Activate Listener for Outbound Flows

In order to trigger and run any outbound flow first you need to activate the listener for that flow. Activating listener means activating the service of outbound calls on the outbound flow. To activate the listener, you need to follow below steps -

1. Create any outbound flow

2. Attach the DIDs to that flow

3. Drop a mail on help@phonon.io regarding the same with the following details

   1. Client ID/ Account ID

   2. Flow ID

   3. All the DID numbers attached

How to trigger Outbound Flows ?

Triggering outbound flow means uploading customer’s details to broadcast or run the outbound campaign (like customer number, startime, flow variables). That is making calls to those customers at mentioned starttime. The outbound flows can be trigged in three ways -

1. Webservice End Point

→ The API Request (with method as post) should be send to mentioned webservice end point in the flow. The webservice endpoint for

1. Outbound Multicast flow is “https://central.phonon.in/kairos-apis/outbound/create”

2. Outbound Dialer flow is “https://central.phonon.in/kairos-apis/outbounddialer/create”

→ API Request Body :

{
	"api-version" : "1.0",
  	"security-id" : "your security ID",
    "flow-id" : "your flow ID",
    "calls" : [{
        "client-identifier" : "Call identifier",
        "start-time" : "start date and time"
		"contact-numbers": ["Contact no to call"],
		"keys" : [
          {"name" : "$flow.key.<Flow Variable>",
          "value" : "value for flow variable"},
          {"name" : "$flow.key.<Flow Variable>",
          "value" : "value for flow variable"}
        ]
    }]
}

→ You can get security ID and flow ID from the flow’s configurator tab. Example shown below

Note - Before sending request, make sure to whitelist your IP through which you are sending API request in the whitelist section.

2. Email Upload

• You can find unique email ID for each outbound flows. You can send email with attachment to that email ID.

• Upon file being loaded, the user will receive an auto-response message, that the upload was successful or not.

• Call List File Instructions

  If you're uploading the call list using a file, please keep in mind the following

  1. Support file formats are .csv and .zip

  2. You can upload a .csv file of maximum 5MB

  3. Download the template file from the interface.

  4. telX:Put the customer number with country code in tel1 header, alternative numbers can be added as tel2,tel3, etc. up to tel10.

  5. $flow.key.variable:You can upload value of any flow variable by putting the flow variable name as the header and value in the respective cell.

  6. starttime:You can input the starttime of each record in the starttime header in ISO 8601 format.

  7. Common starttime:If the starttime is common for all the records, you can input the starttime in the file name as "upload_<starttime in ddMMyyyyHHmmss format>.csv' Example: upload_08022020211200.csv

• You can find email ID for email upload in outbound flow’s configurator tab. Example shown below.

3. Direct Upload through Interface

You can upload the .csv or .zip file directly from the interface by selecting a file or by drag and drop method. To know more about direct upload, click here.

Supported Languages on central

Phonon Central supports a wide range of languages so that you can communicate with your multilingual customers.

The languages supported by Google for different technologies are -

1. https://cloud.google.com/text-to-speech/docs/voices

2. https://cloud.google.com/speech-to-text/docs/languages

3. https://cloud.google.com/dialogflow/docs/reference/language

The languages supported in central for different functionalities are as follows -

1. Text To Speech

Text to speech is the technology which converts you plain or SSML text into a speech. We have integrated with google for this and we support all the languages (almost) supported by google. The list of languages supported for text to speech are as follows :

2. Speech To Text

Speech To Text is the technology that converts any speech (audio file) into plain text. You can use this functionality to take voice inputs from customers and can further use it to process it. We also support India’s regional languages so irrespective of your customer, their speech will be converted to text. The languages supported for speech to text are as follows :

3. DialogFlow

DialogFlow can be used to process the voice input, to fetch intents, their responses, entities etc. The languages supported in DialogFlow are as follows -

System Variables

System Variables are the variables defined by default by the system in which the real time data of the call or flow will get saved. These system variables can be used in the flows as and when required. The value of these variables will be different for each call (if the variable category is ‘call’).

