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
- Uploading a CSV file into a source
- Preparing data for .CSV upload
- 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
- Training chat and calls data
- 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™
- Developer
- 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
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® Marketplace activities
- 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 Aug 11, 2025
Important:
These activities have limited support via internal labs and will soon be replaced by the Official Activities. It is recommended that you use the Official Activities for most use cases.
Create a Communications Mining Record which you can later upload into the platform
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Communication data type | Input | Type of communication data you would like to convert to a CM record |
| Record ID | Input | A unique hexadecimal number which identifies the record uniquely in the source |
| Message timestamp | Input | Day and time when the data was created. If timezone is not specified it’s assumed to be UTC |
| Message body | Input | String which is either email body content or other message content |
| Thread ID | Thread ID | A unique hexadecimal ID identifying a thread. Messages which has same threadID will be grouped together to form a conversation |
| Subject | Email content mapping | A string containing the message's subject |
| From | Email content mapping | The message sender email ID as string |
| To | Email content mapping | A string array of primary recipients |
| Cc | Email content mapping | A string array of carbon-copy recipients |
| Bcc | Email content mapping | A string array of blind carbon-copy recipients |
| User-defined string properties | User-defined properties | Any metadata of type string that applies to the record e.g. Domain Name, policy number, etc. |
| User-defined number properties | User-defined properties | Any metadata of type number that applies to the record e.g. star rating, score, etc. |
| Communication Mining Record | Output | The created record |
Get an existing communications mining record from within the platform
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Project name | Input | Project in Communications Mining™ from where you want to get the record |
| Source name | Input | Source in Communications Mining from where you want to get the record |
| Record ID | Input | A unique hexadecimal number which identifies the record uniquely in the source |
| Record | Output | The retrieved record |
Upload a batch of communications mining records to the given source
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Project name | Input | Project in Communications Mining™ from where you want to upload the record(s) |
| Source name | Input | Source in Communications Mining from where you want to upload the record(s) |
| Upload list of Communications Mining records | Input | Upload list of Communications Mining records |
| Record | Input | Create a record using Create Record activity |
| Records list | Input | Create a record using Create Record activity and append them to a list using Create List activity |
| Upload responses | Output | Upload responses |
Fetch a batch of communications from the given stream
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Project name | Input | Project in Communications Mining™ from where you want to fetch a batch |
| Dataset name | Input | Dataset in Communications Mining from where you want to fetch a batch |
| Stream name | Input | Stream in Communications Mining from where you want to fetch a batch |
| Stream feed | Output | Stream feed |
Advance a stream
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Select the stream to advance | Input | Select the stream that is an output of the Fetch Batch from Stream activity |
| Advance to the latest Sequence ID | Input | Advance the selected stream to the last fetched record’s ID |
| Advance to | Input | Sequence ID you received from the Fetch Batch from Stream activity |
| Advance stream response | Output | Advance stream response |
Reset a stream to the given date
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Select the stream to reset | Input | Select the stream that is an output of the Fetch Batch from Stream activity |
| Reset to a datetime | Input | The date time of record creation where you want to reset the stream to |
| Reset stream response | Output | Reset stream response |
Get predictions for a batch of communications mining™ records
| NAME | TYPE | DESCRIPTION |
|---|---|---|
| Project name | Input | Project in Communications Mining from where you want to predict records. |
| Dataset name | Input | Dataset in Communications Mining from where you want to predict records. |
| AI model version | Input | The version of the model to use, can be a version number or "Live" or "Staging". You can view available versions in Models page. |
| Use auto-threshold | Input | Enabling auto-thresholds returns a list of pre-defined thresholds that the label prediction satisfies. |
| Threshold | Input | A number in the range of 1-100.Predict list of Communications Mining recordsInputPredict list of Communications Mining records.RecordInputCreate a record using Create Record activity. |
| Records list | Input | Create a record using Create Record activity and append them to a list using Create List activity |
| Transform tag | Transform tag | The transform tag that you want to use to process the raw email |
| Prediction results | Output | Prediction results |
