Google Dialogflow CX

Google Dialogflow CX is a third-party platform that provides voice virtual agents. Virtual agents interpret what your contacts say and respond appropriately. They do this using technologies such as:

• Speech-to-text Also called STT, this process converts spoken language to text. (STT)
• Text-to-speech Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. (TTS)
• Natural language processing Also called NLP, this process understands human speech or text and responds with human-like language. (NLP)
• Artificial intelligence (AI)

Virtual agents are flexible and can provide a range of functions to suit the needs of your organization. For example, you can design your virtual agent to handle a few simple tasks or to serve as a complex interactive agent.

Comparison of Google Dialogflow CX and ES

CXone supports Google Dialogflow ES and CX. The two versions are similar, but have some key differences.

Dialogflow ES is suitable for small, simple bots. It simulates nonlinear conversation paths using a flat structure of intents and context as a guide. This approach doesn't support large or complex bots. You can pass contexts using the customPayload property of the Virtual Agent Hub Studio action used in your scripts. These bots use context data to determine the contact's intents.

Dialogflow CX supports complex, nonlinear conversational flow suitable for large, complex bots. It allows intents The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. to be reused and doesn't require contexts. You can pass customPayload data, but you don't need to include contexts.

Conversation Flow for Voice Virtual Agents

To start an interaction with a voice virtual agent, contacts The person interacting with an agent, IVR, or bot in your contact center. call a phone number and reach your organization. The contact may be connected directly to the virtual agent, or they might need to choose an option in an IVR Interactive Voice Response. Automated phone menu contacts use via voice or key inputs to obtain information, route an inbound voice call, or both. menu. The contact's utterances What a contact says or types. are transcribed Also called STT, this process converts spoken language to text. into text so the virtual agent can use them.

The virtual agent analyzes the contact's utterances to understand the purpose or meaning behind the words. This is known as the contact's intent. The virtual agent sends an appropriate response as text. The virtual agent's response is synthesized into audio by a text-to-speech Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. service. Transcription and speech synthesis can happen in CXone or, in some cases, in the provider's platform

The method of sending and receiving requests differs depending on the method of connection the virtual agent uses: 

• Utterance-based: Requests and responses are sent via Virtual Agent Hub and the script with each turn. This option allows for customization of the virtual agent'sbehavior from turn to turn.
• SIP backchannel:Requests and responses are sent back and forth between the virtual agent and the contact. CXone stays connected to the virtual agent service throughout the conversation, but does not participate in it. CXone waits for the signal that the conversation is complete or that the contact needs transferred to a live agent.

At the end of the conversation, the virtual agent sends a signal to the script. It can signal that the conversation is complete, or that the contact needs to speak with a live agent. If the conversation is complete, the interaction ends. If a live agent is needed, the script makes the request. The contact is transferred to an agent when one is available.

When the conversation is complete, the script can perform post-interaction tasks, such as recording information in a CRM Third-party systems that manage such things as contacts, sales information, support details, and case histories..

Components of an Integration

The integration of Google Dialogflow CX involves the following components: 

• CXone: CXone must have a configured voice or digital chat-based channel Various voice and digital communication mediums that facilitate customer interactions in a contact center. to use with the integration.
• Virtual Agent Hub in CXone: Virtual Agent Hub holds the configuration information for connecting to your virtual agent A software application that handles customer interactions in place of a live human agent. provider, such as service account credentials. This includes choosing the options you want to use for transcription Written form of all or part of a voice or digital interaction., if your integration requires this service.
• Studio scripts: You need at least one script that includes a virtual agent Studio action. The action must be configured with the connection information for your virtual agent. The point of contact for the channel you're using with the integration must be configured to use this script.
• Google Dialogflow CX: Your virtual agent must be fully configured in the provider's platform. See the prerequisites on this page for any specific requirements.

Conversation Transcripts

You can capture the transcript and intent information from Google Dialogflow CX voice conversations. If you use a SIP backchannel connection with Dialogflow CX, this option is not available for you. You can use the captured data in any way you want. For example, in cases where an interaction is transferred to a live agent, you could display it for that agent. Another option could be to save it as a permanent record of the conversation. You can choose to capture just the transcript, just the intent information, both, or neither.

