[SEO Subhead]
This Guidance helps automakers enhance the contact center experience by using Amazon Connect and integrating with Original Equipment Manufacturer (OEM) Telematics Service Platform (TSP) and QnA Bot on AWS or retrieval augmented generation (RAG) technology, to build an intelligent automotive call platform. As an automaker, you can use your own knowledge base to help the artificial intelligence (AI)-powered conversational bot automatically answer questions from callers, while protecting the caller’s data from data leakage to third parties outside of the AWS environment. This Guidance enables inbound and outbound call services, such as emergency call (eCall), breakdown call (bCall), and information call (iCall) so that callers can get the tailored support they need for their vehicles.
Please note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
The caller dials the Original Equipment Manufacture (OEM) contact center built on Amazon Connect through vehicle 4G/5G phone network. The call streams to a call center through Web Real-Time Communications (WebRTC).
Step 2
Edge-side event data related to the caller’s vehicle (such as the vehicle number, GPS position, and more) transmits into the relevant OEM system (a Telematics Service Provider [TSP]) hosted on Amazon API Gateway, AWS Lambda, and Amazon Elastic Compute Cloud (Amazon EC2).
Step 3
The human agent channel gets connected, and a human agent can pick up the call to ask specific customer questions.
Step 4
In parallel with data being sent to a human agent channel, a bot channel opens and synchronizes with conversational content from the call. This channel uses QnA Bot on AWS, which is built on Amazon Lex and powered by Amazon SageMaker or Amazon Bedrock. Amazon OpenSearch Service stores the OEM knowledge base.
Step 5
Lambda requests contact data from Amazon Connect and then sends contact data to the OEM TSP system, retrieving the specific data of the customer and vehicle.
Step 6
OEM TSP data serves as prior knowledge. Customer conversation serves as input tokens for a large language model (LLM) hosted on SageMaker or Amazon Bedrock, which offers a choice of high-performing foundation models (FMs) from leading AI companies.
Step 7
QnA Bot on AWS gives suggested answers to the human agent.
Step 8
The human agent can reach out to the OEM system for remote vehicle support (for example, controlling the door locks, blinker, or horn) as requested by the caller.
Step 9
The human agent can also request services (such as towing, emergency services, or concierge) from service providers.
Step 1
The caller dials the Original Equipment Manufacture (OEM) contact center built on Amazon Connect through vehicle 4G/5G phone network. The call streams to a call center through Web Real-Time Communications (WebRTC).
Step 2
Edge-side event data related to the caller’s vehicle (such as the vehicle number, GPS position, and more) transmits into the relevant OEM system (a Telematics Service Provider [TSP]) hosted on Amazon API Gateway, AWS Lambda, and Amazon Elastic Compute Cloud (Amazon EC2).
Step 3
The human agent channel gets connected, and a human agent can pick up the call to ask specific customer questions.
Step 4
In parallel with data being sent to a human agent channel, a bot channel opens and synchronizes with conversational content from the call. This channel uses QnA Bot on AWS, which is built on Amazon Lex and powered by Amazon SageMaker or Amazon Bedrock. Amazon OpenSearch Service stores the OEM knowledge base.
Step 5
Lambda requests contact data from Amazon Connect and then sends contact data to the OEM TSP system, retrieving the specific data of the customer and vehicle.
Step 6
OEM TSP data serves as prior knowledge. Customer conversation serves as input tokens for a large language model (LLM) hosted on SageMaker or Amazon Bedrock, which offers a choice of high-performing foundation models (FMs) from leading AI companies.
Step 7
QnA Bot on AWS gives suggested answers to the human agent.
Step 8
The human agent can reach out to the OEM system for remote vehicle support (for example, controlling the door locks, blinker, or horn) as requested by the caller.
Step 9
The human agent can also request services (such as towing, emergency services, or concierge) from service providers.
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 ExcellenceRead the Operational Excellence whitepaper
Amazon Connect can easily scale to match business workload and relieve you from heavy infrastructure investment. The Amazon Connect Contact Lens function feature statistically queries key business indicators for analyzing service quality. Amazon Connect provides a ready-to-go cloud contact center for automotive customers with case processing, quality monitoring, and more.
-
SecurityRead the Security whitepaper
API Gateway can isolate access from frontend without reaching backend services. AWS Identity and Access Management (IAM) grants minimum role rights to the Lambda function, and the services and resources are deployed within a virtual private cloud (VPC) and without exposure to the public internet. Customer profile information is synchronized with AWS Key Management Service (AWS KMS) encryption into Amazon Connect, and the data transmission between Amazon Connect and the web user interface (UI) uses the TLS protocol.
-
ReliabilityRead the Reliability whitepaper
For meeting reliability demands, Amazon DynamoDB provides high availability and durability for tables by automatically replicating the data across multiple Availability Zones and AWS Regions. Lambda supports concurrent executions for high availability. Amazon Connect can provide high-quality service and create replicas in other AWS Regions for configuration, instance, and business backup. The components are highly available, and the services can easily recover from disasters.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
You can choose the right instance type for concurrency needs and to meet response time requirements. Lambda can also help you meet concurrency limits. Additionally, Amazon Connect can be deployed into different Regions and route customer request according to availability.
-
Cost OptimizationRead the Cost Optimization whitepaper
Services in this Guidance can help you save on costs by removing the need to invest in infrastructure and host unnecessary resources. For example, Lambda offers on-demand price models for inbound and outbound calls so that you only pay for the resources you use.
-
SustainabilityRead the Sustainability whitepaper
Cloud services, such as OpenSearch Service, Amazon Connect, and SageMaker for contact center, data analytics, and ML workloads reduce your on-premises data center footprint and associated energy usage. Amazon Connect allows remote work and flexible scaling to avoid overprovisioning of on-premises servers, lowering overall energy consumption. Amazon Connect, OpenSearch Service, and SageMaker can help you reduce your environmental impact through on-demand and efficient resource provisioning.
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
QnABot on AWS
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.