Create a BigQuery dataset
Create a new table in BigQuery dataset
Build an ML model to predicts time taken to resolve an issue
Run the query to evaluate the ML model
Create a Dialogflow Agent
Import an IT Helpdesk Agent
Create a Fulfillment that Integrates with BigQuery
Implement a Helpdesk Chatbot with Dialogflow & BigQuery ML
Wouldn’t it be awesome to have an accurate estimate of how long it will take for tech support to resolve your issue? In this lab you will train a simple machine learning model for predicting helpdesk response time using BigQuery Machine Learning. You will then build a simple chatbot using Dialogflow, and learn how to integrate your trained BigQuery ML model with your helpdesk chatbot. The final solution will provide an estimate of response time to users at the moment a request is generated.
The exercises are ordered to reflect a common cloud developer experience:
Train a Model using BigQuery Machine Learning
Deploy a simple Dialogflow application
Use an inline code editor within Dialogflow for deploying a Node.js fulfillment script that integrates BigQuery
Test your chatbot
What you'll learn
How to train a machine learning model using BigQuery ML
How to evaluate and improve a machine learning model using BigQuery ML
How to import intents & entities into a Dialogflow agent
How to implement custom Node.js fulfillment scripts
How to integrate BigQuery with Dialogflow
Basic concepts and constructs of Dialogflow. Click here for an introductory Dialogflow tutorial that covers basic conversational design and fulfillment using a webhook.
Basic SQL and Node.js (or any coding language) knowledge.
Solution Feedback/Lab Help
For more information on this solution or feedback on this lab, please reach out to firstname.lastname@example.org.
이 실습의 나머지 부분과 기타 사항에 대해 알아보려면 Qwiklabs에 가입하세요.
- Google Cloud Console에 대한 임시 액세스 권한을 얻습니다.
- 초급부터 고급 수준까지 200여 개의 실습이 준비되어 있습니다.
- 자신의 학습 속도에 맞춰 학습할 수 있도록 적은 분량으로 나누어져 있습니다.