For example, I have a skill that tells the user about food interactions with medications. The user tells Alexa which medication they want to know about.
Each intent corresponds to a different medication interaction (e.g., grapefruit juice, antacids, etc.). Under the GrapefruitDrugs slot-type, I have several slot values (all of them are drug names). When the GrapefruitIntent is called, it gives the user a warning about this interaction. The problem is that I have other slot-types that share the same drugs and their warnings also need to be communicated to the user.
'Drug X', however, will interact with both grapefruit juice AND antacids. So the slot-type AntacidDrugs also has 'Drug X' listed as a slot value. I want both intents to be called.
How do I make sure that both intents get called? I've looked into chaining intents, however I have yet to see an example other than one that links an intent to the LaunchRequest.
Intents are here just to point out what kind of sentence you have received on your webhook. Webhook can be on lambda or can be your custom server (e.g. Java, PHP, NodeJs …). In any case, here is your code and logic. Here you know at what state your conversation is and how should given intent be interpreted.
So in some conversation states you will react the same for two intents, while in some cases you might interpret the same intent in two different ways.
Related
I have a skill that elicits a U.S. state and county from the user and then retrieves some data. The backend is working fine, but I am concerned about how to structure the conversation. So far, I have created an intent called GetInfoIntent, which has two custom slots, state_name, and county_name
There are about 3,000 U.S. counties with many duplicate names. It seems silly to me that I am asking for a county, without first "narrowing down", by states. Another way I can think of to do the conversation is to have 50 intents, "GetNewHampshireInfo, GetCaliforniaInfo, etc. If I did it this way, I'd need a custom slot type for each state, like nh_counties, ca_counties. etc.
This must be a pretty generic problem. Is there a standard approach, or best practice, I can use?
My (not necessarily best practice) practice tips:
Single slot for single data type. Meaning only have one slot for a four digit number even if you use it in more than one place for two different things in the skill.
As few intents as you need
no more no less. You certainly can and should break up the back end code with helper code, but try and not break the intents into too many smaller pieces. It can lead to difficulty when Alexa is trying to choose the intended intent.
Keep it voice focused. How would you ask in a
conversation. Voice first development is always the way to go.
For the slot filling I think it is fine to ask both state and county.
If the matching is not correct ask for confirmation.
Another option is to not use auto filling within the Alexa skill and use the dialog interface. Ask the county first and then only when it has more than one state option and is ambiguous continue the dialog to fill the state.
Even if you did have 50 separate intents you really never want to have two slots that can be filled by the same word. For example having a mo_counties and ky_counties that Clack satisfies both is ambiguous and can cause unneeded difficultly.
So for someone looking for the "best practice" I have learning that there isn't one yet (maybe never will be). Do what makes sense for the conversation and try and keep it as simple as it needs to be and no less on the back end.
I also find it helpful to find a non-developer to test your conversation flow.
This wasn't really technical and is all opinion, but that is a lot of what Alexa development is. I would suggest Tuesday Alexa office hours at https://www.twitch.tv/amazonalexa very helpful and you can ask questions about stuff like this.
My interaction has to be executed in two steps. in first step. Alexa will get some information to the user. On the basis of published information, Alexa will ask to take another action from the user's answer (Which is yes/no).
So is it possible to invoke one intent and on the basis of previous intent's reply through reprompt, i would be able to call another intent of alexa app.
if so, then how can i do that through akexa node js SDK v2.
Use Case:
My app is connecting with third party API which needs alexa to use Account Linking. Scenario is, when my account is linked and i have valid access token. Here's how conversation will go:
User: Alexa, ask "a" to get me overdue invoices.
Alexa: You have "x" number of invoices. Do you want to send payment reminders?
User: Yes.
Alexa: Your request to send reminders has been registered. Anything else I can help?
User: No Thanks.
So for this, I have to communicate with an external API two times. One, while getting overdue invoices, and two, while sending reminders.
From your example, I'm guessing you have invoices as one intent, then reminders as another intent. If reminders is only ever used immediately after invoices, then I'd make them a single intent. But if you want users to create reminders at any point, or if you have multiple intents that could flow into the reminders intent, then separate intents can work.
Check out:
How to Pass a new Intent
Each of the Dialog directives includes an updatedIntent property that can take an Intent object. Use this to:
Trigger a dialog on a completely different intent. For example, after completing the dialog for a BookFlight intent, you could return Dialog.Delegate with updatedIntent set to BookRentalCar to start new dialog.
...
When you use updatedIntent to change to a different intent, the directive acts against the new intent instead of the original:
...
When you use updatedIntent to set or change data on the original intent, make sure that the intent name and full set of slots matches the intent sent to your skill.
So to use your example, this is what you would do:
User: Alexa, ask SkillName to get me overdue invoices.
Trigger invoices intent.
Make API call, get # invoices.
Return Dialog.Delegate or Dialog.ElicitSlot or Dialog.ConfirmIntent with updatedIntent set to reminders intent. (include any and all slots, must be a full intent object)
Set the outputSpeech to "You have X number of invoices. Do you want to send payment reminders?"
Alexa: You have X number of invoices. Do you want to send payment reminders?
User: Yes.
Depending on which Dialog Directive you've chosen to use, it will return the user's answer differently. Either filling a slot you've prepared, or in a confirmationStatus, or AMAZON.YesIntent.
Check for the correct one of those, and make your reminders API call if confirmed.
