Softdial Contact Center (SCC) from Sytel provides a complete solution platform for building any kind of chatbot.
Sytel's Scripter provides a Text Processing Library to build and support chatbots. It is possible to build up from a simple dialog with direct questions to customer, to a more sophisticated dialog by using the Natural Language Text Processing facilities in Scripter.
As an example of how Scripter's Natural Language Text Processing engine works, let's imagine that the conversation can be initiated by either the chatbot, or the customer. A typical use case for this conversation might be an upgrade of a TV package. First we confirm the customer's ID and then we ask an open question. At this point, Scripter can use Natural Language Text Processing to define the customer's intention.
Let's say we have the following dialog flow as reference:
Figure 1— An example of a chatbot dialog flow using Softdial Scripter
Scripter's Natural Language Text Processing engine splits the customer message into sentences and words, classifying the words as follows:
Figure 2— An example of an interpreted dialog flow using the Softdial Scripter Natural Language Processing Library
As result of this process we then have a list of terms to cross reference with a knowledge base to define a chatbot action (for example, upgrade the TV package). In this case the customer wrote "I would like to upgrade my tv package". Analysis of this sentence returns a group of terms that will be used to define the intention of this customer. For the above sentence, this is the list of terms: like, upgrade, tv package. This list can now be used to see if there is a matching action.
Let's say we have, in our knowledge base of actions the following relationship:
Figure 3— An example of an action definition using a multi-term dictionary search available from Scripter Text Processing Library
So, the likely next action is to present a choice of upgrade packages and ask which one is wanted. The script flow will keep this loop until the final action which might be to send a message to the relevant ERP to proceed with the chosen package upgrade.
This is a very simple and logical example of one of the possibilities that Softdial Scripter offers as a tool set to build chatbots that will handle specific scenarios. All these activities are supported by access to the customer's data and the creation and use of special dictionaries, supported by Scripter.
There is no right way or wrong way of developing such chatbot applications, with the process depending upon the nature of the activities covered by the chatbot and how the chatbot owner wants to engage with customers. In practice a number of scenarios might be developed by Scripter, before the one(s) with the best responses is/are chosen.