- 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
Data upload & management FAQs
The platform is able to support multiple forms of conversational data, that is, when a person is talking to another person in a digitally mediated channel. Examples include emails, case management tickets, chats, call transcripts, surveys, reviews, case notes, amongst others.
The platform interprets the core conversational contents of a conversation. For email conversations, subjects, body text and the thread are all considered but the contents of the attachments are not. The platform is able to identify when emails have attachments and their names, file types, and size. The names of the attachments can be displayed in the UI and can form part of the body of text from which the platform's models train.
The objective of training a model is to create a set of training data that is as representative as possible of the dataset as a whole, so that the platform can accurately and confidently predict the relevant labels and general fields for each message. The labels and general fields within a dataset should be intrinsically linked to the overall objectives of the use case and provide significant business value.
Yes, if you have sufficient permissions you can use our APIs to add data to the platform, or you can add data to a source via CSV upload.
The storage of data in the platform can be scaled to suit the needs of our clients, and allowed volume usage is dependent on agreed licence terms. Usage within the maximum volume agreed in the license is completely acceptable. Exceeding the maximum volume will require a discussion and may incur additional cost.
The platform will not automatically delete historical data. Older data can be removed by your Communications Mining™ Administrator if required.
Users can export their data from the platform via CSV or using the platform's APIs. Detailed explanations of how this can be done are shown in our how-to guides as well as our API documentation. The platform will not automatically delete historical data. Older data can be removed by your Communications Mining™ administrator if required.
Once you have logged in you will be taken to the Datasets page where you can create your own dataset, if you have the associated permissions to do so. For more details, check Creating a new dataset.
- What forms of communications do you handle?
- How do you handle communications with attachments?
- Can I upload data to the platform myself?
- What volumes of data can the platform support and is there a limit?
- How long does the platform store my data for?
- How can I export my data from the platform so that I can use elsewhere?
- How do I create my own datasets?
- How can I connect to the API?
