Which GCP service to use - Digalogflow API

Dialogflow 프로덕트에 관련된 개념, use-cases를 정리합니다.

Dialogflow

Dialogflow API

• An end-to-end development suite for conversational interfaces like chatbots or voice-powered apps and devices.
• Cross-platform connecting to your own apps (on the web, Android, iOS, and IoT) or existing platforms (e.g., Actions on Google, Facebook Messenger, Slack).

Use cases - Voicebots for customer service

Give customers 24/7 access to immediate conversational self-service, with seamless handoffs to human agents for more complex issues by building virtual agents and interactive voice response (IVR) that can perform tasks such as scheduling appointments, answering common questions, or assisting a customer with simple requests.

• Virtual agents for contact center
  

Use cases - Chatbots for B2C conversations

Connect with your customers on their preferred platform, at any time, from anywhere in the world. Whether your customers want to ask common questions or access specific information, text virtual agents offer an instant and satisfying experience for customers who want quick and accurate responses.

• Text virtual agents for messenger
  

Contact Center AI

Lower cost and increase customer satisfaction with the best of Google's AI technology.

• Key features: Insights flows into both Virtual agent with Voice and Chat and into Human agent with Real-Time Prompts
  
• Integrations and products : Dialogflow CX, Speech-to-Text, Text-to-Speech, Natural Language AI

EXAMTOPIC Q 10.

You work for a large financial institution that is planning to use Dialogflow to create a chatbot for the company’s mobile app. You have reviewed old chat logs and tagged each conversation for intent based on each customer’s stated intention for contacting customer service. About 70% of customer inquiries are simple requests that are solved within 10 intents. The remaining 30% of inquiries require much longer and more complicated requests. Which intents should you automate first?

KEY : Analyzed old chat logs and tagged intention label ⇒ 70% of chats simple & classified 10 intentions and the rest 30% of inquiries more complicated request. Which one to automate first?

• ❌ A. Automate a blend of the shortest and longest intents to be representative of all intents.
• ❌ B. Automate the more complicated requests first because those require more of the agents’ time.
• ⭕ C. Automate the 10 intents that cover 70% of the requests so that live agents can handle the more complicated requests.
• ❌ D. Automate intents in places where common words such as “payment” only appear once to avoid confusing the software.

---

Source:Dialogflow