I have MS BOT client which the user will interact with. The Bot will use LUIS models for NLP. For any queries tagged under None, we should involve a human agent immediately. What is the best way to transfer the conversation from Bot client to human agent?
I think, none intent is not the right place to divert chat to human assistant. You should use text analytics to find the sentiment of user's reply and if it scores negative then you should redirect the chat to human assistant.
In Microsoft Bot it provides a setting to transfer Bot-to-Human if needed or the bot is unable to understand. Here are the steps to do on the Microsoft platform.
This changes depending on the Chatbot platform, for example, in Dialogflow JSON need to be used. In that JSON code, you can mention the human agent Id and set like the "Talk to Human" button and transfer.
Related
I have a fully mature agent in DialogFlow with utterances, intents and entities. Is there a way to quickly bring this info over into a new app in Luis? I really don't want to reenter the information. I know DialogFlow allows for a zip export. Is this format recognized by Luis?
This format is not recognised per Luis but both Dialogflow and luis have APIs and you can use those APIs to extract the utterances from Dialogflow and then POST those into Luis
I am developing an Azure bot, and I am intending to link it to Cortana channel. But not sure if that need the speech to text to be part of the services needed to create that bot. or Cortana client handles the communication between cortana and the bot with the text?
Responding via speech is completely under your control. The entire Cortana experience can be driven via text entry on Windows 10 and mobile app. However, your skill may not pass certification if published because of screen-less devices like the Invoke and best practice of responding with voice is triggered by voice. You can pull DeviceInfo and fail gracefully if there is no display.
I have developed a chatbot using dialogflow and hosted my webhook api to firebase cloud. I have integrated this bot to MS Team and Skype where I am able to access the bot from both channels. I have a requirement that I have to show "user typing..." notification to users in the chat window similar to session.sendTyping() having in MSBot. Do we have similar functionality using webhook option?
Any help would be appreciated.
Thank you!
This is not a feature that is built into Dialogflow. If you want to add this, you'll need to use another system to store the state of the focus and receive it on other devices. This could be accomplished through storing the boolean state in Firebase's database, for example.
I know Dialogflow (Api.ai) can be a bot in Slack. But what about monitoring the conversation and possibly manually intervene in the conversation? If possible, what would be the general direction to implement this?
So Slack has Open APIs for interacting with the Slack App. Here
Since you want to monitor the conversations so Events APIs and Conversations APIs would help you to notify as well as capture the conversations.
conversations.history will help you to fetch the messages within public or private channels.
Since you want to intervene in the conversation then I suggest using chatbot, which will provide a suitable way to intervene and respond to some particular events. Bot Users
Dialogflow has an sample on how to do this: https://github.com/dialogflow/agent-human-handoff-nodejs
You'll have to build you own front end for the human to override the response and call the Dialogflow query API to integrate:
Slack <--> Front end w/human override <--> Dialogflow's query API <--> Dialogflow Agent
Yes, it's possible. Just login to DialogFlow with your Google credentials, then on the left sidebar you can see the Integrations Tab. Click on it. You will find a bunch of different integrations for line, telegram, Twilio, kik, Viber, Skype and a lot more.
Click on Slack. It will ask you for some details for connecting with endpoints such as client ID, token, client secret. You can get it from the Slack API. You can also check the Slack API integration link here. After everything is properly set up, click the "Test in Slack" button in the DialogFlow Slack integration.
Is there any way in which Chat User information can be identified like user name, logged-in ids etc. in Slack or Skype integration with Api.ai.
Thanks,
Dinesh
This feature is now implemented only for Slack service. You could use context generic and its parameters slack_user_id and slack_channel.
For another services you have to implement your own processing using api.ai open source bots.