- 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
Once you have defined your objectives, you can start turning them into labels. Labels should contain all the concepts and intents you want to capture in the dataset to meet your specific objectives.
- Process or request types
- Quality of serivice or failure demand
- Root causes and exceptions
- Customer or client experiences
- Sentiments
- Product types
- System and data
These are typical labels that our customers use, regardless of their use case or industry. Not all of them may be applicable to your model, and you may have other types of labels that are important to meet your objectives.
Each of these types of labels, including what they capture and what they help to answer, are covered in more detail in this section.
| Label type | What it captures | What it helps to answer |
|---|---|---|
| Processes or request types | These capture the core processes or inbound requests that a team has to handle. Often, it matches directly to a service catalogue of tasks that the team owns, and is arranged in a hierarchy capturing added levels of specificity for sub-processes or requests. |
These are foundational labels for your model, helping to provide insight, monitoring, and action across the entire channel. To help identify process improvement opportunities, or make processes more efficient by enabling automation, the platform needs to be able to identify the processes themselves. For analytics, they are combined with all the other label types to generate insights focused on root causes, sentiments, quality of service, and so on. Segmenting the data further using metadata helps further understand the nature and source of these requests. For automation, they are crucial for auto-routing, and automating processes end-to-end. |
| Root cause and exceptions | These labels are intended to capture the root causes of problems, or types of exceptions, that drive teams or customers to get in contact, for example, missing trade details for a financial service operations team. | These are fundamental to identifying process improvement opportunities. Mapping root cause labels to process or request type labels provides a clear picture of problems existing in the communication channel. |
| Quality of service or failure demand | These capture concepts relating the level of service within a communication channel, or demand generated by failures in process or service, for example, Chaser and Escalation. |
These help answer questions such as:
|
| Sentiments | If training a model without sentiment analysis enabled, which is the recommendation for B2B communications channels, you can use labels that capture the sentiments expressed in the communications instead. For example, customer frustration or customer delight. |
These are targeted at providing insights relating to client, customer, and even employee experience. By mapping the sentiments expressed to the other concepts predicted, you can find key pain points in processes and customer journeys that have the greatest negative and positive impacts. |
| Customer or client experiences | These relate to specific experiences had by clients or customers, and often go hand in hand with labels capturing inbound request types, for example, the item never arrived for a B2C retail company. |
These are the ultimate drivers of why clients or customers are contacting a business, and therefore provide powerful insights. They may overlap with root cause-related labels, though they are focused on the experience of the sender, and potentially not the upstream root cause. |
| Products | These capture the different products that a team or channel deals with, whether as a customer, servicer, or seller, such as ETFs or Property Insurance. | These labels can be combined in analytics with other label kinds to provide deeper insights on which products relate to which process or request type, or root causes or exceptions. |
| Systems and data | Every team interacts with a number of systems and data sources during their day-to-day, not just Outlook. These labels capture references to these, such as Salesforce or SAP. | Like the previous products, these can typically be combined with other labels to provide more granular insights. Combining systems and data-related labels with processes and exception types can help identify priority improvement opportunities upstream. |
Once you have defined your labels and your target taxonomy structure, you must define the key data points, that is, the fields, you want to extract from your communications data. The fields are used to facilitate downstream automation, but can also be useful for analytics. For more details on how to define and set up your fields correctly, check and Using general fields.
