Can anyone advise me on how to ensure Dialogflow replies with correct tense, what I mean is that a user may ask questions such as:
'Can I pay monthly' or 'Is there a set-up cost'
I have entities for these aspects e.g.
'No Set-up Fees'
In my reply, I have a variable e.g.
When using the system there are $System_Benefits
The issue is this is literal so I'm getting e.g.
Q. is there a set-up fee?
A. When using the system there are set-up
The answer doesn't make sense it is not responding with 'No Set-up Fee'
I can't seem to work out how to control the response in a positive or negative tense
There is 'No' set-up fee
or
'Yes' you can pay monthly
Hope this makes sense, can anyone help me?
If your entity reference value was No Set-up Fees and set-up was a synonym in the Dialogflow Entities editing interface, then No Set-up Fees would be displayed in the answer.
Related
I want to make a simple Q&A Alexa app similar to Alexa's custom Q&A blueprint app. I don't want to use blueprints because I need additional functionality. What is the best practice for creating the Alexa app? Should I create a separate intent for each question or should I somehow use utterances?
The best way depends upon what the questions are and how it will be asked.
1. If the questions has a simple structure
Consider these examples:
what is a black hole
define supernova
tell me about milkyway
what is a dwarf star
then it can be configured like this in an intent:
what is a {space}
define {space}
tell me about {space}
and the slot {space} -> black hole, supernova, milkyway, dwarf star.
From the slot value, you can understand what the question is and respond. Since Alexa will also fill slots with values other than those configured, you will be able to accommodate more questions which follows this sentence structure.
2. If the question structure is little complex
what is the temperature of sun
temperature to boil water
number of eyes of a spider
what is the weight of an elephant
then it can be configured like this in an intent:
what is the {unit} of {item}
{unit} to boil {item}
{unit} of eyes of a {item}
what is the {unit} of an {item}
Here,
{unit} -> temperature, number, weight, height etc.
{item} -> sun, moon, water, spider etc
With proper validation of slots you will be able to provide the right answer to the user.
Also, you will be able to provide suggestions if the user asks a question partially.
Ex:
user: what is the temperature
[slots filled: "unit"="temperature","item":""]
Now, you know that the user asked about temperature but the item is missing, so you respond back with a suggestion like this
"Sorry I didn't understand. Do you want to know the temperature of the sun?"
3. If the questions has totally different structure
How to deal with an annoying neighbor
What are the types of man made debris in space
Recommend few good Nickelback songs
Can I jump out of a running train
If your questions are like this, with total random structure, you can focus on certain keywords or crust of the question and group them. Even if you can't group them, find out the required fields or mandatory words.
IntentA: How to deal with an annoying {person}
IntentB: What are the types of man made {item} in {place}
IntentC: Recommend few good {person} songs
IntentD: Can I {action} out of a running {vehicle}
The advantage of using slots here is that even if the user asks a partial question and an associated intent is triggered, you will be able to identify it and respond back with an answer/suggestion or error message.
Ex:
user: what are the types of man made mangoes in space
[IntentB will be triggered]
If you have configured this without a mandatory slot, your backend will be focusing on the intent triggered and will respond with the right answer (man made debris in space), which in this case won't make any sense to the user.
Now, with proper usage of slots and validation you can find that instead of debris your backend received "mangoes" which is not valid. And therefore you can respond back with a suggestion or error message like
"Sorry, I don't know that. Do you want to know about the man made debris found in space"
Grouping questions will help you to add other similar questions later with ease. You can use one intent per question if it is too difficult to group. But remember to validate it with a slot if you want to avoid the situation mentioned right above.
While naming question-intents use a prefix. This might help you to group handlers in your backend code depending on your backend design. This is not mandatory, just a suggestion.
Summary:
Group questions with similar structure.
Use slots appropriately and validate them.
Use predefined slots wherever possible.
Don't just depend on intents alone, because intents can be mapped if its the closest match. But the question might be entirely different or might not make any sense. So use slots appropriately and validate them.
If possible provide suggestion for partial questions.
Test thoroughly and make sure it wont break your interaction model.
You should check Alexa Dialog Interface that allow you to make Q/A or QUIZZ.
https://developer.amazon.com/fr/docs/custom-skills/dialog-interface-reference.html
Not able to identify simple phrases like "my name is not Harry, it's Sam".
It is giving me name as harry and company name as Sam, Since name and company name was required in the same sentence.
It should have taken name as Sam and prompted the user again for company name OR should have given complete fallback.
