Intents

Understanding User Intentions

Understanding Intents

Intents represent the goals or purposes behind a user's interaction with Parloa. They are composed of utterances, which are specific expressions or phrases users may use when engaging with the bot. An intent could be as straightforward as a greeting or as complex as a request for detailed information.

Within the Speech Assets, the Intents window is your central hub for managing user intentions.

The Intents tab lists all potential user goals, labeled as Intents. Each intent corresponds to a distinct action or request, like signaling a problem or seeking support.

Managing Intents

Here are common actions you can perform with your intents:

Creating Intents

1. Click the button.
2. Click Custom Intent, displayed on the right pane.

3. Enter the name of your intent and click or press Enter.

Renaming Intents

1. Hover over the desired intent.

2. Click on icon in your list of intents.

Deleting Intents

To permanently remove an intent:

1. Hover over the desired intent.

2. Click on the icon.

Intent Identification Workflow

Parloa processes potential intents through a hierarchical matching system:

1. Initial attempt is to match with locally defined intents.

2. If unsuccessful, search within the Global State for a possible match.

3. Should that fail, refer to the local 'else' pathway.

4. Absent a local 'else', employ the Global State 'else' pathway.

5. For advanced scenarios, use intent.rankingAll to evaluate recognized intents against custom thresholds.

Customizing Intents for Different Platforms

When managing intents for multiple platforms, you can customize them to fit each platform's specific requirements without needing to create new intents from scratch.

Intent Configuration Window

1

Intent name.

2

Current selected platform tab – customize settings for each platform here.

3

Group assignment – Add intent to a group by clicking the Not Grouped button, as described here.

4

Platform availability toggle – If off, the intent is excluded from the respective platform's speech model.

5 + 6

The default confidence threshold is set to 30%.

• For utterance-based intent recognition, the system uses NLU confidence scores directly.

• For description-based intent recognition, the system prompts the large language model (LLM) to provide a confidence score along with a stack-ranked list of recognized possible intents.

7

Fallback Intent trigger – This feature is crucial for managing situations where the confidence threshold for an intent recognition is not met.

• Toggle Off: If the toggle button is turned off for an intent, it will be excluded from the respective platform's speech model, rendering it inactive and unable to trigger under any conditions.

• No Fallback Selected: In cases where no Fallback Intent is actively toggled on any intent, Parloa defaults to using its built-in PARLOA.Fallback Intent. This ensures that there's always a safety net for unrecognized utterances, maintaining the flow of conversation without abrupt interruptions.

• Toggle On: Activating the toggle on a specific intent designates it as the new Fallback Intent. It's important to note that only one Fallback Intent can be active at any given time across all intents. However, even when set as the Fallback Intent, it can still be triggered by its specific utterances like any regular intent and will follow its defined routing paths, whether it's triggered as a fallback or through its direct utterances.

Advanced Configurations

You can further tailor your intents by:

• Specifying the platforms each intent is available on for targeted interactions.

• Modifying confidence thresholds to gain more precise control over intent recognition.

• Redefining the Fallback Intent for improved error handling. It's important to note that each project is equipped with a dedicated Fallback Intent to streamline your setup. When activating the Fallback option for multiple intents, be aware that selecting a new Fallback Intent will automatically deselect the previous one, ensuring a singular Fallback Intent is in effect at any given time.

Intent Groups

Intent groups enable you to categorize related intents. They offer a structured approach to handling your conversational model, simplifying modifications, and enhancing system maintenance.

Intent Group Example

Creating an Intent Group

1. Select the + Add Group button.

   

   The following displays:

   
2. Enter the name of the new group.

3. Click on Add Intent to Group to display a list of available intents.

4. Choose the intents you want to include and select the Create button.

Once your first group is created, any intents not assigned to a group will be listed under Not Grouped automatically.

Adding Intents to a Group

You can add an intent to a group using one of the following methods:

Method 1: Hover and Edit

1. Hover over the group to which you want to add the intent.

2. Click the + Add Intent button.

   

   The following displays:

   
3. Type in and add your intent to the group.

4. Confirm by clicking Done.

Method 2: Drag and Drop

Click and hold the intent you wish to group, drag it to the desired group, and release to drop it there.

Method 3: Intent Settings

1. Click on the intent you want to group.

2. Click the button, shown below:

   
3. In the dropdown menu, choose the group for your intent.

Renaming an Intent Group

1. Hover over an intent group and click the Edit Name button:

   
2. Enter the new name:

   
3. Click Edit to confirm the change.

Deleting an Intent Group

1. Hover over an intent group and click the button. A confirmation window displays:

   
2. Click the Delete button to confirm.

If there is only one custom group besides Not Grouped, deleting it will eliminate all groups. It's best practice to maintain at least two groups, including Not Grouped, to fully utilize intent grouping features.