Understanding text analysis

Text analysis is an important aspect of conversational channels that enables a Pega Platform application to intelligently and seamlessly interact with a user in a natural conversational manner. Text analyzers examine user input one by one using natural language processing (NLP), adaptive analytics, and artificial intelligence. To use text analysis in conversational channels, you define one or more text analyzers for Pega Intelligent Virtual Assistant (IVA) or Pega Email Bot in your application.

Text analyzer functionality

Text analyzers detect the following information categories:

Topic
The general subject, an intent of an email, text message, or a voice command. An IVA or an email bot links all suggested cases and suggested responses to topics. For example, an email bot can determine that the topic of an email relates to a car insurance, and then open a car insurance business case.
Entity
The text contains proper nouns that fall into a common category, for example, a person, location, date, organization, or ZIP code. You can configure the IVA or the email bot to automatically assign the entities that they detect to properties of a new business case.
Sentiment
The opinion that a user expresses in an email, a chat text message, or a voice command: positive, neutral, or negative. An email bot can detect a negative sentiment of a user email, and then escalate the issue by automatically forwarding that information to a customer service representative.
Language
The language of an email, a chat text message, or a voice command. An email bot can detect the language of a user email, perform text analysis in that language by using NLP, and then automatically send a reply in this language to the user.

Text analysis in an email bot

Each text analyzer definition for an email bot supports advanced text analysis of email header, body, subject, and attachments, including image files. To perform text analysis of image-based file attachments, you use the Pega Document Processing Service (DPS) component that you install from Pega Marketplace.

With text analysis and intelligent email routing, an email bot interprets an email and determines how to correctly respond to a user. This functionality also improves the triage process by creating a correct business case with the help of the email topic.

For example, when an email bot detects the email topic and entities using text analysis, the bot automatically forwards the email to a work queue, sends a reply back to the user, or opens a top-level business case, depending on the routing conditions that you define.

To refine the text analysis capability for your email bot, you can define multiple text analyzers to serve the same or different purposes.

For example, you can define one advanced text analyzer to perform text analysis of only the email body, and then define another text analyzer to analyze the email attachments.

Text analysis in an IVA

A text analyzer that you define in an IVA provides advanced text analysis of user input, including text voice commands. Each text analyzer helps the system determine the best matching response by using NLP, adaptive analytics, and artificial intelligence. For more information, see Exploring text analyzers.

For example, an IVA performs text analysis and detects a topic, language, and sentiment of the user input. The IVA uses this information to find the best matching response. Based on the topic, the IVA opens a business case; based on the sentiment, the IVA displays a menu of commands; based on the language, the system sends a reply message in the same language to the user.

You can define multiple text analyzers for an IVA to serve the same or different purposes.

For example, you can define one advanced text analyzer to run within a case context, and then define a second text analyzer to run outside of a case context. When an IVA starts a business case during an interaction with a user, the system uses the first text analyzer to find the best matching response. When an IVA does not start or already closes a case in a user session, the system uses the second text analyzer to find the best matching response instead.