eva by NTT DATA documentation
What's new in v3.4
Build your first bot in just a few minutes
How to create a bot
How to add a channel for a bot
How to develop a bot
How to train a bot
How to use bot template
Supported/verified third-party software
eva Installation in Azure Cloud
what is eva
Getting familiar with eva terms
List of most common words in alphabetical order
Profile with access to all eva resources
Application programming interface, a communication protocol that helps different apps communicate with each other.
Question-answering software that interpret users’ questions and answers them based on documents uploaded beforehand.
Process of making sure that a bot answers an intent within expected parameters.
Virtual agent capable of understanding human speech and responding accordingly.
Pre-built and ready-to-use framework templates that can be adjusted to different use-cases.
Massive import of intents to a bot knowledge base or examples/utterances to an intent.
Platform where the bot interacts with users.
Visual flow element that makes it easier to use the Workspace interface and to create and manage your bot.
everis proprietary Natural Language Processing (NLP) engine.
Name of the space that hosts all eva resources.
Software that processes human natural language.
Call to action. These are links or buttons on a page that encourage users to take a specific action. Sometimes it comes as an email form and a button with texts like “Subscribe”.
Feature in Cockpit where Admins and Editors can check bot’s performance through provided metrics.
Resource used when building the knowledge base that removes possible ambiguities or requests help from the user to complement their interaction.
Main feature in eva, it's the workspace where you can create dialogs and build your bot knowledge base.
Profile that can access all eva resources, except create, edit and delete users and bots.
User interaction, usually associated with an adjective, noun, product, services, etc., that can modify or complement the Intent.
everis virtual agent - Virtual agents building and managing platform.
Answer that can be evaluated by the user.
Process when a human agent takes over the conversation, usually because the bot doesn't understand the user, or the issue is not yet in the knowledge base.
eva allows integration with different cognitive engines, like Clever (everis), Watson (IBM), Dialogflow (Google), Luis (Microsoft), and others.
What the user has in mind when asking a question; represents its main purpose. Identifying these intents is critical to a chatbot success for it’ll start the conversation.
The sum of all flows, intents, answers, services and trainings in a bot.
Measure of a data to manage or analyze the bot’s performance.
A fallback answer that works as a flow when the bot doesn’t understand the user’s context.
Value added to configure software behavior.
The place where intents, answers, services, flows and trainings are stored.
Name of the process that allows the bot to learn to interpret user inputs; intent classification.
Answer that must be connected to an external API (depends on external sources). Your bot will have to look elsewhere to answer your user and you have to show where.
The person who is talking to the bot.
A sentence the user would say during a conversation with the chatbot. It is the most important component of an intent.
A way of receiving information between two applications.
The first message the bot sends to start off chatbot-human interaction. It is an answer cell and works as a unique flow.
Where you can visualize and design flows.
Using eva - Previous
How to use bot template
Next - Using eva