Intent miner overview
The following permissions assigned to any user role:
- Language Understanding > Miner > Add, Delete, Execute, Upload, View
- Language Understanding > Miner Intent > View
- Language Understanding > Draft > Add, Delete, Edit, View
- Speech & Text Analytics > Topic > Add, View
Use the intent miner to help quickly identify user intents in conversations between customers and agents. Use topic mining to discover topics and phrases of interest within a conversation that you can then use to create topics in the intent miner. Intent miner searches a historical set of conversation chat and voice transcripts between agents and customers for a specified date range. Next, it extracts the top set of intents or topics and the analytics that surround those intents or topics. Finally, it returns a list of intent utterances or topic phrases that the system associates with that intent or topic.
You can import mined intents in Architect into a Genesys Dialog Engine Bot Flow for intent configuration. For more information, see Import mined intents into a Genesys Dialog Engine Bot Flow.
You can add mined topics into Genesys Cloud > Quality Admin > Topics for topic configuration. For more information, see Create draft topics from a completed miner.
- You can only run up to five mining sessions at a time.
- You can save up to 100 intent miner sessions in a single org.
- You must have a minimum of 50 conversations available for the mining session. If you cannot meet the minimum, consider expanding the date range to include more conversations.
This section describes the available columns on the intent miner home page. The arrows up arrows and down arrows in each column enables you to sort the information.
Click the image to enlarge.
|Column or object||Description|
|Miner Name||The name of the miner session. To open the miner and view or edit the intents, click the miner name.|
The state of the mining session. For example:
For more information about each status type, see Status results in Add a new miner.
The type of mining session; either Topic or Intent.
For topics only, select either internal, external, or both participants.
|Date Created||The date that a user added a mining session.|
|Date Modified||The last date that a miner was updated or draft intents were edited.|
|Media Type||The type of mined conversations: chat or call.|
Select which dialect in which to mine topics. This setting directs the intent miner to search for transcripts with the matching language. You can only select one language at a time.
The source of the conversations for the mining session:
|Date Range||The start and end range that includes the mined conversations.|
The tasks you can perform on the mining session:
What are intents?
Intents describe a goal or task that a user wants to do, such as tracking their package or booking a cab. A user interacts with a bot to resolve their intent. In bot design, intents and utterances form the basis of a dialog model.
Example intents: Pay bill, Open account, Exchange rate.
What are utterances?
Utterances are phrases or sentences that users would use to describe what they want to do. The bot tries to understand and identify the user’s intent from these utterances.
A user can say: “I need a room for tomorrow” or “I want to book a room for tomorrow.” Both utterances convey the same intention: book a room for tomorrow. Another utterance might be: “Book me a suite for three nights starting tomorrow.”
What are topics?
Topics are collections of phrases that indicate a business level intent. The Topics page provides lists and descriptions of topics, and the number of phrases associated with the topic. For example, a topic called Attorney or lawyer mention described as phrases about legal actions and lawyers might have 25 potential associated phrases.
For another example, if you want to identify interactions in which the customer is looking to cancel a service, you could create a topic named Cancellation with a number of phrases including: “close out my account” or “I wish to cancel” and so forth. In addition, topics help to boost the recognition of specific words and phrases in voice transcription and in the interaction overview as they adapt the underlying language model to look for organization specific language in conversations.
Topic mining is particularly useful to workforce engagement management users. For more information about how to create topics and phrases, see Work with a topic and About programs, topics, and phrases.