Setting up Semantic Model Metadata for Conversational Analytics

Your query input is displayed based on the metadata of the semantic model. This metadata includes elements such as descriptions, keys, tags, drivers, and key element settings, which help you get more targeted and relevant data inputs. If the metadata of the semantic model is insufficient, the accuracy of the answers may be compromised. In such cases, you can modify the semantic model metadata at any time to get more targeted and relevant data retrieval.

To configure the metadata of the semantic model, perform the following steps.

1. On the Dialogs page, click the metadata icon. This will redirect you to the semantic model designer's page.

   Open

   

2. Click Refine Model > AI Settings tab. On the AI Settings page, click the Set Metadata link. The Conversational Analytics Metadata page is displayed. Use this to define the conversational analytics metadata, such as Tags, Descriptions, and Key Elements.

   Open

   

3. Use the Conversation Analytics Metadata dialog box to define the conversational analytics metadata, such as Tags, Descriptions, and Key Elements.

4. Use the checkboxes to mark semantic model fields as Key Elements for conversational analytics. This field will be used to train the AI model for conversational analytics

5. Click Apply. You can view the selected metadata by clicking the three-dots actions menu. The selected metadata will now appear in the fields list.

   Open