ixp
latest
false
- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access control and administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Preparing data for .CSV upload
- Uploading a CSV file into a source
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label low average precision
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining™
- Selecting label confidence thresholds
- Creating a stream
- Updating or deleting a stream
- Developer
- Uploading data
- Downloading data
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Fetching data for Tableau with Python
- Elasticsearch integration
- General field extraction
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
Communications Mining user guide
Last updated Nov 10, 2025
Note:
- You must have assigned the IXP Project Admin or IXP Developer roles as an Automation Cloud user, or the Streams admin permission as a legacy user.
- You must have assigned the IXP Analyst, IXP Viewer, or IXP Model Trainer roles as an Automation Cloud user, or the View streams permission as a legacy user, which allows you only to view the streams assigned to a dataset. Without this permission, the Streams page will not show in the dataset navigation menu.
To create a stream, proceed as follows:
Attention: Before you create a stream, make sure you have a pinned model.
- Navigate to the Datasets page and select the Streams tab.
- Select New stream +. This opens the Create a stream modal, where you need to fill in the required fields:
- Title - Give the stream a title and a description.
- API Name - Set an API name.
- Model version - Specify the model (labeller) version to use.
- Filters - Use the filters bar in the side panel to set user-property filters, which must be satisfied for messages to enter the queue for the stream.
- Select a label and a confidence threshold as shown in the following image:
When you set a threshold, that label is returned in the stream if the platform predicts that label with a confidence equal to or greater than the set threshold. Setting a label threshold does not change what messages are returned from the stream, only which predictions are returned with them.
The platform predicts the number of false positives and false negatives the stream would get wrong or miss.
The default threshold for a label is 100%. At this point, it is disabled, and the stream will not return predictions for the label.If the threshold is set to less than 100%, then the stream will return predictions for the labels that are above the threshold. - Select the check button to create the stream.
