Real-time category best practices
A successful real-time category Grouping of calls in Speech Analytics that pertain to specific business issues among all transcribed interactions. is one that captures the interactions that most accurately define the relevant business issue. Assigning the right terms and filters to the right real-time category is critical to its success.
The best practices to follow are similar for both solutions, where differences between the two solutions are noted where applicable.
Use best practices and follow useful tips to fine-tune your category definition:
Clone standard categories
It is recommended to bootstrap the real-time categories design by cloning standard categories, and adapting them to the real-time scenario.
Real-time category terms
A term One to five words that are meaningful to a specific type of business, or phrases that stand out in interactions in Speech and Text Analytics. for a real-time category can be a single keyword, a phrase enclosed in quotation marks, or an expression with a NEAR operator. Invest time to assign appropriate terms to a category. Add words or phrases that capture the interactions that most accurately define the business issue.
The real-time categories ranking Rating of a specific interaction in the search results in Speech Analytics, which is determined by the number of instances of the search term within the interaction, and the interaction’s individual score. is based on 1-star rank, as it is based on a single call match in real-time. This imposes a great importance on selecting the terms diligently.
Real-time category filters
Set filters that fine-tune your category definition. For example, filter out the relevant interactions based on interaction In Speech Analytics, an interaction represents a single part of the contact between one employee and the same customer. In Text Analytics, an interaction is the communication session between one or more employees and the same customer with a unifying contextual element. properties.
The categories that you build are used in the recording analytics rules. This enables you to overlay additional business logic on top of the categories such as categories detection Function of the IAFD product that compares a caller’s voice to one or more voiceprints in a watch list to detect if a target is participating in a call. next to one another or next to call start/end events.