The system variables defined in Central platform are as follows -

Response Codes in widgets

Response codes are the variables which gets updated after the execution of the widget. Response codes helps in knowing particular status of the field and in troubleshooting if the widget gets failed.

Webhook

Success Response - Below are the variables which will get updated if the execution of the widget was successful and the flow moved to ‘line 0’.

Error Response - Below are the variables which will get updated if the execution of the widget was Failed and the flow moved to ‘line 1’.

KYC Documents

Here is the list of documents required for KYC process in ‘Central Platform’ according to different categories.

Setup DialogFlow and using in Central

If you want to design an IVR or an chat bot, that works on voice reorganization then you can use speech processing widget to achieve the same. Before that you need to perform basic setup in DialgFlow according to your use case. The setup requires following things -

→ Let's say you need to achieve following Use Case: 

There is an agent bot ‘Eva’ which when called, gives you 3 options and asks you to choose one 

Option 1 - To get Payment details

Option 2 - To get Account details

Option 3 - To get Loan details

If the user selects option 1 then he will be able to get the payment details, if the user says option 2 then he will be able to get account details and if the user selects option 3 then he will get details regarding loan. To do so you can configure dialogFlow as follows: 

Step 1 : Open DialogFlow

Step 2 : Go to Entities Page 

Entity: Each intent parameter has a type, called the entity type, which dictates exactly how data from an end-user expression is extracted.

Dialogflow provides predefined system entities that can match many common types of data. There are system entities for matching dates, times, colors, email addresses, and so on. You can also create your own custom entities for matching custom data. For example, you could define a vegetable entity that can match the types of vegetables available for purchase with a grocery store agent. 

Step 3 : Create New Entity

In order to create new entity you need to be aware of following terms-

Entity type: Defines the type of information you want to extract from user input. For example, OPTIONS could be the name of an entity type in our case as we want the user to select an ‘option’. Click on ‘Create Entity’ to create an entity type. 

Entity entry: For each entity type, there are many entity entries. Each entity entry provides a set of words or phrases that are considered equivalent.

If ‘options’ is an entity type, you could define these entity entries like: Option one, Option two, Option three.

Entity reference value and synonyms: Some entity entries have multiple words or phrases that are considered equivalent, like ‘option one’ and ‘first option’. For these entity entries, you provide one reference value and one or more synonyms.

Example : 

Reference value- Option 1

Synonymes- Option one, Option 1, First option, 1 option etc

Step 4 - After adding the details, SAVE the Entity 

If you want to use this entities in your flow then you can directly fetch entity (in speech processing widget) of particular intent and store the Entity in any variable to further use in the flow as shown below.

Step 5 - Now go to Intents page

An intent categorizes an end-user's intention for one conversation turn. For each agent, you define many intents, where your combined intents can handle a complete conversation. When an end-user writes or says something, referred to as an end-user expression, Dialogflow matches the end-user expression to the best intent in your agent. Matching an intent is also known as intent classification.

Step 6 - Create a new intent

Step 7 - Add training phrases in it

Training phrases: These are example phrases for what end-users might say. When an end-user expression resembles one of these phrases, Dialogflow matches the intent. You don't have to define every possible example, because Dialogflow's built-in machine learning expands on your list with other, similar phrases.

For Example- If we want user to select ‘option1’, we can create an intent name ‘option1’ and can add some training phrases which the end user might say like - I choose option one, I want first option, I prefer option 1 etc

Step 8 - Now add the responses of the intent

Responses: Responses can be text or  speech to return to the end-user. These may provide the end-user with answers, ask the end-user for more information, or terminate the conversation.

For example- Suppose if the end user selects option 1 and we need to provide the payment status then we add response as shown below.

So whenever the user gives input from the training phrases of this intent, one of the response will be given back to the user.

Step 9 - Now Save the intent 

Step 10 - To use this responses in your flow you can configure flow as follows

1. first configure NLP Engine

2. Create any inbound or outbound flow as per need, For the above example the flow can be like  - 

3. Enable ‘Fetch intent’ and then ‘fetch response’ in speech processing widget

4. Use this response variable further in any widgets like in play widget to give the user voice response. 

Integrations

1. Google

2. Amazon AWS

3. IBM Watson