I'm having some troubles with intents on API.AI.
I have an intent -let’s call it intent01- aimed at managing any generic info request about some services (e.g. “I would like to know more about your services” and so on), which replies to the user explaining the services and asking him if he want to have more details about service1 or service2.
I than created 3 intents (intent01.1, intent01.2, intent01.3) in order to handle the possible user’s replies to intent1 (“I want to know more about service1”, “I want to know more about service2” or “no interest”), because each of them has to provide a different answer. They are linked to the father intent using the context.
I also wanted to manage a possible direct user’s question such as “I want to know more about service 1”, so I created a different intent (intent02), which provides exactly the same answer of intent01.1.
This solution doesn’t seem to be much scalable, do anyone know a best practice in order not to duplicate intents in such a situation?
Thank you for your time
Stefano
Please see here i think it resolves your issue. Regards
Related
So I am currently working on this project and I am confused on how to tackle this issue I am having.
I am creating this website that will go behind the scenes and input the data the user is providing us with and checking to see availability on various websites. I am confused on how the logistics of this would work. Would it make more sense to use API's rather than create maybe a bot (I don't even know if this would work) or even if there was a way to code it in myself.
A similar platform to what the general idea behind what operations would be used is vaccines.gov where the system will display the availability of vaccines nearby (a value inputted by user is zipcode). I just need to be pushed in a general direction as I am unsure how to approach this.
Thank you!
I'm looking to build an event management tool and want to give users the possibility to inquire disabilities.
I need a predictable input refering to an existing disability or handicap so the event organizers and the software could know about it.
In a wonderfull world, i'd like to use the id or label to redirect the organizer to an help notice and i want it internationalizable.
I don't know why my question was downvoted, is it something with stackoverflow rules or the queston itself ?
Anyway, i found i could start answering my question here:
https://bioportal.bioontology.org/ontologies/ICF
I have a workflow that asks different Yes/No questions. Using the Amazon built in Yes and No intents, how can I use them for multiple questions.
Here is an example of the flowchart.
I create a state called "Injury" in order have different handlers for this flow. When the use says "No" to the first question, the AMAZON.NoIntent emits the BurnIntent question. At this point if the user says "No", it loops back to the BurnIntent. How can I determine inside the Yes and No intents which intent to move on to? Is there a way to track which question I'm on to determine which intent to emit?
One of the ways would be to keep the state or a question in the self.attributes. That is some kind of session variables which is shared between intents and wiped out once the user ends using a skill.
For example, you can store there the last question you have asked the user by self.attrbiutes["lastQuestionID"] = questionId or a current "level". Then, once your "Yes/No" intent has been triggered you can use that value and decide what to do next.
My assumption is that you are using Node.js SDK. But I'm pretty sure there is something similar for other languages.
You can also read a little bit more about state management in the Tips on State Management at Three Different Levels article.
An alternative way is to make custom yes no slots and use it for each question if your flow isn't too big.
This post explains how to do it.
Bot Framework version - 3.11.0
I have added intents as below in LUIS:
Whenever I call the API as here I get entities empty. It works randomly like this query works
Am I missing anything? What might be the reason LUIS can able to find the entity in one case than other, as both are using same utterance and intent?
You are using very few utterances. You should use at least 12 and with a varied structure, not just "Who know..." "Who knows..." etc. Also for the other intents you need to add enough utterances as well.
The more intents you can add here it will be better. And after adding the intents and entities please make sure you are training/re-training the bot. Many times LUIS has a tendency to skip a trained model altogether. Also please do publish the model for a better efficiency.
When I was setting up an account with gmail few years back (probably this is still a case, haven't check) I've noticed that system doesn't allow to register common terms, nouns as username, it seemed that it used a sort of dictionary for screening. I would like to implement similar feature in my app, anyone have idea how to tackle this? App is written in PHP but understand I'll have to hook it up with online service.
Thanks
Wordpress MU has such feature too, you fill a list of possible usernames that you want to avoid and they become unavailable for users. You can check its source to get their approach...
Sinan.
Well the API will vary from service to service so I'd suggest you find one, look at their developer docs and then if you have a question ask it here.