Content on this page is for a product or feature in controlled release (CR). If you are not part of the CR group and would like more information, contact your CXone Account Representative.
Google Dialogflow ES is a platform you can use to develop virtual agent bots for your organization. You can integrate them into CXone for voice and CXone chat channels. Digital First Omnichannel chat channels aren't supported at this time.
Virtual agent bots interpret what your contacts say or type 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 digital agent.
Requirements
To use Google Dialogflow ES virtual agent bots with CXone, you need:
- Google Cloud Platform account.
- Prepared Google Dialogflow ES virtual agent A software application that handles customer interactions in place of a live human agent. bot.
Google Dialogflow ES Management
You can manage Google Dialogflow ES virtual agent bots in Virtual Agent Hub. To access Virtual Agent Hub, you need to use CXone Studio. If you don't have Studio installed, you can download and install it.
Google Dialogflow ES Configuration
Before you can add a Google Dialogflow ES bot to CXone, you must create and configure it using the tools provided by
When your Google Dialogflow ES bot is ready, you can add it to CXone Virtual Agent Hub and create or modify Studio scripts to use it. To configure this bot in Virtual Agent Hub, you need the following information:
View information about Google Dialogflow ES configuration fields
|
Field |
Details |
|---|---|
| Customer GCO Project ID | Your organization's Google Cloud Project ID. This is the identifier for your virtual agent. You can find it in the Google Dialogflow ES console settings. This field is visible only if you are using an OEM service account. |
| JSON Service Account |
The service account key file you created and downloaded from your Google Cloud Console. Copy and paste the entire content of the key file into this field. This field is visible only if you're using your own Google Dialogflow ES account. The service account key is a JSON object similar to the following example. { "type": "service_account", |
|
Language |
The language you want this bot to use. This is the language that the virtual agent understands. |
| Region | The region where your Google Dialogflow ES virtual agent is located. |
| Environment | The name of the custom environment your bot is published to. If you leave this field blank, the draft environment is used. |
| Perform Output TTS | Click to enable this bot to generate text-to-speech (TTS Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content.) output. |
| TTS Voice Name | Select the specific voice you want the bot to use for TTS output. Only visible when Perform TTS Output is on. |
| Speaking Rate | Changes how fast the TTS voice speaks. Only visible when Perform TTS Output is On. |
| Pitch | Changes the pitch of the TTS voice. Only visible when Perform TTS Output is On. |
| Volume Gain | Changes how loud the TTS voice is. Only visible when Perform TTS Output is On. |
| Timeout Event | Name of the Google Dialogflow ES event you want to trigger on timeout. |
| DTMF Break Out Pattern | If the specified characters are pressed, the script skips straight to the OnDTMFBreakout branch. |
| Use Google Protobuf JSON Serializer |
Click the toggle to On to enable Google Protobuf Serializer. Serialized responses improve performance by reducing the size of the responses and the memory required to process them. The size reduction makes it less likely for responses will exceed 32KB, which is the general size limit for script variables. NICE CXone recommends that you enable this option. If you need to disable it for any reason, it should be re-enabled as soon as the issue is resolved. If you set up your Google Dialogflow ES integration prior to the Spring 2022 version of CXone , it's important that you check your scripts for payload parsing. Anywhere you find this, you need to replace it with parsing from the new schema before you enable this option in your integration. For example, if your script currently references something like this: {parameters.fields.myfield.stringValue} you would change it to: {parameters.myfield} |
Custom Payload Best Practices
Follow these best practices when integrating custom payload data Google Dialogflow ES into CXone:
- CustomPayload is used to pass context for an intent What the contact wants to communicate or accomplish. Context helps the bot understand the user's intent. Contexts aren't required, but they help the bot match an utterance What a contact says or types. to an intent.
- In a Snippet action in your script, create a DYNAMIC customPayload object that follows the format outlined in the
- You can also pass custom data with customPayload without contexts. To do this, include standard JSON key-value pairs to a DYNAMIC object.
- The customPayload dynamic object is passed as a bot parameter as JSON, as shown in the example script.
View example script for integrating custom payload
This script is an example of how to integrate custom payloads with Google Dialogflow ES bots. This script uses the VoicebotExchange action, but the process of integrating custom payload is the same.
Scripting Guidelines
Before integrating a virtual agent A software application that handles customer interactions in place of a live human agent., you need to know:
- Which script you want to add a virtual agent to.
-
The Studio actions
Performs a process within a Studio script, such as collecting customer data, playing a message or music, or routing a contact to an agent. you need to use for your bot. - Where the Studio actions must be placed in your script flow.
- The configuration requirements specific to the virtual agent you're using.
- 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. You can do this to customize your bot.
- Re-configure the action 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, your script may not work as intended.
- Complete any additional scripting and test the script.
Ensure that all parameters in the Virtual Agent Hub actions you add to your script are configured to pass the correct data. See the online help topic for the action you're using for information about how to configure each parameter.
If you need assistance with scripting in Studio, contact your CXone Account Representative, see the Scripting Reference Material sections of the online help, or visit the NICE CXone Community site.
Supported Actions for Voicebots
Voicebot Exchange Action
This action is for complex bots or for when you need to customize the bot's behavior from turn to turn.
Voicebot Exchange monitors the conversation between the contact and the bot turn by turn. It sends each utterance What a contact says or types. to the bot. The bot analyzes the utterance for intent What the contact wants to communicate or accomplish and context and determines the response to give. The action returns the bot's response to the contact. When the conversation is complete, the action continues the script.
Voicebot Conversation Action
This action is only for use with very simple bots. It does not allow for customization of the bot's behavior from turn to turn.
Voicebot Conversation interacts directly with the bot, passively monitoring the conversation in real time. The bot analyzes the conversation for intent What the contact wants to communicate or accomplish and context from a constant audio stream and returns appropriate responses to the contact. When the conversation is over, the action continues the Studio script. The action passes along any relevant information for screenpops, agent routing, and so on.
Supported Actions for Chatbots
Textbot Exchange Action
This action is for complex bots or for when you need to customize the bot's behavior from turn to turn.
TextBot Exchange monitors the conversation between the contact and the bot Virtual agent designed to handle specific interactions turn by turn. It sends each utterance What a contact says or types. to the bot. The bot analyzes the utterance for intent What the contact wants to communicate or accomplish and context and determines which response to give. TextBot Exchange returns the bot's response to the contact. When the conversation is complete, the action continues the script.
Textbot Conversation Action
Textbot Conversation interacts directly with the bot, passively monitoring the conversation in real time. The bot analyzes the conversation for intent What the contact wants to communicate or accomplish and context and returns appropriate responses to the contact. When bot indicates that the conversation is over, the action continues with the Studio script. The action passes along any relevant information for screenpops, agent routing, and so on.
