I want to have the user respond with a longish response, like talk about their education and family background. In this, I would like to identify multiple intents and then go back to the user with multiple questions (one by one) as a follow-on to the intents detected. Can I do this in DialogFlow CX and how?
As per my knowledge, there are 2 type of Chatbots- Open Domain and Closed Doman Intent Based. I was wondering how are conversational agents created such that can converse as if they are Open Domain, but still respond to specific user queries and intervene. As an example, consider a healthcare bot that acts as an empathetic conversation agent but also tells you specifically when to take medicine and answers specific questions about the medicine.
The obvious approach that comes to mind is fine tune something like DialogGPT etc. for your own purpose and also have an intent classifier. If the intent classifier does not recognize an intent then pass control to DialogGPT.
The problem with this is once “inside” an intent you have to be careful in ensuring the conversation related to the intent is over before proceeding further. Additionally you would have to pass in the whole context to DialogGPT each time which would be fairly time consuming. I was wondering how chatbots and personal assistants overcome this problem. Any help would be appreciated!
My goal is to program NFC tags in such a way, that Spotify starts playing a specific track/album/playlist.
But after writing a Spotify URI (e.g.
spotify:track:6rqhFgbbKwnb9MLmUQDhG6) to my tag, it only opens the app and disregards the resource.
The problem seems to be the way Android handles the tag, because the URI works without any problems when I call it from another app.
A related problem is the way URLs are handled: When I open a Spotify URL like
https://open.spotify.com/track/6rqhFgbbKwnb9MLmUQDhG6 from another app, it directly launches Spotify, whereas it would unsuccessfully try to open it with a browser after touching the tag.
It seems like Android only processes the scheme of the URI. Is this correct? If so, is there something that can be done to circumvent this? Why would that be the case?
This is primarily an attempt at understanding what’s going on (and whose fault the shitty UX is 😉). I don’t think there’s anything I can do to fix it and that’s fine, I’m okay with that.
I have a subscription to the New York Times. I have their app installed, and I’m subscribed to their email newsletter. When I open one of these emails, they contain a link to the article at the end, which looks like
https://nl.nytimes.com/f/newsletter/(id). This obviously contains an article reference, as well as probably some tracking code for my subscription.
When I click that link in Gmail…
What I would love to happen is:
Android’s app selector dialog pops up and asks me whether I’d like to open this in the NYT app, or one of my browsers.
The app is fine, but sometimes I might want to have it in the browser instead for various reasons.
What I would expect to happen is:
That it just jumps directly to the NYT app.
Not my prefered solution, but I think my use case is bit unusual and just going to the app is probably what most users would expect after installing the app.
What actually happens:
Android’s app selector dialog pops up and asks me to select one of my browsers (but not the NYT app!). After selecting one, the browser pops up for a split second, then makes way for the NYT app.
What… the hell!?
That makes no sense, is a bad experience and provides no benefits!
Whose fault is this? Does the app not register the correct URL intent? If so, any theories as to why they didn’t?
Or is this a flaw in Android’s intent system and the app did the best it could?
Or do the browsers do anything they’re not supposed to? (I have Chrome and Flynx installed, btw. With intentionally none of them selected as a ‘default’ — I want to get the selector modal each time.)