I am trying to make a search algorithm with dialogflow that could take any combination of: first name, address, phone number, zip code or city as input to a search algorithm. The user does not need all of them, but we will refine our search with each additional answer until we only have one result. Basically we are trying to identify which customer we are talking to.
How should this type of intent (or set of intents) be structured? We have tried one intent with multiple parameters, but we do not need all of them to be required. We have also written a JavaScript function for fulfillment but how can we communicate back to dialogflow as to whether we need more information?
Thank you very much for your help.
Slot filling is designed for this purpose.
Hope that helps.
Please post more code/details to help answers be more specific.
First, keep in mind that Intents reflect what the user is saying, and not typically what you're replying with or what other information you need. Slot filling sometimes bends this rule, but only if you have required slots.
Since you don't - you need a different approach.
This can be done with a single intent, although you may find that multiple intents make it easier in some ways. The approach is broadly the same:
When you ask the question, make sure you set an Outgoing Context with a relatively short lifespan (2-3 is good) to indicate you are collecting user info.
Create an Intent (or Intents) that have sample phrases that capture the information you need.
Some of these will have obvious entity types (phone number and zip code) while others will be more difficult (First name has a system entity type, but it doesn't include all possible first names).
You will need to create sample phrases that collect the parameters by themselves, along with phrases that make sense. You're the best judge of this, and you should probably write some sample conversations before you write the phrases.
In your fulfillment, you'll figure out if you have enough information.
If you do, you can reply and clear the Context that was set. (Clearing it is important so Dialogflow doesn't match the information collecting Intent again.)
If you do not, you can add the information you have as parameters to the Context so you can save it for later processing, make sure you reset the Context lifespan (so it doesn't expire), and prompt the user for additional information. Again, having a conversation mocked out ahead of time will help here.
Related
Good day,
I am currently trying to create an intent that is able to put out responses depending on the user input. (The chatbot should be implemented on a website later)
Let's say we have an entity called cars with three entries: "Volkswagen" "Audi" "Ford".
Now when the user types in something with e.g. Audi in it, the response will correspond to this. Something like this: If Audi then give this response, if Ford then this response.
I couldn't find anything helpful yet.
Thank you in advance!
Remember that Intents represent what the user says and not how you handle this or how you reply. Although Dialogflow does offer the ability to respond to Intents, these aren't based on specific values that may appear in parameters.
There are, however, a variety of ways you can handle what you're doing, based on the rest of what you're trying to do.
Multiple Intents
One solution is to create an Intent for each type of thing that the user may talk about. You could then put the response you want for each in the response section of that Intent.
This is probably a bad approach, but may be useful in some ways. It requires you to duplicate phrases between the different Intents, which leads to a lot of duplication. On the upside, it does let you vary the replies, and truly represents the Intent of what the user is trying to say.
Using Parameters with Fulfillment
A better approach is to have a single Intent with many phrases representing what the users can ask. These phrases would have parameters of your Entity Type.
You can then enable Fulfillment for this Intent and write a Fulfillment webhook for the Intent that would look a the value of the parameter and send back an appropriate reply.
Using Parameters with DetectIntent
Since your ultimate goal is to embed this on a website, it may be more appropriate to have your website show something different based on what the user has said. (For example to show a picture of the car in another pane or links to different pages, to use your example of cars.)
In this case, your chat client (or a proxy) would be calling the DetectIntent API. You can structure your Intent similar to above, with parameters of the Entity Type, and the reply that is sent to your client would contain the Intent along with the value of the parameter. Your client then can check the value of the parameter and change the display accordingly.
I have created a pizza bot in dialogflow. The scenario is like..
Bot says: Hi What do you want.
User says : I want pizza.
If the user says I want watermelon or I love pizza then dialogflow should respond with error message and ask the same question again. After getting a valid response from the user the bot should prompt the second like
Bot says: What kind of pizza do you want.
User says: I want mushroom(any) pizza.
If the user gives some garbage data like I want icecream or I want good pizza then again bot has to respond with an error and should ask the same question. I have trained the bot with the intents but the problem is validating the user input.
How can I make it possible in dialogflow?
A glimpse of training data & output
If you have already created different training phrases, then invalid phrases will typically trigger the Fallback Intent. If you're just using #sys.any as a parameter type, then it will fill it with anything, so you should define more narrow Entity Types.
In the example Intent you provided, you have a number of training phrases, but Dialogflow uses these training phrases as guidance, not as absolute strings that must be matched. From what you've trained it, it appears that phrases such as "I want .+ pizza" should be matched, so the NLU model might read it that way.
To narrow exactly what you're looking for, you might wish to create an Entity Type to handle pizza flavors. This will help narrow how the NLU model will interpret what the user will say. It also makes it easier for you to understand what type of pizza they're asking for, since you can examine just the parameters, and not have to parse the entire string again.
How you handle this in the Fallback Intent depends on how the rest of your system works. The most straightforward is to use your Fulfillment webhook to determine what state of your questioning you're in and either repeat the question or provide additional guidance.
