Call Tagger

Delacon introduces a new way to categorise your calls

Delacon’s Speech Analytics Module (SAM) provides you with the ability to automatically transcribe and analyse every phone call your business receives. The SAM can also place these calls into predefined call categories. The existing SAM Call Categoriser uses a probability model to categorise calls, using a list of keywords. These keywords are given individual weighting, which tells the SAM how important they are to the category, and your business. The SAM will listen to, and transcribe, every call made to your business. By evaluating how often each of these keywords is used, alongside their weighting, the SAM will categorise each call. More important keywords are given priority when deciding the category, as will keywords that are used more often.

A new method of call categorisation

Delacon has recently released a new categorisation methodology called the Call Tagger. The Call Tagger takes a more rigorous approach – rather than using a probability-based model, the Tagger uses quantitative data to determine the category of each call.

Similar to the Call Categoriser, the Tagger starts with a transcript of each call, and a list of important keywords. Rather than assigning a weight to each keyword to define its importance, you define how many times each keyword must be used in a call before that keyword condition is considered ‘met’. By having a list of these keyword conditions, you can define how precise you want the Call Tagger to be.

Not all calls in a particular category will be exactly the same, of course. Once you have your list of keyword conditions, you can tell the Call Tagger how many of those keyword conditions needs to be met before it can categorise each call.

Call Tagging example

For example, for Category ABC, you might define the following set of keyword conditions:

KeywordRequired frequency
Keyword14
Keyword22
Keyword31
Keyword41

You then define the minimum number of keyword conditions that must be met in order for a call to be placed in the category. In the example above, you can define that in order for a call to be placed in the category ABC, one, two, three, or all of the keyword conditions need to be met. The Tagger will then analyse each call, and count the mentions of each keyword: 

CATEGORY ABC
KeywordRequired frequencyActual frequencyCondition met?
Keyword143No
Keyword223Yes
Keyword312Yes
Keyword411Yes

In the example above, if the overall minimum condition was to meet one, two or three of the individual keyword conditions, then the call would be placed in Category ABC. However, if the overall condition was to meet all of the individual keyword conditions, then this particular call would not be placed in Category ABC. If a call does not meet your criteria for the category, it will be placed in the General category.

By using call tagging, you can gain valuable data about your customers and target market, guiding future strategies and growth opportunities.

Start Call Categorisation today

Both methods of categorisation are available to you, and which you choose will depend on the kinds of calls you take. Using separate SAM analytics profiles, it’s possible to use both methods to analyse the same transcriptions. We’d be delighted to work through your first Call Categorisation project with you to establish which method would suit you best.

Call Categorisation is built around our AI-powered Speech Analytics solution. For more information about Speech Analytics, Call Categorisation, or any of our other services, please contact us here.

If you already have Speech Analytics set up on your Delacon account, and you’d like to implement Call Categorisation, please contact your Account Manager.

Leave a Reply

Your email address will not be published. Required fields are marked *