re not quite a satisfying user experience.

The most advanced approach is to use deep learning techniques to train a generative model, get a list of potential responses, and then score them to choose the best suited response. Deep learning algorithms mean that chatbots are able to learn from every interaction and incorporate that feedback so that their performance is continuously improves. This cycle of continual improvement means that they are refining themselves over time and it leads to a more “natural” user experience.

Generative models based chatbots are smart ones but need large amount of meaningful conversational data to reach a decent quality. This is an extremely hot area of current research and gives us grounds to hope that bots will get better at imitating humans.

Understanding the vendor landscape

In practice, there are two major types of chatbots: goal-oriented and general conversational. The former helps the user perform specific tasks, such as booking a ticket or ordering food. A conversational bot, on the other hand, does not necessarily have a well-defined intention. It focuses on having open domain conversation with user and it does not have to remember all the context of conversation.

To create a successful chatbot, the market is flooded with an array of platforms and tools, having different complexity levels, conversation intelligence, and integration capabilities. Leading technology giants like IBM, Google, Microsoft, Amazon, and Facebook are investing this space to provide frameworks and as-a-service platforms. The most common ones include Google Dialogflow, Amazon Lex, Microsoft Bot framework and LUIS service and IBM Watson Assistant.

There are multiple aspects to consider when implementing a chatbot. It is important to find the platform that fits your particular need. Open source NLP libraries such as Spacy and allenNLP are available for those who prefer a customized chatbot solution.

In conclusion, chatbots are “the new apps” and are poised to revolutionize user interface design. They have enormous potential and are set to become a competitive and customer experience differentiator for enterprises.