Hi and welcome to Stackoverflow.
Dude. This is not a simple phrase.
Negative questions are always very difficult to catch by Dialogflow.
Suppose I have a question like,
I want to check *google* revenue for the year *2017*
As you can see, google and 2017 are the entities.
But now in the same way if you say,
I don't want to check *google* revenue for the year *2017*
The chances of hitting that old intent is very high as dialogflow matches almost 90% of this sentence with your old sentence. So it might fail.
Hope you are trying to ask something similar to this.
Anyhow coming to your point, If company name and name are different entities, then
Two things you can avoid:
As everyone mentioned,check your entities. The values should not be present in both the entities. This will fail because dialogflow will not know whether it should treat 'Sam' as your name or company name.
If you are not using the values from an entity, instead using '$ANY', then It has a very high chance of failing. And If you are using Dialogflow's system entity like, $given-name, then that is also not preferred as it does not catch all the names. So avoid these entities.
Things you can try:
Train Train And Train. As you would be aware, the training section in dialogflow is pretty good. Train it a few times and it will automatically learn and master it.
But , please note: Wrong training will result in wrong results. It should be 100% accurate. Always check before you approve a training.
And try using webHooks, actions, and/or events to figuring your way out from an external API.
In the chat application i am developing with dialog flow has scenario like this. Users can ask details about loans that they can get. that is a one intent. once user says the loan type they want i need to save it and use it every where when they ask question. for one example i have a another intent called loan payments.
In that intent they can ask questions like
I am interested in getting a personal loan for a duration of 5 years
and the loan amount would be 5 million rupees. Can you let me know the
monthly repayment amount?
to calculate that, loan type is a must (personal loan in this case). so if any user has specified the loan type before i need to use it here other wise i need to ask users to provide it again. but if i am using context i cant add add required. how to achieve this. also since i have already set the parameters i cant change the value of them. this is how my parameters look like
This is where your business logic comes in picture. Chat application can be built in two ways, directional & open-ended. In first one, you can explicitly go on asking few questions with set options/buttons for the services that you're offering & user has to select any one of them or in the second one, you keep it open for people to type-in anything & then you extract values & respond them based on their inputs.
Now that you're of second type, even if you use contexts, dialogflow offers you a favor to extract parameter values of first intent in the second one. You just have to use, #context_name.parameter_name. But now, if you're saying that if user has already defined loan type in earlier intent then you don't want to ask him again it in next intent, then this is purely a business logic that you will have to code in your webhook. Dialogflow won't do it for you.
I hope, this answers your question & if you don't want to do it that way, go for directional flow.
For my studying project, we implemented Stripe. From our app, you can buy stuff/services and split the price between users. However, we're facing a problem and we aren't sure to understand how to handle it.
Let's take this example:
A, B and C are friends and they want to split a payment. A and B accept the transaction and get debited. However, C accept but the
payment gets refused because he doesn't have enough of money on is
account.
Since A and B were charged, then we have to refund, but then we lose money, so we would like to know if it's possible to check, before charging, if the user can pay or not.
We thought about eWallet but... My team doesn't really want to implement it for some personal reasons.
We're a bit stuck, does someone has any idea or just a tip?
Thank you in advance !
I think you could probably accomplish this with Auth & Capture; i.e., Auth all 3 cards, and only proceed to Capture if all Auths are successful.
First of all, i'm not sure if this is the right place for this kind of question, so if anyone wants to point me in a better direction, do not hesitate!
I'm currently working on a website that will allow users to trade real physical objects between eachother. For exemple, User 1 trades a rare collectible coin, to User 2, which in turns sends an other collectible coin that he has double of.
What would be the safest way for me to make sure that both parties get their coins, without anyone getting scammed ?
I already figured that I'd be using the Paypal API to check for a "Verified address".
For now, it isn't viable for me to receive both package and "re-ship" them.
I was thinking of maybe holding an amount on both credit card until both confirm delivery, but i guess that one can receive a package and say he never received it.
Edit : Would it be too much of a trouble for the user if i force them to use a shipping method and print a "shipping sticker" that i create when they both agree to do the transaction? That way it would force them to use a signature shipping method.
All ideas are more than welcome!
Thanks
There really is not a 100% way to avoid a scam as a buyer can always come back and say they did not receive the item, it was damaged, not as described, file a dispute/chargeback or etc. However PayPal does have buyer and seller protections that come into play as well that help to protect buyers from such things. Plus PayPal's fraud filters and screenings some of the best in the industry.