Assume you want to create an intent to order the pizza and the user has to choose what kind of pizza he wants. In order to recognise what pizza the user wants you create an entity pizza with the entries:
diavola, prosciutto and hawaii
How do you handle the situation if a user specifies a pizza which does not exist in the pizza entity? Currently you could use prompts of "action and parameters" to tell the user that his choice was not valid. However, if the user has not chosen a pizza type at all he will be prompted with the same sentence, which does not makes sense in this scenario.
Example 1:
User: I want to order a pizza funghi
Bot: I do not understand your choice.
Example 2:
User: I want to order a pizza
Bot: I do not understand your choice.
In the latter example you would want to the bot to say: What kind of pizza do you like?
Details:
Training phrase: I want to order pizza [diavola] -> entity_pizza
Action and parameters: parameter entity_pizza is required and prompt = "I do not understand your choice"
Related
I tried searching for the resolution and been stuck on this problem for a few days. I am using actions-on-google (nodeJS) and dialogflow to make a chatbot
Here is a sequence:
1. Choose between food and drinks
2. If food:
----------- does it have to be gluten free?
----------- does it have to vegeterian
----------- Confirm order
----------- Would you like a drink with it?
----------- If yes, go to drink intent and pass food params too. (This is the step I am basically stuck at)
3. If drink,
----------- If coming from food, add it to order
----------- which drink?
----------- confirm order
4. Order placed successfully.
I am unable to move from followups to main intent. Is there a way to do so? conv.followup only worked for child followups.
Intents represent what the user says or does and not how you respond to what they're saying. So in this case, it doesn't really make sense to say that you want to "trigger" the drink Intent.
Instead, you'd ask if they want a drink and, if they say "yes", you would prompt them for the drink they want. Similarly, if they just said up front that they wanted a drink, you'd prompt them for their drink selection. These are two different Intents, but they get the same response and then continue down the same path.
You can't "pass parameters" the way you might be thinking, but you can store values in the parameters of a Context (or in the session storage, if you're developing an Action). One good technique is to build the order and store it in a Context as you go, and then when you're all done, get the values from the Context to confirm and place the order.
Contexts are also commonly used to choose a scope for processing answers - Intents with an Input Context require that Context to be set in order to be triggered. Followup Intents use this to limit when that Intent becomes valid, so you can set that Context yourself during Fulfillment.
(You also don't need to use the Followup Intent Contexts - you can handle this using Contexts you manage yourself.)
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?
Suppose i want to make a pizza ordering DialogFlow agent. To order a pizza we need 3 things: size, type and toppings.
If we want to go with follow-up intents approach rather than using entities then there will be so many combinations in which user might provide the information.
1: i want a pizza -> no info
2: i want small pizza -> size
3: i want small cheese pizza -> size and type
4: i want small cheese pizza with olives -> size, type and toppings
5: i want small pizza with olives -> size and toppings
...
and so on
How to solve this problem?
There will be so many combinations if we have more entities (2^n combinations)
Note 1: cannot take entities and slotfilling option as there are so many problems if we go down that road, like re-prompts loop, validation etc.
Is there any better solution?
Note 2: If we use entities, mark them required, and set prompts then many times if it does not get desired input from user it get stuck in re-prompt loop, i.e it keeps asking user same (or random) prompt for same entity. In my use case, it is bad for user experience. If we use follow-up intents instead, then we can set fallback intents for all those intents which solved this problem. (please note that this is just example of the use case)
This is another example of why I used follow-up intents, it solved my date capturing problem as well. I took #sys.date.recent and set a fallback intent to capture inputs like last week, last month etc, this was not possible using slots.
First, remember that Intents should reflect what the user says, not necessarily what you are doing.
On the surface, it isn't clear why slot filling (either with fulfillment or using built-in prompts) won't meet your needs. Since you've indicated that all three bits of information are necessary (size, type, and toppings), you can mark them as such in your phrases and Dialogflow will prompt for the missing information until it gets everything.
You almost certainly do not want to use Followup Intents. These are good when you always have a specific response that you send that will always have a very narrow set of replies from the user, but are very poor if the response from your action will prompt the user to reply in many different ways.
Instead, I would use a related concept: Contexts. (At least if you're not going to use slot filling.) When you ask the question of what they want, set a Context so you know they are. Then have one or more Intents that have this as an Input Context that accept the various things the user might say. Your webhook should see if you have the information you need and, if not, prompt them what else you're looking for. At the end, prompt for a confirmation, but they may say something that adjusts the order.
