Global Intents

Global Intents

Overview                                               

Global Intents Steps bring the power of NLU (Natural Language Understanding) to your conversations.

It enables your Bot to utilise Intent Recognition Mechanism to identify the intention of customers, and use it to progress the conversation journey.

Intents can be used to handle a wide range of customer requests, from simple questions to complex queries. When an Intent is matched, the Bot will follow the path you have configured as follow up to that specific intent recognition.

The biggest advantage of using Global Intents over rule based Bot Step (E.G. Listening Step), where customers have to return pre-determined options and follow specific syntax or commands to express their intents, is that your customer can phrase their response in a variety or ways and Global Intents can still understand the intent behind a message and and route the conversation where you want. 

When configuring a Global Intent step you can choose what 'Engine' you want your Bot to use. You can select either WebioFlow or DialogFlow.

WebioFlow

When you select Webioflow, you access pre-made Intents from our Webio Global Intents pool.



Our Intents are finely tuned in the world of Credit&Collection and can easily identify many customer intents, such as intent to pay or to express a complaint and then take the route you have configured for the intent that is being matched. 

The WebioFlow engine will dramatically enhance the ability of the Bot to understand the intent behind a customer response and follow up with a relevant message/question you configure, this way automating and enhancing even further payment collection triage processes.


                                           

Please note that "Late Payment" (Used in the example above) is not available yet on our App front end. Get in touch with support@webio.com if you want to learn more.

How To Enable And Use WebioFlow AI Intents?

  1. Open the Action Steps category, on the left hand side and drag and drop on the flow builder a 'Global Intents' Step.
  2. Select WebioFlow.


  1. Compose your message. 

  1. Open the AI Block, select the Intent you need (Check below for a full list of intents) and drag and drop it in the "Drag&Drop Intent" box.

  1. Save your configuration.

You can add as many Intents and you want in your Global Intent steps.

  1. If no intents get picked at all the Bot will follow the Default Output (At the bottom of the card) and the path you have configured for it. 


  1. You can also configure a manual Default Intent. This will have priority on the Default Output at the bottom of the card. However if the AI model doesn't identify any intent at all (Including the Default one), the Bot will go for the Default Output at the bottom of the card. Is advisable to always configure at least Default Output. 


  1. Configure as many follow up steps as needed for each of the intents you have used in your Global Intents step.


What WebioFlow AI Intents Can Understands?

Please check this link to learn more about WebioFlow Intents abilities.

WebioFlow AI Entities

When using Webioflow you also access our Entities pool so you can match entities to a specific intent.



WebioFlow Entities Gathering can be used as follow up to any of the intents that gets picked during the conversation. WebioFlow Entities is able to parse in the message returned from the customer any of the following entities, no matter what's the format or order they are provided.
  1. Phone number 
  2. Date  
  3. Name 
  4. Number
  5. Post Code
  6. Amount of Money
  7. Custom Entity - Please get in contact with support@webio.com if you want to enable this feature.

How To Use WebioFlow AI Entities

Please note that WebioFlow AI Entities may be used only in combination with the Intents you configure in your Global Intents Step. If you are looking for a standalone Entity Gathering step please follow this link.  

Ensure you included on the step the Intents you want to follow up with Entities request:

  1. Click on ADD ENTITY

  1. Drag and drop in the Drag&Drop on the Entity box,  the desired Entity and select in what Fieldname you want to store customer responses. You can add multiple Entities. (E.G. Name & Date Of Birth)


  1. Compose your message. Ensure you ask for the Entities your are looking for.


  1. If needed add follow up Entities for the remaining Intents that are present in the step.
                                                                                    
  1. Hit SAVE. 
Your Global Intents Step is now configured. You have will have now to configure the rest of your Bot steps and create a follow up path for each of the intents/entities that can get picked within your Global Intents step.

E.G.



When using Entity Gathering within a Global Intent step you can use the Default fallback step to configure a path the Bot should be follow in case one or more Entities you are looking for are not being returned or detected.

DialogFlow

When you select Google DialogFlow as a Global Intents step engine, you access all the Intents from your own Google DialogFlow agent. 

If you want to use DialogFlow:
  1. Open the Action Block and drag and drop on the flow builder a Global Intents step.
  2. Select DialogFlow. 
  3. In the Bot Field select the desired DialogFlow agent. (Make sure you have integrated your DialogFlow agent from the Organizations screen first - Webio - 

WebioFlow - A Few Examples

  1. How To Build A Simple ID&V Bot Using Global Intents And Logical Branch

In the example below, we used a Global Intents step powered by WebioFlow engine (Step 2) and provided the customer with two options:

1. Checking their account details. 
2. Performing a payment.

If the customer returns an intent that is picked by the "Account Enquiry", the Bot will follow up with an entity gathering message to gather name and date of birth of the customer.

If the customer reply includes a valid name and date of birth, these two entities will be saved in the custom fields we respectively named "fullname" and "DOB" (Step 2).

We then have used two logical branches (Step 5 and 6) to cross check that the customer returned entities that match our records. 





When the customer, in response to your Global Intents step (Step 2) returns the entities you are looking for, the Logical Branches will then check if the provided details match or do not match the records you have on your spreadsheet/system.
The Bot will then take the path you have configured depending if the conditions in the two Logical Branches (Step 5 & 6) are satisfied or not.

 

 

  1. How To Capture An Amount Of Money (Promise To Pay) With Global Intents 

Using Global Intents, we asked first to the customer to confirm if they can perform a repayment or not. (Step 1)

If the customer is proposing a potential re-payment, this will be picked up by the "Promise" intent. (Step 1)

When the 'Promise' intent gets picked up, the Bot is following up with an WebioFlow entity gathering functionality, in order to collect the Amount Of Money the customer is willing to pay.

(Entity gathering  parses the entities you are looking for in the customer message structure even if the they do not return the requested entity in a specific format - E.G. Entity can pick the amount of money no matter customer replies "100£", "I'm gonna pay 100£" , "I  think I can pay 100£")

Thanks to a Logical Branch (Step 2),  we have then set a threshold of 250£ to verify if the amount the customer is willing to repay acceptable or not.



  1. How To Build A Quick Survey Bot Using Global Intents 



See Little Survey Bot in action.


    • Related Articles

    • Integrating A DialogFlow Agent

      How To Integrate A DialogFlow Agent To An Organization Dialogflow agents use natural language understanding to return intents. When used as part of your Webio Conversational Middleware solution they allow your bots to manage conversations with ...

    • WebioFlow Intents

      Overview WebioFlow pre-trained Intents provide your Bot with the ability to identify customer intents, such as positive, negative responses or Credit&Collection enquiries and determine which route to follow based on the flow you have configured. This ...

    • Dialogflow V2 Setup

      DialogFlow agents can be integrated with your Webio organisation to utilise natural language understanding to identify the intent of a response, and use this intent to progress the conversation journey. Integrate each of your dialogflow agents to ...

    • Typeform Integration

      Overview A Typeform integration to your Organization brings the power of conversational forms into your bots. How To Integrate Your Typeform Account In Webio Please get in touch with support@webio.com if you want to learn more.

    • Step types

      Overview Bots are created as a flow of steps. Your Bot's automatic conversation will follow the flow based on the rules you configure and the path you design. When you create a new step, you need to choose what type of step it is, configure it, and ...