A categorization profile contains categories and subcategories for the Conversation Analyzer feature. Conversation Analyzer uses the profile to categorize transcripts of call recordings. The profile also contains any substitution rules you provide. Using the substitution rules, Conversation Analyzer refines the transcribed text.
The categorization profile applies to the associated account. For information about where you can view the categorized recordings and refined transcripts, see Listening to, viewing, and commenting on interaction content.
...
| Note |
|---|
| title | Analyzing transcripts |
|---|
|
Conversation Analyzer analyzes transcripts in several steps: - Conversation Analyzer identifies characters in the transcripts. Characters are either word or nonword characters. Characters from the Unicode categories , plus apostrophes, such as letters, spacing and non-spacing marks, connectors, and decimal numbers are word characters. Other characters are nonword characters and act as word separators. Nonword characters include !, £, $, %, ^, &, *, (, ), and -.
- Conversation Analyzer uses findings from step 1 to identify the individual words in the transcripts.
- Conversation Analyzer looks for words in the transcripts that match the rules in the categorization profile:
- Conversation Analyzer applies substitution rules first, replacing text if found.
- Conversation Analyzer tags the processed transcripts with the corresponding categories if found.
|
...