I'm designing a helpdesk chatbot in dialogflow and currently training it with existing data from my ticketing system. What is the best practice for handling inputs that contain multiple intents? Here is an example with the intents in bold:
"Hi, my name is John Doe and I'm a first year student. I want to know where to register for classes and also reset my enterprise password. Please help."
So is the solution to ask people to keep things simple up front? I think currently dialogflow will point the user to one of the intents above, but i'm not sure how it decides which intent to match with.
You will probably have one intent for each feature that your bot offers, i.e. RegisterClass, ResetPassword etc. In that case there is no good* way to handle the case where someone asks for two things at once, your users will have to limit themselves to one request at a time. You can however use a fallback intent to explain this at runtime. This intent would be triggered if a users utterances matches none of the other intents and could give the user a quick explanation like
"Sorry, I didn't get that. Please tell me what you would like to do,
e.g. 'register a class' or 'change my password'"
This would keep a natural conversation going and alleviate the need to "train" users specifically for your agent.
*You could of course add combined intents like RegisterClassAndChangePassword, but that would become very clumsy and most likely not work reliably. You could also try to parse the request in your backend, but then you would essentially circumvent Dialogflow's core feature.
Related
So I have a flow prepared.
User: I would like to book an appointment
Bot: Sure. Does 3pm works for you?
User: Yes
Bot: Great. Appointment has been set. (Response from Fulfillment)
Bot: Anything else you need help with? Yes | No (How to achieve this)
I have tried triggering followupEvent but that won't display any response till the chain of intent is complete.
When the followupEventInput parameter is set for a WebhookResponse,
Dialogflow ignores the fulfillmentText, fulfillmentMessages, and
payload fields. When Dialogflow receives a webhook response that
includes an event, it immediately triggers the corresponding intent in
which it was defined.
I have End Intents ready for response for Yes and No. But need help in triggering it.
An intent shouldn't be used as a step in your flow or be tied to a single response, its intended to represent a category of phrases your user might say to complete a certain goal in your conversation. Since the was this helpful isn't triggered by any user phrase, but more as a trigger for the user to continue the conversation shows that it shouldn't be a separate intent.
Having the was this helpful phrase be available to multiple intents is a good choice so it can be used throughout your conversation, but I would recommend saving this phrase in a file, an API or a CMS and retrieving the response via code.
I'm not a PHP developer, but I expect it to be along the lines of: responseService.getResponse("requestFeedbackPrompt");
This allows you to retrieve the was this helpful phrase throughout your code, without making the mistake of making a seperate intent for it, as this will create problems later on with keeping state.
If you would decide to go with a single intent for this, you will quickly see that it will become difficult to maintain track of context, states and which step of the conversation you are in as multiple intents will go through this generic intent.
What would you do if you need a different variant of the was this helpful response, with the single intent, you will end up creating an intent for each variation and you will have to align the conversation flow and state accordingly every time.
If you use the service, you just call responseService.getResponse("OtherFeedbackPrompt);`
Hi have something similar in one of my bots. I have taken a different approach to those mentioned.
My bot asks if there's anything it can help with at the end of a an acknowledgement fulfilment.
The customer then has the option to respond with Yes or No.
Within the page that asks the question I have created routes.
One route for Yes and another for No.
The Yes route directs customers back to the point where they can start making selections. The No route provides a fulfilment to the customer and ends the session. I have used Yes and No intents for these.
I have been working with Google Dialogflow to create a Google Assistant experience.
My GA Action is to Raise Support tickets and those tickets are raised in our system via API.
We ask the user to describe the Issue they are facing, We have used a fallback Intent to capture the Issue/Ticket Description(Since the reply can be any free text, is this the best way to capture free text?).
Once the user gives a description, A webhook is called and the results are sent to our backend to capture.
We have noticed that when the user uses the words "not working" as a part of the issue description, it always calls the welcome intent, instead of going to the follow up Intent. If the user describes the Issue without using those words, it works fine. Below are 2 different responses.
I personally feel that this is a bug in GA, is there any way to solve it?
