Please visit the COVID-19 response page for resources and advice on managing through the crisis today and beyond.
A leading European insurance company was receiving an increasing number of customer emails relating to policies. Personnel were diligently reading and analyzing messages and attachments to answer questions and close claims. Tracking the requests in these unstructured emails was monotonous, time consuming and costly, and as the company grew, this process wasn’t sustainable. So, the insurer wanted to enable smart automated data extraction to handle its large volume of email inquiries, reducing agent workload, improving customer service and lowering costs.
Cognizant designed a machine learning model based on artificial intelligence (AI) to extract policy, claim and agent-related information automatically from unstructured incoming emails and attachments. The solution integrates our client’s mail exchange server with a cognitive engine on Microsoft Azure. It uses natural-language classification, AI-driven self-learning pattern recognition and keyword text recognition to extract data automatically and then respond without manual intervention. It integrates with Graph API and other workflow engines to provide image recognition for select requests and tracks the accuracy.
We also implemented analytical capabilities to track the consumer emotion index of emails and leverage image recognition for select requests. Our machine learning model incorporates continuous training and improvement, uses a configurable set of key phrases and value patterns for future extensibility, and integrates with third-party tools via a web interface.
We improved our client’s process without disrupting it, increasing operational efficiency while enabling the insurer to reassign human resources to more value-added tasks. The solution also improves the customer experience, easily detecting and responding to different types of requests using the client's large datasets. The configurable interface tracks accuracy statistically.
cost savings over manual processing
increase in the ability to handle inquiries
increase in the speed of customer service
SPREAD THE WORD