Contact Lens for Amazon Connect is a set of machine learning (ML) capabilities integrated into Amazon Connect.
Full text search and sentiment analysis
Conduct fast, full-text search on the Amazon Connect contact search page. Search for contacts based on keywords in transcripts, speaker-separated sentiment scores (-5 to +5), and other call characteristics such as non-talk time resulting from significant pauses in conversation.
Enhanced Contact Trace Record (CTR) detail page
View call participation details such as call transcript by each speaker, customer sentiment trends, customer sentiment break-down, interruptions, and non-talk time directly on the Amazon Connect CTR detail page.
Automated categorization of contacts
Within Amazon Connect you can configure and categorize your customer contacts by creating a rule based on specified attributes and keywords/phrases mentioned by customers or agents. All contacts that meet specified criteria, such as competitive mentions, regulatory disclosures, and script compliance will contain the corresponding label as part of the Contact Lens for Amazon Connect analytics file in your included S3 bucket.
Powerful new data
The Contact Lens for Amazon Connect output file contains call transcripts along with rich metadata such as sentiment, categorization labels, talk speed, issues detected, and interruptions. This enables a wide range of use cases. For example, you can use this data in a Business Intelligence tool along with your Customer Relationship Management data to gain insights into customer engagements. Your data science teams can also use this data to create custom machine learning models.
Sensitive data redaction
Contact Lens for Amazon Connect offers customers the ability to automatically detect and redact sensitive data from both the call recording and the associated transcript. With it, you can focus on extracting insights to improve your customer experience while being considerate of sensitive customer information.
Issue detection
Contact Lens for Amazon Connect uses natural language processing (NLP) to visually identify words and phrases that indicate call drivers or reasons for customer outreach. This is reflected in your call transcripts on the contact detail page to help contact center supervisors uncover new issues. For example, your supervisors can quickly discover a price discrepancy between a website and an email promotion.
Real-time alerting for supervisors (coming soon)
Configure real-time alerts for supervisors based on keywords uttered by customers or agents in conversations.
Language support
Currently, Contact Lens for Amazon Connect supports US English, UK English, AUS English, IN English, and Spanish. We will be adding more languages throughout 2020.
Get started building with Contact Lens for Amazon Connect in the AWS Management Console.