This Guidance offers a scalable, cost-effective approach to call analytics by gathering actionable insights to spot emerging trends, identify agent coaching opportunities, and assess the general sentiment of calls. It uses Amazon Machine Learning (Amazon ML) services to transcribe and extract rich insights from your customer conversations.
Architecture Diagram
Step 1
Call audio is delivered from the telephone system to an Amazon Simple Storage Service (Amazon S3) bucket.
Step 2
This event initiates the creation of an AWS Step Functions workflow, which orchestrates the entire analytics process.
Step 3
Amazon Transcribe and Amazon Comprehend are called by the workflow at the appropriate times for speech-to-text and text analytics functions.
Step 4
Transcript text and AI insights data is delivered to an Amazon S3 bucket to facilitate further analysis.
Step 5
Supervisors or agents can log in to the solution user interface to review transcripts and insights for specific calls.
Step 6
Business analysts can log in to Amazon QuickSight to build dashboards based upon the AI insights data, including sentiment trends, agent performance, hot topic trends, and entity insights.
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
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.
-
Operational Excellence
Data, such as speaker sentiment analysis and how well a customer’s internal compliance rules are met, is used to identify how effective contact center agents are at handling customer calls. The same data identifies the topics and entities discussed in the call. All of this data can be visualised in QuickSight to help business analysts identify trends from a customer’s perspective and potential training needs for agents.
-
Security
All data is encrypted both in motion and at rest, and can use customer-controlled AWS Key Management Service (AWS KMS) keys for this encryption. The solution is entirely serverless, but the AWS Lambda components can optionally run within a customer’s VPC, accessing external services such as Amazon Transcribe and Amazon S3 only through a customer’s approved endpoints.
-
Reliability
The solution is entirely serverless, and each of those services (Amazon Transcribe, Amazon S3) operate using multiple Availability Zones in a resilient fashion.
-
Performance Efficiency
The solution scales usage of its serverless components as it needs to, both up and down, in order to handle the concurrent processing of potentially thousands of calls or those times when there are no pending calls to process.
-
Cost Optimization
The solution only uses serverless components when there is an active call audio file to process, minimizing the incurred costs as much as possible. If required, the original audio files can be archived to lower cost long-term storage on a customer-specified schedule in order to minimize storage costs.
-
Sustainability
By using managed services and dynamic scaling, we minimize the environmental impact of the backend services.
Implementation Resources
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
Post call analytics for your contact center with Amazon language AI services
Your contact center connects your business to your community, enabling customers to order products, callers to request support, clients to make appointments, and much more. Each conversation with a caller is an opportunity to learn more about that caller’s needs, and how well those needs were addressed during the call.
This post demonstrates how to use Amazon Machine Learning (ML) services to transcribe and extract insights from your contact center audio recordings at scale.
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.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.