What's New
Cloud Contact Center Terminology Update
Customer Operational Scenarios Practical Tutorial
Overview
This document aims to help you quickly start with AI Voice Agent and implement its application in outbound scenarios, providing process guidance from preliminary preparation to call data analysis. You can learn about product features through Introducing AI Voice Agent. This document includes the following content: preparation, Intelligent Agent setup for customer operational scenarios, outbound call task creation, and call data analysis.
Prerequisites
1. Before starting, you need to register a Tencent Cloud account and complete real-name authentication.
2. Login to Tencent Cloud and create a voice call application.
3. Before using the Tencent Cloud Contact Center Intelligent Agent feature, you can purchase Intelligent Agent service according to business needs.
4. Calling an Intelligent Agent requires integration with a self-owned phone.
5. After completing application creation and purchase, enter the management console webpage.
AI Agent Setup for Customer Operational Scenarios
The key process in this scenario is as follows:
1. Create an AI Agent: Click AI Agent Management on the left side of the management console, then click Create a Blank AI Agent. Fill in the AI Agent name (for example: Customer Operations) in the pop-up. The system will automatically create a blank process canvas for you.
2. Build an AI Agent using the invite users to join a new activity scenario. Click the start a call node. You can refer to the figure below or autonomously set prompt content. Note: Include the following content: identity (AI Agent identity and language style), task (its main features and the effect you want to achieve), requirements (behavior constraints for the AI Agent).
Add a dialogue node as the opening remark to inform the user of the purpose of the call. Set the user reply category to facilitate further communication or inconvenient/deny communication. For each category, it is recommended to list possible user replies, such as "Yes" or "OK", to help the large model better understand the intent.
3. You can refer to the figure below to continue adding nodes and set scripts and user reply categorization. Beyond the normal introduction process, this process can retain unintentional users. If retention succeeds, enter the activity introduction node. If retention fails, enter the polite AFK node.
If you want to offer more personalized scripts, recommend choose intelligent generation, use large model to generate different scripts each time in a call for better user experience effect.
4. During the dialogue, users may express different intentions. If you wish to learn about user intentions, you can use the configure tags feature to tag user replies. You can view call tag conditions after the call task is completed.
For example, if the user reply shows willingness to participate in activities, you can refer to the figure below to configure the tag name as: Participation Intention, and the tag as: Interested. Likewise, you can configure tags for other responses, such as whether there is interest in learning about it.
5. During the dialogue, users may deny communication at any time. If a user shows unwillingness to learn, complains, or has already communicated at any node, you can refer to the figure below to set a global node and end the dialogue. Once enabled, when any other node triggers the conditions in the global node, automatic redirection to this node is allowed.
6. If you want to learn more about node functions, refer to node introduction. After completion, you can test the dialogue effect of the Intelligent Agent. For detailed operations, see test dialogue effect.
7. The canvas panorama is as follows:
Create an Outbound Call Task
1. After creating the customer operation outbound call Intelligent Agent, you can create outbound call tasks according to business needs (create a single Intelligent Agent call or create a bulk automatic outbound call task).
2. Variable replacement: When uploading the called name list, you can implement personalized scripts for different users through setting variable columns, such as addressing users by surname and gender, for example Mr. Li, Ms. Wang. When creating the Intelligent Agent, set the variable name you want to replace. The variable format is
${variable name}, for example ${name}, ${gender}. You can create different variables according to business needs.For detailed operations, refer to the figure below:
When editing the called name list, you need to enter variable name and variable value, such as
name: Li; gender: Mr..
Effect: The broadcast script for that node is: Hello, is this Mr. Li? The inbound call is for a follow-up call.
Call Data Analysis
After creating and executing the Intelligent Agent outbound call task, you can view the dialogue data, including call connection status and user intent.
Click View Detail to enter and view the specific task details.
You can see the connection rate of this outbound call task and the access status of each call to locate the reason for unanswered calls.
Click Call Detail for a call record to view detailed information, including Conversation Analytics (post-call Tag status), Call Process, and Automatic Speech Recognition (call transcript).
In the post-call tag field, you can view the tag status of the user reply for this call. As shown below, the user indicates interest in learning about and participating in activities. You can further convert customer clues based on this. You can also query Intelligent Agent call post-call tag data through API interface .
You can also click Batch Export to view all call information under this outbound call task. The content example is as shown in the figure below:
フィードバック