Remember, also, that the conversation could go something like this:
Bot says: Hi What do you want.
User says : I want a mushroom pizza.
They've skipped over one of your questions (which wasn't necessary in this case). This is normal for a conversational UI, so you need to be prepared for it.
The type of pizzas (eg mushroom, chicken etc) should be a custom entity.
Then at your intent you should define the training phrases as you have but make sure that the entity is marked and that you also add a template for the user's response:
There are 3 main things you need to note here:
The entities are marked
A template is used. To create a template click on the quote symbol in the training phrases as the image below shows. Make sure that again your entity is used here
Make your pizza type a required parameter. That way it won't advance to the next question unless a valid answer is provided.
One final advice is to put some more effort in designing the interaction and the responses. Greeting your users with "what do you want" isn't the best experience. Also, with your approach you're trying to force them into one specific path but this is not how a conversational app should be. You can find more about this here.
A better experience would be to greet the users, explain what they can do with your app and let them know about their options. Example:
- Hi, welcome to the Pizza App! I'm here to help you find the perfect pizza for you [note: here you need to add any other actions your bot can perform, like track an order for instance]! Our most popular pizzas are mushroom, chicken and margarita? Do you know what you want already or do you need help?
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
I am trying to jump to a random question with followup event, and at the same time store the question number in the context. But dialogflow only jumps to the event without storing the question number. Is there a way to do followup event and store a context in one intent?
app.intent('Quiz - random', (conv) => {
let rand = Math.floor(Math.random() * quiz_len) + 1;
conv.data.current_qns = rand;
conv.followup(`quiz-question${rand}`);
});
Not really. The point of using conv.followup() is to make it as if the new Intent is the one that was actually triggered by the user. Remember - Intents represent what the user is saying not what you're replying with. You can include a parameter with the redirect, which I guess you can use to send the question, but this still would be the equivalent of a parameter sent by the user.
It isn't entirely clear why you feel you need to direct to a different Intent. Is it just to ask the question as part of the reply? Go ahead and ask it in the Intent handler you're in and store the number in the context directly.
Update
You've indicated in the comments that you want to structure things so you have a "random dispatcher" that then redirects to an Intent to ask a question, and that Intent has a Followup Intent that accepts the right answer (and possibly ones that deal with wrong answers).
This requires you to build a lot of extra Intents for all the various questions, and then the conditions on each question. This requires you to re-build this structure every time you want to add a new question.
Dialogflow works very well to navigate the structure of a conversation - so you don't need to use it to navigate specific questions, answers, and responses. Remember - Intents model what a user says in broad terms, not how our agent responds.
Here is a structure that might work better:
There is an Intent that handles the user asking for a random question. The Intent fulfillment for this (ie - the handler function in your webhook) does the following:
Selects a question
Sets a context to indicate which question is being asked
Sends the context and the question to the user
There is another Intent that handles user responses. All user responses. If this is a multiple choice question, you can set very specific phrases, but otherwise you may need to make this a Fallback Intent that has the context specified above as an Input Context.
Your handler for this compares the answer.
If correct, you clear the context, say so, and ask if they want another question. (Which would then loop to the Intent specified in step 1.)
If incorrect, you make sure the context is still valid and tell them they're wrong. Possibly increase a counter so you don't let them guess indefinitely.
This means you're only building two Intents that handle the question itself. You should add a few more. Here are a few to think about:
What happens if the user doesn't say anything at all? The "No Input" scenario should be handled differently than a bad answer.
If you're asking a multiple choice question, perhaps you'll use a list and need to handle a list response.
Finally, if you're using a list, you may want to do something fancy and use Dialogflow's API to set a Session Entity Type for just that question. This allows you to set what you're expecting (with some aliases) for what is correct and incorrect, and then use a Fallback Intent for the context to say that what the user said didn't make sense.
Unless I've done something majorly stupid, it appears I only have one entry point into my Action on Google using Actions SDK and Node.js.
Consequently, I have to work out what the user has said by using some keywords with .indexOf() and then calling the appropriate function.
I thought that would also be simpler and there would be a way I could define an action with several phrases and Google would be intelligent enough to work it all out, even if the user said something slightly differently.
I guess one of the things Im doing wrong/different, is just by having a welcome intent that essentially has a conversation and asks "What would you like to do?" then the user responds, then I have to work out what was said, and follow up an appropriate action.
That seems quite long winded. Any better ways?
The "better way" is to use a tool that is designed for that and has a powerful and flexible Natural Language Processing engine associated with it. Actions directly support both Dialogflow and Converse.AI, and most other NLP engines should be able to provide information about how they work with Actions.
Dialogflow, for example, lets you specify some sample phrases that will meet an Intent, and then supplements that with "similar" phrases to the ones you've specified. Your Node.js webhook gets told which Intent was called, with what parameters you've specified for that Intent, and you can take action based on that information directly.
At this point, the Actions SDK is mostly intended to be used as the base that these and other NLP engines build on top of.