I brought an Amazon echo in hope to have it send commands to my HTPC.
I found and set up the following which uses alexa with eventghost.
http://www.eventghost.org/forum/viewtopic.php?f=2&t=7429&sid=c3d48a675d6d5674b25a35f4850bc920
The original poster used "literal" in the skill intent which I found doesn't work anymore. After reading through the whole thread I saw you need to create a custom slot type.
here is the skill set up
Intent scheme
{
"intents": [ {
"intent": "Run",
"slots": [
{
"name": "Action",
"type": "Commands"
} ]
} ]
}
Custom Slot Types
Commands
cleanup
clean up
move movies
move downloads
move cartoons
move the cartoons
move the downloads
move the downloaded movies
play
pause
stop
Sample Utterances
Run {Action}
What I'm wanting to do is say:
"Alexa tell/ask (Invocation Name) to clean up"
or
"Alexa tell/ask (Invocation Name) to Move movies"
I typed in the custom slot to what I believe is the correct format based on my web searching.
the problem is when I run it through Alexa it sometimes hits Eventghost slightly wrong.
how can I fine tune it. or do i have the skill set up wrong?
Above Setup Looks fine, Alexa skill has ability learn by training Skill more
But I dont know, you made typo error
Your Sample Utterances looks like "Alexa tell/ask (Invocation Name) clean up", but your ask as "Alexa tell/ask (Invocation Name) to clean up" with extra word as "to", if this is not an typo error, please remove word "to"
Because while pronunciation, the word "to" will try to combine with your commands
Related
I'm struggling to build my Alexa Interaction model. My application is used for requesting live data from a smart home device. All i do is basically calling my Server API with a Username & Password and i get a value in return. My interaction model works perfectly for requesting the parameters, for example i can say "Temperature" and it works perfectly fine across all testing devices. For that intent i got a custom RequestType.
However for setting up Username & Password i need to use an built-it slot type: AMAZON.NUMBER. As i only need numbers for my credentials this should work perfectly fine in theory.
I got a interaction model setup which works perfectly fine when i press "Evaluate Model" in Alexa developer console. However once i go to Test on the simulator or to my real Alexa device it's absolutely impossible to call the intent. It always calls one of more other intents? (I see this in the request JSON).
Here's how the intent looks:
{
"name": "SetupUsername",
"slots": [
{
"name": "username",
"type": "AMAZON.NUMBER"
}
],
"samples": [
"my user id is {username}",
"username to {username}",
"set my username to {username}",
"set username to {username}",
"user {username}",
"my username is {username}",
"username equals {username}"
]
}
Whatever i say or type in the Simulator, i cannot call this intent. I have no overlaps from other intents. Does anyone see an issue here?
Thank you in advance
EDIT: I just realized that if you want to do account linking on Alexa you need to implement OAuth2 - maybe my intents are never called because they want to bypass me implementing my own authentication?
UPDATE:
This is the intent that is usually called instead - it's my init intent. So for example is i say "my username is 12345" the following intent is gonna be called:
UPDATE 2:
Here is my full interaction model.
(HelpIntent and SetPassword are only for testing purposes, they don't make sense right now)
It's impossible calling SetupUsername with any of the samples in my model.
You need to build the interaction model. Saving is not enough
When you develop your Interaction Model, you have to save it AND build it. Otherwise only the evaluation model will work (documentation about it).
Then when you test in the test console, you should see in the JSON Input, at the bottom, which intent was called:
"request": {
"type": "IntentRequest",
"requestId": "xxxx",
"locale": "en-US",
"timestamp": "2021-10-20T14:38:59Z",
"intent": {
"name": "HelloWorldIntent", <----------- HERE
"confirmationStatus": "NONE"
}
}
We are developing a skill and my invocation name is "call onstar"
I got an intent "CallOnStarIntent"
I got the next utterances
"switch to onstar",
"access onstar emergency",
"access onstar advisor",
"access onstar",
"connect to onstar emergency",
"connect to onstar advisor",
"connect to onstar",
"i want to use onstar",
"open onstar",
"call onstar emergency",
"call onstar advisor",
"call onstar",
"use onstar",
"start onstar",
"onstar information",
"onstar services",
"onstar please",
"onstar emergency",
"onstar advisor"
These are the listed utterances and they are working fine when i try a utterance "call square" i get Amazon.FallBackIntent as expected. But when i tried with utterances like "ping onstar" , "play onstar", or any utterances that has the word onstar it returns CallOnStarIntent.
Does any one know why is this happening?
Thanks in advance.
Your utterances are processed by a machine learning algorithm that creates a model that will also match similar utterances so this is normal (your extra utterances seem to be similar enough for the model to determine there's a match). However there's something that you can do to make the model more precise at matching:
You can extend the sample utterances of AMAZON.FallbackIntent to include the ones where you don't want a match (e.g. "ping onstar")
You can try to change the sensitivity tuning of the AMAZON.FallbackIntent to HIGH so matching out-of-domain utterances becomes more aggressive
From the Alexa developer docs:
"You can extend AMAZON.FallbackIntent with more utterances. Add utterances when you identify a small number of utterances that invoke custom intents, but should invoke AMAZON.FallbackIntent instead. For large number of utterances that route incorrectly, consider adjusting AMAZON.FallbackIntent sensitivity instead."
