In the AI tab of your bot, in the left column, you will find our Recommendation Engine. It consists of listing the sentences entered by users that the ChatBot did not understand and prioritizing them according to their occurrence.
You can see the results for the current day, the past month, and the current and past years.
This tool therefore allows you to identify turns of phrase and vocabulary that your chatbot has not understood and will serve as a recommendation for adding new keywords and even new AI rules and new content.
Indeed, you will find here requests that you did not think should be processed in your ChatBot.
If you find that the same type of requests are made on a regular basis, it is time for you to address them by adding content. Whether it is responding to it in ChatBot or redirecting the user to another online service, this type of situation must be dealt with.
This is also where you can see if your users tend to write long messages. If this is the case, it will surely be necessary to deactivate the AI from a certain number of characters as we have seen previously.
When adding new keywords or phrases, don't forget the advice we have given you. Analyze the sentences entered by your users and translate them for your bot.
Recommendation Engine for NLP V2
In the Recommendation Algorithm tool following user input is also indicated information between [...] the NLP's vision on this request. This will then allow you very easily to add relevant rules and expressions.
Exemple: The AI does not understand the phrase “Do you have apartments to rent?”
Here is what V1 displays:
Using V2 we see that the algorithm has understood the following sequence of words and verbs: [do you appartment rent]. Which could become a rule.
You no longer need to try to think like a robot to make a new rule since you can actually see how it thinks.