You are here:
Creating, Storing, and Managing Intent Data
Bots have two sets of data: the data around events and the data around intents. Event data refers to the things that happen inside bot conversations. Intent data refers to the data used to train the model so your bot understands your customers. To create a robust bot, you must have a strategy for handling both data sets.
Required Editions
| View supported editions. |
| User Permissions Needed | |
|---|---|
| To build and manage Einstein Bots: | Customize Application OR Modify Metadata OR Manage Bots |
| To manage intent sets and bot training: | Customize Application OR Modify Metadata OR Manage Bots OR Manage Bots Training Data |
Intent data contains utterances, or phrases, that tell the bot what the customer wants. For instance, there are many ways that someone could ask to speak to a service rep: “Transfer me to an agent”, “I need to speak to a human”, or simply “Agent”. The more utterances you add to an intent, the more likely the bot is able to make a correct decision.
It’s important that you have a balanced intent model. A minimum of 20 utterances is required to build the model, but more utterances make the model more accurate. We also recommend that any intent included in the model roughly includes the same number of utterances as the other intents.
Create a strategy for intent data management as your bot grows. A good strategy includes a path for testing and adding new intents and utterances within a sandbox to try out changes. The reason is that adding more utterances and intents to a live bot affects the customer experience.
- Import Intent Data to a Bot
Importing Intent Data is a simple way to add utterances into your bot. You can only upload intent data to dialogs with Intent Enabled, which creates an intent name to relate to the utterances. - Import Intent Data to an Einstein Intent Set
You can use Einstein Intent Sets to move utterances and entities between Salesforce orgs. - Export Intent Data for Einstein Bots
You can export bot intent data using the Data Loader and the Intent Utterance object. - Update an Active Einstein Bot
Your NLP bot is more effective when you update it regularly to react to the latest customer interactions. You can rebuild your active bot’s intent model and automatically go live with the updated model as soon as the build is complete. Or you can build and test your new model in a sandbox with change sets. - Source New Utterances with Intent Sets
You can use Einstein Intent Sets to add many utterances to intents at one time. Intent sets can be shared across orgs to quickly assign utterances to intents. - Manage Intent Data in Einstein Intent Sets
Learn how to use bulk actions in Einstein Intent Sets to move utterances, assign languages, or delete utterances. - Write Utterances for Einstein Bots
You can add utterances manually to any intent by typing them directly into the intent. Utterances added via intent sets and manually all count towards the total number of utterances. - Improve Intent Matching Quality with Bot Training
Help your bot improve its conversation quality with Bot Training. Bot Training, shows you the intent that the bot identified from an utterance. Then you can tell your bot if it was right, or you can correct the bot if it was wrong. - Share Your Intent Model Externally (Beta)
You can easily share your intent model with external Einstein.ai orgs. Use shared models to classify intent on other external datasets. - Delete a Dialog with Intent Enabled
Before you delete a dialog with intent enabled, you must first remove any intent sets from the dialog. Otherwise, an intent set can become “stuck” to the deleted dialog, so that the intent set is no longer visible and can’t be used in a different dialog. You don’t need to remove utterances you’ve added manually.