To adjust the AMAZON.FallbackIntent sensitivity to HIGH you can use either the ASK CLI or JSON Editor to update the interactionModel.languageModel.modelConfiguration.fallbackIntentSensitivity.level setting in the JSON for your interaction model. Set fallbackIntentSensitivity.level to HIGH, MEDIUM, or LOW.
{
"interactionModel": {
"languageModel": {
"invocationName": "...",
"intents": [],
"types": [],
"modelConfiguration": {
"fallbackIntentSensitivity": {
"level": "HIGH"
}
}
},
"dialog": {},
"prompts": []
}
}
The list of utterances for an intent are not to be seen as a closed set of values like an enumeration in programming languages.
They are only samples used to train your Alexa skill. It's described in the documentation page about best practices for sample utterances:
"Alexa also attempts to generalize based on the samples you provide to interpret spoken phrases that differ in minor ways from the samples specified."
I'm struggling to complete the development for a SmartHome action on our security panels, involving different trait implementations (including ArmDisarm, Power, Thermostats, etc.).
One specific problem is related to Toggles Trait.
I need to accept commands to enable or disable intrusion sensor bypass/exclusion.
I've added to the SYNC response the following block, for instance, for a window sensor in the kitchen:
{
'id': '...some device id...',
'name': {'name': 'Window Sensor'},
'roomHint': 'Kitchen',
'type': 'action.devices.types.SENSOR',
'traits': 'action.devices.traits.Toggles',
'willReportState': true,
'attributes': {
'commandOnlyToggles': false,
'queryOnlyToggles': false,
'availableToggles': [
{
'name': 'bypass',
'name_values': {
{ 'name_synonym': ['bypass', 'bypassed', 'exclusion'}, 'lang': 'en'],
{ 'name_synonym': ['escluso', 'bypass', 'esclusa', 'esclusione'], 'lang': 'it'}
},
}
]
}
}
I was able to trigger the EXECUTE intent by saying
"Turn on bypass on Window Sensor" (although very unnatural).
I was able to trigger the QUERY intent by saying
"Is bypass on Window Sensor?" (even more unnatural).
These two utterances where found somewhere in a remote corner of a blog.
My problem is with Italian language (and also other western EU languages such as French/Spanish/German).
The EXECUTE Intent seems to be triggered by this utterance (I bet no Italian guy will ever say anything like that):
"Attiva escluso su Sensore Finestra"
(in this example the name provided in the SYNC request was translated from "Window Sensor" to "Sensore Finestra" when running in the context of an Italian linked account).
However I was not able to find the utterance for the QUERY request, I've tried everything that could make some sense, but the QUERY intent never gets triggered, and the assistant redirects me to a simple search on the web.
Why is there such a mistery over utterances? The sample English utterances in assistant docs are very limited, and most of the times it's difficult to guess their counterpart in specific languages; furthermore no one from AOG has ever been able to give me any piece of information on this topic.
It's been more than a year now for me, trying to create a reference guide for utterances to be included in our device user manual, but still with no luck.
Can any one of you point me to some reference?
Or is there anything wrong with my SYNC data?
You can file a bug on the public tracker and include the QUERYs you have attempted. Since the execution intents seem to work, it may just be a bug in the backend grammar that isn't triggering.
I have created a skill with name "BuyDog" and its invocation name is "dog app"
So that should mean, I can use the intents defined inside only after the invocation name is heard. (is that correct?)
Then I have defined the Intents with slots as:
"what is {dog} price."
"Tell me the price of {dog}."
where the slot {dog} is of slot type "DogType". I have marked this slot as required to fulfill
Then I have added the endpoint to AWS lambda function where I have used the blueprint code of factskills project in node.js, and done few minor changes just to see the working.
const GET_DOG_PRICE_MESSAGE = "Here's your pricing: ";
const data = [
'You need to pay $2000.',
'You need to pay Rs2000.',
'You need to pay $5000.',
'You need to pay INR 3000.',
];
const handlers = {
//some handlers.......................
'DogIntent': function () {
const factArr = data;
const factIndex = Math.floor(Math.random() * factArr.length);
const randomFact = factArr[factIndex];
const speechOutput = GET_DOG_PRICE_MESSAGE + randomFact;
}
//some handlers.......................
};
As per the about code I was expecting when
I say: "Alexa open dog app"
It should just be ready to listen to the intent "what is {dog} price." and the other one. Instead it says a random string from the node.js code's data[] array. I was expecting this response after the Intent was spoken as the slot was required for intent to complete.
And when
I say: "open the dog app and Tell me the price of XXXX."
It asks for "which breed" (that is my defined question) But it just works fine and show the pricing
Alexa says: "Here's your pricing: You need to pay $5000."
(or other value from the data array) for any XXXX (i.e. dog or not dog type).