I think you're doing some things wrong. I don't have enough information to understand 100% what you are doing, but I will try to give you some general advice:
A fallback intent is used to 'fall back' to this intent when a user asks something that is nowhere provided in one of your other intents. That's why your fallback intent has the 'input.unknown' set as action. It will be triggered when the user gives some input that is unknown for your application. F.e. I don't think your '(Pazo) Support Action' will provide an answer if the user asks to book a plane to Iceland, so that's when your fallback intent comes in to give an answer such as 'Sorry, I can't answer that question. Pazo is here to give you support in... What can I do for you?'
Your user can either register a complaint or raise a support ticket if I'm getting this right? I recommend you to make two seperate intents. One to handle the complaints and one to handle the support tickets.
Before developing advanced actions with a seperate webhook and a lot of logic with calling an API etc., I recommend to go through the documentation of Actions on Google:
https://developers.google.com/actions/extending-the-assistant
I hope you're all having a good day.
I'm trying to make a dynamic quiz chatbot in dialogflow.
So, I have a user saying "Let's play a game". It'll then go to the intent and go into fulfillment. The fulfillment will then go into a method and get a list of dynamic questions from my database. There could be any number of questions. So, the bot will ask the first question and then it will wait for the user's answer and see if it's correct. Then it will ask the next question.
So the bot will firstly ask a question, However, I'm stuck at the part where the user will give an answer. Because I have no idea how to get the bot to listen to the user's answer after asking the first question, and go back into the right fulfillment method.
Because if the user answers with "blue", how will the chatbot know that the user is answering a question instead of just randomly saying blue?
You need to make use of contexts.
When the intent is invoked and it fetch the list of questions from your database, you will also set an output-context.
Then you will have to create one more intent which will be invoked when user is giving an answer. In this intent you will set same context in input-context which you have earlier set in output-context.
This way, Dialogflow will know that user is giving an answer, not just randomly saying some words.
Context is the key in conversations.
During our testing, we were unable to complete at least one of the behaviors or actions advertised by your app. Please make sure that a user can complete all core conversational flows listed in your registration information or recommended by your app.
Thank you for submitting your assistant app for review!
During testing, your app was unable to complete a function detailed in the app’s description. The reviewer interacted with the app by saying: “how many iphones were sold in the UK?” and app replied “I didn't get that. Can you try with other question?" and left conversation.
How can I resolve the above point to approve my Google Assistant action skills?
Without seeing the code in question or the intent you think should be handling this in Dialogflow, it is pretty difficult - but we can generalize.
It sounds like you have two issues:
Your fallback intent that generated the "I didn't get that" message is closing the conversation. This means that either the "close conversation" checkbox is checked in Dialogflow, you're using the app.tell() method when you should be using app.ask() instead, or the JSON you're sending back has close conversation set to true.
You don't have an intent to handle the question about how many iPhones were sold in the UK. This could be because you just don't list anything like that as a sample phrase, or the two parameters (the one for object type and the one for location) aren't using entity types that would match.
It means that somewhere, either in your app description or in a Dialogflow intent(they have full access to see what's in your intents) you hinted that “how many iphones were sold in the UK?” would be a valid question. Try changing the description/intents to properly match the restrictions of your app.
I’m building an agent on API.ai where I ask a user a question. I’m not expecting them to answer the question back to my agent. However they may wish to follow up this question later on by asking for some more information. If I ‘end the conversation’ in my intent they can’t then do something such as say ‘tell me more’ without invoking my action again from scratch (in which case all context is lost), but similarly if they don’t say anything, then (on google home at least) the question gets repeated as it's expecting a response.
Is there anyway I could do this?
Actions are conversational experiences. Typically your app would ask a question and the user would provide a response. Once the user exits your app, the conversational context goes back to the assistant.
If you want to provide a quick way to let the user engage with your app again, then consider implementing support for deep links: https://developers.google.com/actions/apiai/define-actions#define_additional_actions
In addition to what Leon has said, you could also manage the context of the user yourself (instead of relying on API.AI's Contexts) and key off the anonymous userid that you get with each request.
This way they can deep-link back to ask you a followup question, and you know "who" is returning and where the conversation last stood when you gave a reply.
I understand that what you basically want is to create an intent in which what the user will say is not predictable (they may not say anything at all).
In that case , you can simply end the response with a prompt to specify it. "...Do you want to ask something more ". If user says "no" , end the conversation in a different intent. Otherwise carry on with the flow.