Management of “Exit Keywords” in NLP
FIND A NEW VERSION OF THE COMPLETE GUIDE ON the AI NLP BOTNATION by CLICKING HERE
It is now possible to add “exit keywords” in the AI – NLP rules by preceding them with an _ (underscore).
If you are managing a scrim on cars with a context by brand.
In the context “Nerault” you need rules like “breakdown”, “maintenance” but also on the brand “Tiaf” to change context if needed.
If the user indicates in the “Nerault” context: “otherwise I also have a Tiaf but it is broken down”, the expression “broken down” is likely to take over because it is certainly more popular in this context whereas the user should be sent to the context linked to the manufacturer “Tiaf”.
The solution so far: the negative keywords “breakdown -tiaf -geupeot -dorf -kosda -etc.”. A nightmare for the chatbot designer and it is to be expected for every expression in all the contexts of the brands or all the expressions composed on all the other manufacturers “breakdown Tiaf” “repair Kosda” “maintenance Dorf” … Even an Excel formula will have trouble generating all the combinations to be imported.
Now you only need to add ONE rule containing simply : _tiaf
“Do you have any tips for a broken down Tiaf?”
The outgoing keyword “_Tiaf” will have priority and will immediately force an exit to the destination sequence which can change the context user on the way if needed.
“Faster than light!
It is possible to add “exit keywords” at will and not necessarily in a context, it can also be in the general context and in this case the interest is to have words that necessarily take over the others if they are in competition during a treatment.
Warning: No vehicles were abused during the development of this feature and any resemblance to existing or former car manufacturers would be purely coincidental.