Contact Lens for Amazon Connect
Contact Lens for Amazon Connect is a set of machine learning (ML) capabilities integrated into Amazon Connect. With Contact Lens for Amazon Connect, contact center supervisors can better understand the sentiment, trends, and compliance of customer conversations to effectively train agents, replicate successful interactions, and identify crucial company and product feedback.
Today, most contact center analytics are based on basic metrics like call duration or customer relationship management (CRM) call notes that are typed in by the contact center agent. What's typically missing from these analytics is insight into the actual conversations between agents and customers. Contact center supervisors care about getting insights like whether agents are having effective conversations, whether any interesting trends in customer sentiment are occurring, or whether the agents are complying with company guidelines and regulatory requirements. This is challenging because audio data is virtually impossible for computers to directly search and analyze. Therefore, recorded speech needs to be converted to text before it can be used in applications. Historically, customers had to work with transcription providers that required them to sign expensive contracts and were hard to integrate into their technology stacks to accomplish this task. Many of these providers use outdated technology that does not adapt well to different scenarios, like low-fidelity phone audio common in contact centers, which results in poor accuracy. While speech-to-text analytics solutions have long promised access to these types of insights, they have not provided an accurate or cost-effective way to extract insights from these conversations.
Using AWS machine learning-based speech-to-text and natural language processing (NLP), Contact Lens for Amazon Connect automatically transcribes contact center calls to create a fully searchable archive and surface valuable customer insights. With Contact Lens for Amazon Connect, customer service supervisors can quickly and easily discover emerging themes and trends from customer conversations, directly in Amazon Connect. The machine learning models that power Contact Lens for Amazon Connect have been trained specifically to understand the nuances of contact center conversations in multiple languages. With Contact Lens for Amazon Connect, customer service supervisors can conduct fast, full-text search on call transcripts to quickly troubleshoot customer issues. They can also leverage call-specific analytics, including sentiment analysis and silence detection to spot customer experience issues and improve customer service agents’ performance. Contact Lens for Amazon Connect will also allow supervisors to be alerted to issues, like when an agent is unable to help a frustrated customer, giving them the ability to intervene earlier when a customer is having a poor experience (coming soon). Using these integrated capabilities requires no technical expertise, and getting started takes just a few clicks in Amazon Connect.
Deeper insight in minutes
Contact Lens for Amazon Connect is simple to set up and use. With only a few clicks, you can use ML-powered analytics to discover deep customer insights from your contact center. Through the intuitive UI, you can analyze call transcripts, customer and agent sentiment, and conversation characteristics without any coding.
With Contact Lens for Amazon Connect, you are only charged for what you use. There are no upfront costs, minimum fees, or long-term commitments, making it a cost-effective way to gain deeper customer insights. Contact Lens for Amazon Connect is also available in the AWS Free Tier, so Amazon Connect customers can try it without any initial investment.
Better customer experiences
Contact Lens for Amazon Connect helps supervisors improve the agent-customer interaction by providing insights into what makes a successful call, compliance risks, and trending topics. You also get rich metadata on call transcripts and conversation characteristics such as interruptions, talk speed, sentiment, and custom category labels.
Conduct fast, full-text search on calls for ad-hoc analysis. Search by keywords, customer and agent sentiment scores, and “non-talk” time to identify calls with varying levels of customer experiences, so that you can react quickly to improve contact center experiences. For example, you can identify what utterances are common in calls that end with positive or negative customer sentiment to improve agent call scripts.
Automated contact categorization
Track all customer conversations for compliance with company policy or regulatory requirements. Define and manage categories based on your specified criteria directly within Amazon Connect. For example, you can use these category labels to create scorecards that show what percentage of agents adhered to your company’s standard greetings and sign-offs.
One view for all analysis
Contact center supervisors can view data and reports from Contact Lens for Amazon Connect directly in the Amazon Connect UI. You can review details of individual calls, analyze transcripts, customer and agent sentiment, and conversation characteristics. For example, you can see how often a customer asks the agent to repeat themselves to identify agent coaching opportunities.
Open and flexible data
Contact Lens for Amazon Connect output file contains call transcripts along with rich metadata such as sentiment, categorization labels, talk speed, and interruptions. You can leverage this data in various existing systems. For example, you can use this data in a BI tool, like Amazon QuickSight, along with your CRM data to gain insights into customer engagements. Your data science teams can also use this data to create custom machine learning models with Amazon SageMaker.
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.
Sensitive data redaction
Contact Lens can also automatically detect and redact sensitive data such as name, address, and social security number from call recordings and transcripts. When recording and analyzing calls, businesses can protect sensitive customer information by controlling access to the redacted and non-redacted data through user-defined permission groups.