Introduction to Content Intelligence

Manu da Silva Updated by Manu da Silva

The Content Intelligence is an exclusive feature from Weni Platform.

Born out of our continuous innovation in Artificial Intelligence studies, a new type of intelligence is available in our module: Content Intelligence. With it, you can register informative texts and ask questions to the intelligence based on its content, without needing to train it. This is made possible through powerful natural language processing (NLP) mechanisms.

In this article, we will discuss the main elements of Content Intelligence and present a brief comparison between Content Intelligence and Classification Intelligence (also known as Entity and Intent).

Elements of Content Intelligence

Although it is a new type of intelligence, several elements are familiar to those who have used the classification model, such as: name, categories, and description, as well as support for hundreds of languages and easy integration with Weni Flows.

The biggest differentiator of Content Intelligence, however, is the Knowledge Bases. They are responsible for recording the content and language of an informative text. An intelligence can contain multiple knowledge bases, each containing a subdivision of the main topic of the intelligence and/or the translation of the text from another knowledge base.

An example of using multiple bases is in an educational context: we can create an Intelligence to discuss the subject of High School Chemistry. In it, you can add a base for each topic, such as General Chemistry, Organic Chemistry, and Inorganic Chemistry.

Another example relates to a company's day-to-day operations: you could create a Frequently Asked Questions (FAQ) Intelligence, storing a specific subject in each knowledge base: finance, promotions, or service information.

When to Use Content Intelligence

Typically, Content Intelligence delivers good results when it stores texts that provide information about a specific topic.

However, the choice between the two types of intelligence should be analyzed on a case-by-case basis, depending on the needs of your project. To assist in the decision-making process, here is a brief comparison of the two types of intelligence:

Content Intelligence

Classification Intelligence

Needs to be trained

No

Yes

Ideal for informative texts

Yes

No

Ideal for individual phrases

No

Yes

Information feeding method

Informative texts

Phrases with entities and intents

Confusion Matrix View

No

Yes

How did we do?

Integrating Intelligence into a Project on the Weni Platform

Integrating a Content Intelligence

Contact