Which solution will meet these requirements MOST cost-effectively?
Use S3 Event Notifications to invoke an AWS Lambda function when PutObject requests occur. Program the Lambda function to analyze the object and extract the ingredient names by using Amazon Comprehend. Store the Amazon Comprehend output in the DynamoDB table.
Use an Amazon EventBridge rule to invoke an AWS Lambda function when PutObject requests occur. Program the Lambda function to analyze the object by using Amazon Forecast to extract the ingredient names. Store the Forecast output in the DynamoDB table.
Use S3 Event Notifications to invoke an AWS Lambda function when PutObject requests occur. Use Amazon Polly to create audio recordings of the recipe records. Save the audio files in the S3 bucket. Use Amazon Simple Notification Service (Amazon SNS) to send a URL as a message to employees. Instruct the employees to listen to the audio files and calculate the nutrition score. Store the ingredient names in the DynamoDB table.
Use an Amazon EventBridge rule to invoke an AWS Lambda function when a PutObject request occurs. Program the Lambda function to analyze the object and extract the ingredient names by using Amazon SageMaker. Store the inference output from the SageMaker endpoint in the DynamoDB table.
Explanations:
This option utilizes S3 Event Notifications to trigger a Lambda function upon file uploads, which is efficient and cost-effective. Amazon Comprehend is suited for extracting entities from text and requires no machine learning expertise to implement. The extracted ingredient names can be stored directly in DynamoDB, making the solution straightforward and automated.
This option suggests using Amazon Forecast, which is not designed for text analysis or entity extraction; it is used for time series forecasting. This would not meet the requirement of extracting ingredient names from recipe records, making it an unsuitable choice.
While this option also uses S3 Event Notifications, it relies on creating audio recordings of text files with Amazon Polly. This adds unnecessary complexity and does not automate the extraction of ingredient names. Additionally, it requires manual intervention from employees to analyze the audio, making it less efficient and cost-effective.
This option suggests using Amazon SageMaker for extracting ingredient names. Although SageMaker is capable of building machine learning models, it requires machine learning knowledge to set up and manage, which contradicts the requirement that the company lacks employees with such expertise. This makes it an impractical and costly solution for the stated needs.