Chatbot Concepts and Terminology

This topic introduces the key chatbot terms you must know before working with DRUID bots.

Artificial Intelligence (AI)

Artificial Intelligence (AI) is intelligence demonstrated by machines. It encompasses everything from Natural Language Understanding (NLU) to machine learning.

Channel

A channel is where the chatbot lives, the place where two-way conversation can happen.

You can build DRUID bots and deploy them across various channels. If you have employee-facing bots, you might consider deploying them on Intranet Web Pages, Microsoft Teams, or Slack. If you have customer-facing bots, you might consider deploying them on your public website, Facebook, WhatsApp, Skype, or in custom Mobile Apps.

DRUID Bot

A DRUID bot is a virtual agent who handles conversations with your end-users. It is a natural language understanding computer program, which translates end-user text or audio during a conversation to structured data that your apps and services can understand.

You design, build and train the DRUID bots to handle the types of conversations required for your system. End users will be able to interact with DRUID bots, using voice or text, to access information, complete tasks or execute transactions or actions.

Context

Similar to the natural language context, the context controls the flow of the conversation. During each conversation flow, you find information saved within the context cached in the bot memory in the form of entities and variables.

Dialog

A dialog is a conversation that defines responses to the defined intents. You find the Dialog as Flow In the DRUID Platform

Druid Local Variable

Druid local variables defined in flows persist during within the conversation during the flow execution.

Integration Context Variable

Integration context variables are assets persisted during the connector task execution. They are used in custom authentication. Druid keeps them in memory until using them in the authorization call to the business API.

Intent

An intent represents the purpose of a user’s input (known as utterance). Intent categorizes the user’s intention for one conversation turn / dialog.

For a chatbot, you define many intents and bundle them together with dialogs into flows. You train a DRUID bot using training phrases, which are examples of what the user might input for the given intent. Whenever the end user writes or says something, the DRUID bot matches the end user’s expression to the best intent.

For each intent, you can define actions to trigger specific actions defined into your system. When the DRUID bot matches the intent, it provides the action to your system.

In the DRUID ChatBot Platform, you find the Intent as Flow.

Flow

Flow = Intent + Dialog

Flow is a special term in the context of DRUID bots. It represents the configuration of a dialog between the end-user and the DRUID chatbot. A DRUID flow consists of both intent and dialog. It has a tree-like structure, where you can configure logical decisions to provide different paths based on context, actions or user input.

Entities

Entities are variables that compliment or modify the intent. An entity is an object (snippet of information) the chatbot can understand and complement the intent in order to serve the correct answer.

Entities are typed memory slots. The entities keep the conversation context. In the DRUID ChatBot Platform the entities are structured objects, with attributes (or fields) and relations between them. The collection of entities within the bot create the Bot Informational Model.

Example: Account entity. A person or organization, which buys offered goods or services from your organization. Includes fields like Name, First Name, Last Name, Email, Orders (collection of Orders), Invoices (collection of Invoices), Payments (collection of Payments).

Machine Learning

Machine Learning (ML) is the AI field that focuses on making machines learn. In the context of chatbots, ML improves the bot ability to answer complex user queries over time.

Natural Language Processing (NLP)

Natural language processing (NLP) is a field of AI. It encompasses everything that relates to a machine understanding human input. To do that, an NLP engine uses many tools like: Natural Language Understanding, sentiment analysis, tokenization, and more.

Natural Language Understanding (NLU)

Natural Language Understanding is the process that examines an utterance and extracts its entities and intent. It allows a machine to understand what a user is saying.

Utterance

Utterance is whatever the user says. The DRUID bots will extract from the Utterance the Intent and the Entities essential to carry a conversation / dialog following the flow matching the intent.