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
Related
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.
I am developing a bot for business using Dialogflow. I want to keep an option "Talk to real person". When my customer wants to talk to real person, bot should stop and someone from my support staff will take care of that user.
How is it possible?
How can I pause/stop my bot and let real person handle conversation?
While searching for answer, I send an email to Dialogflow support and got this reply next day.
At this moment, you'll need to handle the task of passing conversations from bot to humans in your custom implementation. You can take a look at the following sample: https://github.com/dialogflow/agent-human-handoff-nodejs.
Hope this may help someone else having similar issue.
By native google, Dialogflow doesn't support bot to human handoff or provide any Web interface to achieve this, but in dialogflow normally the action “input.unknown” used to hand off the conversation to a Human. The “input.unknown” action is built into Dialogflow and used with the default fallback intent. When none of the intents is matched, the default fallback intent is triggered and action associated with it is added in the response also you need to write a logic what bot should do after that.
But to make things easier you can integrate dialogflow with any third-party tool like Kommunicate. As they provide pre-built chat widget user interface and bot to human handoff can be enabled on a click of a button, Please click here for more detailed information
PS: I work for Kommunicate
The issue is related more to the external software that implements Dialogflow than Dialogflow itself.
You can use the PHP code of Support Board as a starting point, or you can use the Support Board software for that directly. It has the feature that asks the user if he/she wants to contact a human agent when the bot does not understand the question. If the user accepts the bot is automatically disabled and an email is sent to the agents.
More details at https://board.support/
PS: I work for Support Board
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.
I am trying to create a Chatbot through API.AI. Now my chatbot has a flow and it responds based on the users query. So I have created many Follow up Intents. But my follow up intents are not connecting. It is returning the same respinse for the initial question. Where did i go wrong?
Would help to see what your intent looks like. From what you're saying though, it may be that the previous question is not getting the answer its looking for so it will just continue asking it until it does. Check your entity value under action within your intent.