2.4 - Intent Categorization

Users are able to create categories using natural language descriptions to control how intents in user questions can be categorized. Typically, a question would be automatically categorized as FAQ, but users are able to provide additional custom categories.

Once categorization is enabled, the Curate and Analytics screens will change to show groupings around categories.

Users may move intents into categories manually through the Curate tab or the CSV download/edit features. The edits made will be used to train the system for future categorization events.

Add Intent Categories

Navigate to the Configure tab within NeuralSeek, and expand the Intent Categorization field.

• Click the light bulb icon to add a new category row.
• Add a title to the category in the first box on the left side. For example, add: Virtual Agents.
• Underneath, add a link to the source documentation containing information about the category. For example, add https://documentation.neuralseek.com/integrations/supported_virtual_agents/supported_virtual_agents/.

Describe Categories

The box on the right side is where users are able to add a natural language description of the category.

• Add a description of the category. For example, add: Virtual Agents that are supported by NeuralSeek..
• Click the red Save icon at the bottom of the screen to save the newly added Intent Category.

Seek Answers based on Intent Category

Navigate to the Seek tab within NeuralSeek.

• Ask a question involving the newly created Intent Category, so the Intent will appear in the Curate and Analytics screen as well.
  • For example, seek: What Virtual Agents are supported by NeuralSeek?, or Does NeuralSeek support Virtual Agent integration?.

View Intent Categories

Navigate to the Curate tab within NeuralSeek.

• Notice how there is a number 1 next to the new intent underneath the Category label.
• Click the number to view the name of the category that intent is now placed in.
• Optionally, you can edit which category Intents fall into by selecting from the dropdown menu.

Navigate to the Analytics tab within NeuralSeek to view the Intent history of the newly created category as well.

PII Handling

NeuralSeek features an advanced Personal Identifiable Information (PII) detection routine that automatically identifies any PII within user inputs. It allows users to maintain a secure environment while still providing accurate responses to user queries.

Turn Off "Force Answers from the KnowledgeBase"

Navigate to the Configure screen in NeuralSeek and expand the Answer Engineering & Preferences details.

• Change the "Force Answers from the KnowledgeBase" selection to False.

We configure this setting for optimal answer generation for this next example, since the information will not be in our source documentation.

Set LLM - Based PII Filters

Expand the Personal Identifiable Information (PII) Handling details.

• Click the light bulb icon to add a new row.
• Add an example sentence. For example: I graduated college from JMU.
• In the box to the right, add the PII element of the example sentence. In this example: JMU.
• Click the red Save icon at the bottom of the screen.

Seek an Answer

Navigate to the Seek screen of NeuralSeek.

• Seek the question being sure to reference the PII. In this example, seek: What colleges are in Virginia?

Notice the answer is vague and does not include information about specific colleges in that area.

Inspect PII

Navigate to the Curate screen in NeuralSeek. Here, we can see that newly created intent with a symbol indicating that this intent contains PII.

• Expand the intent to view the answers. Notice how the location of "Virginia" that we asked in the question is masked to hide the PII.

Ask an Additional Question

Optionally, you can continue to seek queries and view how the related PII is masked in the Curate screen. For example, seek the question, Where is JMU located?.

• The answer will be vague and not contain information regarding the location due to it containing PII.
• In the Curate screen, the intent will appear with the same symbol indicating PII. Inside the query, JMU will also be masked to protect the PII.