Why is alexa not confirming the word is in slot set or not?
And when
I say: "open the dog bark".
I expected alexa to not understand the question but it gave me a fact about barking. WHY? How did that happen?
Does alexa have a default set of skills? like search google/amazon etc...
I am so confused. Please help me understand what is going on?
Without having your full code to see exactly what is happening and provide code answers, I hope just an explanation for your problems/questions will point you in the right direction.
1. Launching Skill
I say: "Alexa open dog app"
It should just be ready to listen to the intent...
You are expecting Alexa to just listen, but actually, Alexa opens your skill and is expecting you to have a generic welcome response at this point. Alexa will send a Launch Request to your Lambda. This is different from an IntentRequest and so you can determine this by checking request.type. Usually found with:
this.event.request.type === 'LaunchRequest'
I suggest you add some logging to your Lambda, and use CloudWatch to see the incoming request from Alexa:
console.log("ALEXA REQUEST= " + event)
2. Slot Value Recognition
I say: "open the dog app and Tell me the price of XXXX."
Why is alexa not confirming the word is in slot set or not?
Alexa does not limit a slot to the slot values set in the slotType. The values you give the slotType are used as a guide, but other values are also accepted.
It is up to you, in your Lambda Function, to validate those slot values to make sure they are set to a value you accept. There are many ways to do this, so just start by detecting what the slot has been filled with. Usually found with:
this.event.request.intent.slots.{slotName}.value;
If you choose to set up synonyms in the slotType, then Alexa will also provide her recommended slot value resolutions. For example you could inlcude "Rotty" as a synonym for "Rottweiler", and Alexa will fill the slot with "Rotty" but also suggest you to resolve that to "Rottweiler".
var resolutionsArray = this.event.request.intent.slots.{slotName}.resolutions.resolutionsPerAuthority;
Again, use console.log and CloudWatch to view the slot values that Alexa accepts and fills.
3. Purposefully Fail to Launch Skill
I say: "open the dog bark".
I expected alexa to not understand the question but it gave me a fact about barking.
You must be doing this outside of your Skill, where Alexa will take any inputs and try to recognize an enabled skill, or handle with her best guess of default abilities.
Alexa does have default built-in abilities (not skills really) to answer general questions, and just be fun and friendly. You can see what she can do on her own here: Alexa - Things To Try
So my guess is, Alexa figured you were asking something about dog barks, and so provided an answer. You can try to ask her "What is a dog bark" and see if she responds with the exact same as "open the dog bark", just to confirm these suspicions.
To really understand developing an Alexa skill you should spend the time to get very familiar with this documentation:
Alexa Request and Response JSON Formats
You didn't post a lot of your code so it's hard to tell exactly what you meant but usually to handle incomplete events you can have an incomplete even handler like this:
const IncompleteDogsIntentHandler = {
// Occurs when the required slots are not filled
canHandle(handlerInput) {
return handlerInput.requestEnvelope.request.type === 'IntentRequest'
&& handlerInput.requestEnvelope.request.intent.name === 'DogIntent'
&& handlerInput.requestEnvelope.request.dialogState !== 'COMPLETED'
},
async handle(handlerInput) {
return handlerInput.responseBuilder
.addDelegateDirective(handlerInput.requestEnvelope.request.intent)
.getResponse();
}
you add this handler right above your actual handler usually in the index.js file of your lambda
This might not fix all your issues, but it will help you handle the event when a user doesn't mention a dog.
I would like to know how to display a file when a user types something.
Ex: Show me the course details
Output: The file(pdf format) which is on my PC gets displayed.
Basically, you need to know how to work conversation: is one API for creating Intents, Entities and your Dialog flow.
Your application will access all nodes with the return from the API, and you will create conditions to get something for know if the user asked something about "Show me the course details".
I recommend to you create one intent like #aboutCourse and show examples to Watson know if the user will ask something with this purpose.
Something like:
Watson says: Hi! How can I help you?
User: Please show me the course details
Watson will recognize your intent and response what you paste within the node with the Intent condition #aboutCourse.
Make sure if the user really want this with:
Watson says: You really want to know details about the course?
User: yes / ok // or something to confirm
Or you can add some Intent confidence level for this node condition like: intents[0].confidence >= 0.75
And your code will check if the Intent is #aboutCourse and the entity is #yes, and do something in your application.
Or, you can create one context variable too, because, depends on your node flow, the intents will modify within your flow because every time Watson try to recognize what the user wants.
With your dialog flow, you will create one context variable and check if user says yes, like:
{
"context": {
"courseConfirm": "<? #yes ?>" //create one intent with confirm examples and value equal yes
},
"output": {
"text": {
"values": [
"Ok, you say #yes. I'll check, one moment."
],
"selection_policy": "sequential"
}
}
}
And within your application:
function updateMessage(input, response) {
if (response.context.courseConfirm == 'yes') {
//do something with code with code
}
}
Or you can create one function inside my example, like this answer.
Obs.: This code example is with conversation-simple project, from IBM Developers, but you will do something like my example with the same logic:get the return from API and do something within your application.