In the first part of this product sheet we showed how Natural Language Processing and Scripter can be used to develop a Chatbot.

In this second part of the product explanation we will show how you can build an intentions dictionary to map the relationship between relevant terms and then define possible intentions to the chatbot so that a reasonable response can be generated.

In order to build this dictionary, the supervisor will utilize a user interface in Scripter Designer that allows the chatbot designer to go through a series of logical steps to create the most relevant responses to any inbound chat message.

In figure 1 below, the Intentions Analyser is used to extract intentions from words customers use. Verbs such as "like" or "want" are identified and grouped as "Positive Intention".  Nouns such as "TV" or "package" identify the items that the text is concerned with.

Building Intentions from groups of Intention Words (fig. 1)

Having identified individual words in a phrase and flagged those individual words as having an intent, all of the words can be combined to identify the overall intent of the phrase.

Let's say the NLP identifies words that are contained within the "PositiveIntentions", "TVPackage" and "Upgrade" intents.  The combination of these three groupings allows the NLP system to identify an overall intent to the phrase, in this case that the customer wishes to upgrade their TV package (see figure 2).

List of intentions mapped to responses (fig. 2)

There may be many combinations of intentions, each one having a different meaning and requiring a different response.  To accommodate this, it is possible to build a library of intentions and to assign to each intention a response which can be sent back to the customer.

Additionally, Sytel's Scripter engine can be triggered to perform other tasks besides simply responding with text.  Tasks could include transferring the session to a live agent with the skills needed to handle the session, or performing a lookup against a database to get an account balance and returning the result to the customer.

Within Sytel's product you can build complex and highly functional chatbots that can interpret complex sentences used by customers and act on those messages in many different ways.  Well-configured chatbots deliver an excellent customer experience that can save a customer time and can increase efficiency in the contact centre.