Return fulfilled intent with output message:
Alexa: Your request to send reminders has been registered. Anything else I can help?
I am developing an app and everything is working good. One condition are there where I have set the utterances but if user is speaking something else, I am throwing it to the fallbackIntent. One of my utterance is {name} so user can speak any name. But I have define range of name as well that user is allowed only these names. So my problem is if the user is choosing defined names, everything working great and if user said something else like what is weather of chicago, it is going to fallbackIntent as well but the issue is if user speak some name which is not in the list, then too it is coming into defined intent. What i want that if user speak something which is correct but not in my defined name then too redirect it to the fallbackIntent. Is there any way I can call intent in giving condition? I am using php.
When you define a custom slot, Alexa take it's values as samples. So values which are not in the slot-value-list will also be passed to you. And with respect your intent, those slot values are valid, hence that intent is triggered.
The solution is to validate the slot values at your backend and return an appropriate response.
In your case, if u get any other names other than those you have defined, respond back with an error or give FallbackIntent's response.
When you create a custom slot type, a key concept to understand is
that this is training data for Alexa’s NLP (natural language
processing). The values you provide are NOT a strict enum or array
that limit what the user can say. This has two implications
1) words and phrases not in your slot values will be passed to you,
2) your code needs to perform any validation you require if what’s
said is unknown.
lets say i have a skill with 2 custom intents, 'FirstIntent' and 'SecondIntent'. SecondIntent also has a required slot, 'reqSlot'.
Now, i would like to sequence my intents. After my skill sent the FirstIntent-response, i would like Alexa to send a request with SecondIntent and a directive to elicit reqSlot, without the user to invoke it.
They say here, at the parameter 'updatedInted':
"Note that you cannot change intents when returning a Dialog directive, so the intent name and set of slots must match the intent sent to your skill."
Is this generally possilbe or did anyone figure out a workaround for this scenario?
Thanks :)
There are ways to handle this.
You can try:
When you send your first response it must set the shouldEndSession flag to false.
The end of your first response's output speech should lead the user into invoking the second response. For example: 'Say telephone number followed by your number'.
This way the user doesn't need to explicitly invoke your skill to get to the next intent.
It is not currently possible to cause Alexa to start speaking without a user first having spoken to it.
So for example, I cannot create a skill that will announce to my wife that "Ron is on his way home" whenever I leave work.
I can however, create a skill that my wife can ask "Is Ron on his way home", and it can respond with the answer.
Also, the new notifications allow a skill to post a notification, but this just causes the Alexa to light up its circular ring to indicate that a notification is waiting. A user must still ask Alexa to read it. In the example I cite above, that might be ok.
A lot of us would love for Alexa to be able to spontaneously start talking, but Amazon has not enabled that. Can you just imagine the opportunity for advertising abuse that functionality might enable? Nothing like sitting down watching TV and having Alexa start talking, "Hey, wouldn't some Wonder Popcorn taste great about now? We're having a sale..."
For example: If the user writes in the Watson Conversation Service:
"I wouldn't want to have a pool in my new house, but I would love to live in a Condo"
How you can know that user doesn't want to have a pool, but he loves to live in a Condo?
This is a good question and yeah this is a bit tricky...
Currently your best bet is to provide as much examples of the utterances that should be classified as a particular intent as a training examples for that intent - the more examples you provide the more robust the NLU (natural language understanding) will be.
Having said that, note that using examples such as:
"I would want to have a pool in my new house, but I wouldn't love to live in a Condo"
for intent-pool and
"I wouldn't want to have a pool in my new house, but I would love to live in a Condo"
for intent-condo will make the system to correctly classify these sentences, but the confidence difference between these might be quite small (because of the reason they are quite similar when you look just at the text).
So the question here is whether it is worth to make the system classify such intents out-of-the-box or instead train the system on more simple examples and use some form of disambiguation if you see the top N intents have low confidence differences.
Sergio, in this case, you can test all conditions valid with peers node (continue from) and your negative (example else) you can use "true".
Try used the intends for determine the flow and the entities for defining conditions.
See more: https://www.ibm.com/watson/developercloud/doc/conversation/tutorial_basic.shtml
PS: you can get the value of entity using:
This is a typical scenario of multi intents in Conversation service. Everytime user says something, all top 10 intents are identified. You can change your dialog JSON editor like this to see all intents.
{
"output": {
"text": {
"values": [
"<? intents ?>"
],
"selection_policy": "sequential"
}
}
}
For example, When user makes a statement, that will trigger two intents, you'll see that intents[0].confidence and intents[1].confidence both will be pretty high, which means that Conversation identified both the intents from the user text.
But there is a major limitation in it as of now, there is no guaranteed order for the identified intents, i.e. if you have said
"I wouldn't want to have a pool in my new house, but I would love to live in a Condo", there is no guarantee that positive intent "would_not_want" will be the intents[0].intent and intent "would_want" will be the intents[1].intent. So it will be a bit hard to implement this scenario with higher accuracy in your application.
This is now easily possible in Watson Assistant. You can do this by creating contextual entities.
In your intent, you mark the related entity and flag it to the entity you define. The contextual entities will now learn the structure of the sentence. This will not only understand what you have flagged, but also detect entities you haven't flagged.
So example below ingredients have been tagged as wanted and not wanted.
When you run it you get this.
Full example here: https://sodoherty.ai/2018/07/24/negation-annotation/