Customer Service is a core service for a lot of businesses around the world and it is getting disrupted at the moment by Natural Language Processingpowered applications. In this first assignment you will implement a serverless, microservice-driven web application. Specifically, you will build a Dining Concierge chatbot that sends you restaurant suggestions given a set of preferences that you provide the chatbot with through conversation.
This assignment has the following requirements:
- Build and deploy the frontend of the application
- Repurpose the following frontend starter application to
- interface with your chatbot
- Host your frontend in an AWS S3 bucket
- Set the bucket up for website hosting
- https://docs.aws.amazon.com/AmazonS3/latest/dev/Host ingWebsiteOnS3Setup.html
- Build the API for the application
- Use API Gateway to setup your API
- use the following API/Swagger specification for your API
https://github.com/001000001/aics-columbias2018/blob/master/aics-swagger.yamlUse http://editor.swagger.io/ to visualize this file
- You can import the Swagger file into API
Create a Lambda function (LF0) that performs the chat operation Use the request/response model (interfaces) specified in the API specification above
- For now, just implement a boilerplate response to all messages:
- User says anything, Bot responds: “I’m still under development. Please come back later.”
- You will need to enable CORS on your API methods
- API Gateway can generate an SDK for your API,
which you can use in your frontend. It will take care of calling your API, as well as session signing the API calls — an important security feature
Build a Dining Concierge chatbot using Amazon Lex.
- Create a new bot using the Amazon Lex service. Read up the documentation on all things Lex, for more information:
- Create a Lambda function (LF1) and use it as a code hook for Lex, which essentially entails the invocation of your Lambda before Lex responds to any of your requests — this gives you the chance to manipulate and validate parameters as well as format the bot’s responses. More documentation on Lambdacode hooks at the following link:https://docs.aws.amazon.com/lex/latest/dg/using-lambda.html
- Bot Requirements:
1.Implement at least the following three intents:
- The implementation of an intent entails its setup in Amazon Lex as well as handling its response in the Lambda function code hook.
- Example: for the GreetingIntent you need to 1.create the intent in Lex, 2. train and test the intent in the Lex console, 3. implement the handler for the GreetingIntent in the Lambda code hook, such that when you receive a request for the GreetingIntent you compose a response such as “Hi there, how can I help?”
- For the DiningSuggestionsIntent, you need to collect at least the following pieces of information from the user,through conversation:
- Dining Time
- Number of people
- Phone number
- Based on the parameters collected from the user, push the information collected from the user (location,cuisine, etc.) to an SQS queue (Q1). More on SQS queues here: https://aws.amazon.com/sqs/
- Also confirm to the user that you received their request and that you will notify them over SMS once you have the list of restaurant suggestions.
Integrate the Lex chatbot into your chat API
1. Use the AWS SDK to call your Lex chatbot from the APILambda (LF0).
2.When the API receives a request, you should 1. extract the text message from the API request, 2. send it to your Lex chatbot, 3. wait for the response, 4. send back the response from Lex as the API response.
Use the Yelp API to collect 5,000+ random restaurants from
- Use the following tools:
- Get restaurants by your self-defined cuisine types
- You can do this by adding cuisine type in the search term ( ex. Term: chinese restaurants)
- Each cuisine type should have 1,000 restaurants or so.
- Make sure your restaurants don’t duplicate.
2.DynamoDB (a noSQL database)
- Create a DynamoDB table and named “yelp-restaurants”
- Store the restaurants you scrape, in DynamoDB (one thing you will notice is that some restaurants might have more or less fields than others, which makes DynamoDB ideal for storing this data)
- With each item you store, make sure to attach a key to the object named “insertedAtTimestamp” with the value of the time and date of when you inserted the particular record
- Store those that are necessary for your recommendation.(Requirements: Business ID, Name, Address,Coordinates, Number of Reviews, Rating, Zip Code)
3.Note: you can perform this scraping from your computer or
- from your AWS account — your pick.Create an ElasticSearch instance using the AWS ElasticSearch Service.
- Create an ElasticSearch index called “restaurants”
- Create an ElasticSearch type under the index “restaurants” called “Restaurant”
- Store partial information for each restaurant scraped in ElasticSearch under the “restaurants” index, where each entry has a “Restaurant” data type.
You only need to store RestaurantID and Cuisine for each restaurant
本网站支持 Alipay WeChatPay PayPal等支付方式
E-mail: firstname.lastname@example.org 微信号:vipnxx