I am facing an issue whereby words that does not match with any intents, it will assume it belongs to intent with the most labeled utterances.
Example: if
Intent A consists of utterances such as Animals
Intent B consists of utterances such as Fruits
Intent C consists of utterances such as Insects
Intent D consists of utterances such as People Name
Desired: If the random word(s) does not fit into any of the luis intent, it will fit into none luis intent. Example of desired: If word such as "emotions" or "clothes" were entered, it will match as "None" intent.
Actual: When user type random word(s), it match with luis intent with highest number of labeled utterances. If word such as "emotions" was entered, it will match as "A" intent as intent A consist of highest number of labeled utterances.
Please advise on the issue.
Set a score threshold, below which your app won't show any response to the user (or could show a "sorry I didn't get you" message instead). This avoid responding to users with anything LUIS is unsure about, which usually takes care of a lot of "off topic" input too.
I would suggest setting it your threshold between 0.3 and 0.7, depending on the seriousness of your subject matter. This is not a configuration option in LUIS, rather in your code you just do:
if(result.score >=0.5) {
// show response based on intent.
} else {
// ask user to rephrase
}
On a separate note, it looks like your intents are very imbalanced. You want to try and have roughly the same number of utterances for each intent, between 10 and 20 ideally.
So without more details on how you've built your language model, most likely the underlying issue is that you either don't have enough utterances in each intent that have enough variation displaying the different ways in which different utterances could be said for that particular intent.
And by variation I mean different lengths of the utterance (word count), different word order, tenses, grammatical correctness, etc. (docs here)
And remember each intent should have at least 15 utterances.
Also, as stated in best practices, do did you also make sure to include example utterances in your None intent as well? Best practices state that you should have 1 utterances in None for every 10 utterances in the other parts of your app.
Ultimately: build your app so that your intents are distinct enough with varying example utterances built into the intent, so that when you test other utterances LUIS will be more likely able to match to your distinct intents--and if you enter an utterance that doesn't follow any sort of pattern or context of your distinct intents, LUIS will know to detect the utterance to your fallback "None" intent.
If you want more specific help, please post the JSON of your language model.
I am using "list" entity. However, I do not achieve my expected result.
Here is what I have for LUIS intent:
getAnimal
I want to get a cat**[animal]**.
Here is what I have with LUIS entities:
List Entities [animal]
cat: russian blue, persian cat, british shorthair
dog: bulldog, german shepard, beagle
rabbit: holland lop, american fuzzy lop, florida white
Here is what I have with LUIS Phrase lists:
Phrase lists [animal_phrase]
cat, russian blue, persian cat, british shorthair, dog, bulldog, german shepard, beagle, etc
Desired:
When user enters "I want to get a beagle." It will be match with "getAnimal" intent.
Actual:
When user enters "I want to get a beagle." It will be match with "None" intent.
Please help. Your help will be appreciated.
So using a phrase list is a good way to start, however you need to make sure you provide enough data for LUIS to be able to learn the intents as well as the entities separate from the phrase list. Most likely you need to add more utterances.
Additionally, if your end goal is to have LUIS recognize the getAnimal intent, I would do away with the list entity, and instead use a simple entity to take advantage of LUIS's machine learning, and do so in combination with a phrase list to boost the signal to what an animal may look like.
As the documentation on phrase lists states,
Features help LUIS recognize both intents and entities, but features
are not intents or entities themselves. Instead, features might
provide examples of related terms.
--Features, in machine learning, being a distinguishing trait or attribute of data that your system observes, and what you add to a group/class when using a phrase list
Start by
1. Creating a simple entity called Animal
2. Add more utterances to your getAnimal intent.
Following best practices outlined here, you should include at least 15 utterances per intent. Make sure to include plenty of examples of the Animal entity.
3. Be mindful to include variation in your utterances that are valuable to LUIS's learning (different word order, tense, grammatical correctness, length of utterance and entities themselves). Highly recommend reading this StackOverflow answer I wrote on how to build your app properly get accurate entity detection if you want more elaboration.
above blue highlighted words are tokens labeled to the simple Animal entity
3. Use a phrase list.
Be sure to include values that are not just 1 word long, but 2, 3, and 4 words long in length, as different animal names may possibly be that long in length (e.g. cavalier king charles spaniel, irish setter, english springer spaniel, etc.) I also included 40 animal breed names. Don't be shy about adding Related Values suggested to you into your phrase list.
After training your app to update it with your changes, prosper!
Below "I want a beagle" reaches the proper intent. LUIS will even be able to detect animals that were not entered in the app in entity extraction.