ENTITIES&SMART MATCHING IN POWER VIRTUAL AGENTS

In this blog, we’ll examine Power Virtual Agents’ Entities and Smart Matching. We’ll walk over an instance where an airline bot assisted a passenger in locating their boarding time.

In the Dataverse, entities are not the same as tables. In PVA, entities make natural language references to information. This includes things like people, places, and other things. Let’s examine a case in point.

Imagine you have a flight bot that notifies you when it is time to board the aircraft. Let’s create a structure that will house the passenger boarding group number.

Click on Entities and select New Entity.

We see 2 options available – Closed List, and Regular Expression (RegEx). Let’s go with Closed list:

Enter a name and description, and start to enter in the list items. Note the Smart Matching, we will talk about this later i have entered only 3 groups and click save.

Now let’s use the group.

Go to Topics and create a new topic. We will call it Boarding Time, and add a trigger phrase “When can I board”:

Now let’s ask a question We will ask What is your group number, and get the user to select our Group entity options

Now add new Condition and select a group=1

I have add the three condition and add the message as shown in the below screenshot

Let’s try this out. We see the bot picks up the entity and uses it properly

That’s because we have Smart Matching enabled on our Group entity. This can help match “misspellings, grammar variations, and words with similar meanings”.