Skip to main content

AWS Solutions Library

Guidance for Analyzing Customer Conversations on AWS

Go to sample code

Overview

This Guidance demonstrates how to use voice analytics to uncover insights from customer phone conversations and improve customer satisfaction. Customer service phone calls are automatically transcribed using speech-to-text technology and then analyzed using generative AI natural language processing to identify trends, complaints, product issues, and frequently asked questions. The insights gained from these analyses are summarized in reports for management, helping you better understand customer pain points and opportunities to enhance the customer experience.

How it works

This architecture diagram shows how to build an automated workflow for analyzing contact center customer conversations (such as voice calls and chat) using foundation models hosted on Amazon Bedrock.

Download the architecture diagram

Deploy with confidence

Ready to deploy? Review the sample code on GitHub for detailed deployment instructions to deploy as-is or customize to fit your needs. 

Go to sample code

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

The built-in logging capabilities, operational metrics of Lambda, Amazon S3, and DynamoDB, coupled with Amazon CloudWatch, provide visibility into the application's performance. The event-driven architecture, facilitated by Amazon S3 events, streamlines deployment and maintenance processes. It also enables efficient resource allocation and scalability, while reducing operational overhead. This approach allows for proactive identification and resolution of issues.

Read the Operational Excellence whitepaper

Granular access control mechanisms, such as AWS Identity and Access Management(IAM) policies in Amazon S3, Lambda, and DynamoDB, secure the application. Scoping down IAM policies to the minimum required permissions limits unauthorized access to critical resources. Secure HTTPS connections between services like Lambda, Amazon Transcribe, and Amazon S3 protect data in transit, while encryption with AWS Key Management Service (AWS KMS) safeguards data at rest in DynamoDB.

Read the Security whitepaper

Managed services such as Amazon Transcribe, Lambda, and Amazon SNS enhance the application’s reliability, as AWS handles infrastructure, scaling, and failover mechanisms for the services. The event-driven architecture decouples services, reducing single points of failure and allowing easier recovery or replacement of individual components.

Read the Reliability whitepaper

Amazon Transcribe offers specialized capabilities for efficient audio and text data processing for faster analysis and quick responses. Lambda's automatic scaling minimizes resource provisioning concerns. Following best practices for Lambda memory size settings optimizes performance. For DynamoDB, Provisioned Capacity mode with autoscaling accommodates gradually changing or predictable traffic patterns, optimizing performance.

Read the Performance Efficiency whitepaper

The pay-as-you-go pricing model of serverless services like Lambda and Amazon S3 optimizes costs by avoiding over-provisioning or underutilization. The DynamoDB Time to Live (TTL) feature automatically deletes aged-out data without consuming write throughput, and AWS Graviton2 Processors power cost-effective Lambda functions.

Read the Cost Optimization whitepaper

Serverless services such as Lambda and managed services such as Amazon S3, Amazon Transcribe, and DynamoDB enhance sustainability by optimizing resource utilization, eliminating idle waiting times, and avoiding unnecessary compute resource consumption. Automatic scaling provisions resources based on demand, minimizing idle resources and associated energy consumption. Amazon S3 storage classes, lifecycle policies, and the DynamoDB TTL feature further reduce storage costs.

Read the Sustainability whitepaper

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.