If you want to capture this information, you must enable it in the Google Dialogflow CX configuration settings in Virtual Agent Hub. You must also configure a Studio script used with your virtual agent. The script must include a action configured to manage the captured data. Captured data is stored temporarily for the life of the contact ID. If you need to save it, you can configure the script to send it to an archive. You are responsible for scrubbing all saved data for PII (Personally Identifiable Information).

Contact Center AI Insights

If you use Google Dialogflow Contact Center AI Insights, you need to make an additional configuration to your Studio script. The Contact Center AI Insights feature only works on conversations that have been marked complete.

By default, it takes 24 hours for Dialogflow CX virtual agent conversations to be marked complete. However, you can force them to close by sending an automated intent to Dialogflow at the end of each interaction.

To do this, you need to send the value conversation_complete through the AutomatedIntent property of the Voicebot Exchange action after the interaction has ended. You can hard-code this value in the property, or you can send it via a variable.

Speech Context Hints

Speech context hints are words and phrases sent to the transcription service. They're helpful when there are words or phrases that need to be transcribed a certain way. Speech context hints can help improve the accuracy of speech recognition. For example, you can use them to improve the transcription of information such as address numbers or currency phrases.

If you want to use speech context hints, you must add them to your script. Dialogflow speech context hints are sent in the custom payload. You must include two parameters: 

• speechContexts.phrases: The Google class token for the hint you want to give. The token must match the language and locale of your contacts. If you want to add multiple tokens, add a speechContexts.phrases parameter for each token.
• speechContexts.boost: A weighted numeric value between 1-20 to the specified phrase. The transcription service uses this value when selecting a possible transcription for words in the audio data. The higher the value, the greater the likelihood of the transcription service choosing that word or phrase from the alternatives.

For example:

DYNAMIC customPayload
customPayload.speechContexts.phrases="$OOV_CLASS_ALPHANUMERIC_SEQUENCE"
customPayload.speechContexts.boost=10		

You can see the contents of this parameter in Studio traces and application logs.

Custom Scripting Guidelines

Before integrating a virtual agent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish., you need to know: 

• Which script you want to add a virtual agent to.

• The virtual agent Studio action you need to use.

• Where the Studio actions must be placed in your script flow.
• The configuration requirements specific to the virtual agent you're using.
• Provider-specific requirements. Autopilot has no provider-specific requirements. For Autopilot Amelia only, the script has the following requirements: 

  • When nesting JavaScript within the JSON payload in Amelia virtual agents, use single quotes instead of escaping double quotes with a backslash ( \" ).

  • JSON structures must be "contentType": "dfoMessage", where the M in Message is capitalized. It won't work with a lower case m.

• How to complete the script after adding the virtual agent action. You may need to: 
  • Add initialization snippets as needed to the script using Snippet actions. This is required if you want to customize your virtual agent's behavior.
  • Re-configure the Studio action Performs a process within a Studio script, such as collecting customer data or playing music. connectors to ensure proper contact flow and correct any potential errors.
  • Use the OnReturnControlToScript branch to handle hanging up or ending the interaction. If you use the Default branch to handle hanging up or ending an interaction, your script may not work as intended. StandardBot behaviors. You can learn more about handling the end of the interaction in the online help about
  • Complete any additional scripting and test the script.

You may be able to obtain template scripts for use with virtual agent integrations from CXone Expert Services. If you need assistance with scripting in Studio, contact your Account Representative, see the Technical Reference Guide section in the online help, or visit the CXone Community site.

Studio Action for Voice Virtual Agents

The Voicebot Exchange action is for complex virtual agents, or for when you need to customize the virtual agent's behavior from turn to turn. It monitors the conversation between the contact and the virtual agent turn by turn. It sends each transcribed utterance What a contact says or types. to the virtual agent. The virtual agent analyzes the utterance for intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. and context and determines the response to give. The action passes the virtual agent's response to the contact. When the conversation is complete, the action continues the script.

If you want to configure barge in or no input, additional scripting is required.