Through multiple intent types that can be detected in the process of text analysis, you can determine the expressed intent of customers. For example, by determining the intent type of the sentence I'd like to buy flight tickets from London to Paris as sell > purchase and extracting location entities, you can automatically create a case for booking a flight for the author of the sentence.
The following table lists of intent types that can be detected in your application by the default pzDefaultIntentModel intent detection model.
| Primary | Secondary | Example |
|---|---|---|
| direct | cancel | I am about to just cancel my service. |
| direct | confirmation, yes | The problem has been resolved, thanks. |
| direct | confirmation, no | I do not want to be your customer anymore. |
| direct | escalation | The manager has been notified of your issue. |
| direct | greeting | Thanks & regards! |
| direct | stall | Requested your team to switch to that plan. |
| inbound | apologize | I am deeply sorry for your inconvenience. |
| inbound | compare | Their offer is clearly better than yours. |
| inbound | complain | I am tired of waiting for you to resolve this simple issue! |
| inbound | praise | Best customer support I've ever received. |
| objective | N/A | A bank is a place that looks after people’s money for them and keeps it safe. |
| outbound | churn | I will just switch my provider. |
| outbound | enquire | Any new offers? |
| sale | purchase | Yesterday, I bought a brand new laptop from uPlusTelco. |
| sale | sell | Later I realized that snapdeal was selling at hardly 3k. |
| sale | wish | I just wanted to upgrade my phone. |