1. Home
  2. Kore.ai Conversational Platform
  3. Concepts
  4. Knowledge Ontology

Knowledge Ontology

Kore.ai Knowledge Graph helps you turn your static FAQ text into intelligent, personalized conversational experience. It goes beyond the usual practice of capturing FAQs in the form of flat question-answer pairs. Instead, the Knowledge Graph enables you to create an ontological structure of key domain terms and associate them with context-specific questions and their alternatives, synonyms, and Machine learning-enabled classes. This article provides an overview of a Knowledge Graph using the following sample ontology of a bank.

Components of Bot Ontology

Terms or Nodes

Terms or Nodes are the building blocks of an ontology and they can be used to define the fundamental concepts and categories of a business domain. As shown in the image below, you can organize the terms on the left-hand panel of the Bot Ontology window in a hierarchical order to represent the flow of information in your organization. You can create, organize, edit, and delete terms from there. For easier representation, we identify some special nodes using the following names:

Root Node

Root node forms the topmost term of your Bot Ontology. A Knowledge Graph consists of only one root node and all other nodes in the ontology become its child nodes. Root node takes the name of the bot by default, but you can change it later.

First-level Nodes

The immediate child nodes of the root node are known as First-level nodes. There can be any number of First-level nodes in a graph. It’s recommended to keep First-level nodes to represent high-level terms such as the names of departments. Examples: Personal Banking, Online Banking, and Corporate Banking.

Leaf Node

Any node to which question-answer sets are added is called their Leaf Node, be it First-level, Parent, or Child.

Parent-Child Relationship

Depending on their position in the ontology, a node plays different roles, for example, it becomes a Parent Node when a subcategory or Child Node is added to it. A parent node is in simple terms a category that may have one or more subcategories under it, called the child nodes. Examples: Loan is the parent node of Home Loan and Personal Loan. Personal Loan again has two child nodes: Rate and Fees, Help and Support.

Note: A parent can have any number of child nodes, but a child can only have a single parent node.

Synonyms

Users would use a variety of alternatives for the terms of your ontology. Knowledge Graph allows you to add synonyms for the terms to include all possible alternative forms of the terms. Adding synonyms also reduces the need for training the bot with alternative questions. For example, the Internet Banking node may have the following synonyms added to it: Online Banking, ebanking, E-banking, Cyberbanking, and Web banking.

When you add a synonym for a term in the Knowledge Graph, you can now add them as global synonyms. Local synonyms apply to the term only in that particular path, whereas global synonyms apply to the term even if it appears on any other path in the ontology.

To add local synonyms, type them in the box under Path Level Synonyms. To add Global synonyms, click Add New under Knowledge Graph Synonyms and enter them.

Classes

Classe is a collection of typical end-user utterances that define the nature of a question when they ask for information related to a term. A class is a common collection that can be applied to multiple terms across your Bot Ontology. The following image shows a class called Issues that consists of common user utterances used to talk about issues that are applied to the Login Issues node.

Note: Classes also help you filter nodes based on associated user utterances. So, if the user types an utterance that is present in a class, the bot only searches the nodes to which the class is applied. If the utterance is present in any other node to which the class is not applied, the node is ignored by the bot. For example, Issues class includes an utterance called “It is not working.” If a user types “My password is not working,” the bot searches only those nodes to which the Issues class is applied and not others.

Questions and Answers

These are the actual questions associated with your business domain and their corresponding responses. The question-answer pairs must be added to relevant nodes in your bot ontology. A question may be asked differently by different users and to support this, you may associate multiple alternate forms for each question.
Jump to Creating a Knowledge Graph.

Was this article helpful to you? Yes 4 No 1