In the fast-paced world of customer service, efficiency and accuracy are paramount. After each call, contact center agents typically spend up to a third of the total call time summarizing the conversation with the customer. Additionally, manual summarization can lead to inconsistencies in style and level of detail due to different interpretations of note-taking guidelines. Not only can this post-contact work increase customer wait times, it can also pressure some agents to avoid taking notes altogether. Supervisors also spend a considerable amount of time listening to call recordings or reading transcripts to understand the essence of a conversation with a customer when investigating customer problems or evaluating an agent's performance. This can make it difficult to expand quality management within the contact center.
To address these issues, we launched a generative artificial intelligence (ai) call summarization feature in amazon Transcribe Call Analytics. Transcribe Call Analytics is an ai-powered generative API for generating highly accurate call transcriptions and extracting conversation insights to improve customer experience, agent productivity, and supervisor productivity. Powered by amazon Bedrock, a fully managed service that delivers a selection of high-performance base models (FMs) through a single API, generative call summarization in Transcribe Call Analytics produces call summaries that reduce agents' time. They spend time capturing and summarizing notes after each conversation. . This reduces customer wait times and improves agent productivity. Generative call summary also provides supervisors with a quick view of a conversation without the need to listen to the entire call recording or read the entire transcript.
As noted by Praphul Kumar, Chief Product Officer at SuccessKPI,
“Generative call summarization in the amazon Transcribe Call Analytics API has allowed us to add generative ai capabilities to our platform more quickly. With this feature, we can improve productivity in our customers' contact center by automatically summarizing calls and eliminating the need for agents to write notes after calls. “We look forward to bringing this valuable capability into the hands of many more great companies.”
We previously published Use Generative ai to Increase Agent Productivity with Automated Call Summarization. This new generative call summary feature automatically integrates with multiple services and handles the necessary configurations, making it simple and seamless to get started and reap the benefits. You do not need to manually integrate with services or perform additional configurations. Simply enable the feature from the amazon Transcribe console or by using the start_call_analytics_job API. You can also use generative call summarization through the amazon Transcribe Post Call Analytics solution for post-call summaries.
In this post, we show you how to use the new generative call summary feature.
Solution Overview
The following diagram illustrates the architecture of the solution.
You can upload a call recording to amazon S3 and start a Transcribe Call Analytics job. The summary is generated and uploaded back to S3 along with the transcript and analysis as a single JSON.
We show you how to use the generative call summary feature with a amazon-transcribe-post-call-analytics/blob/develop/pca-samples/src/samples/Auto1_GUID_001_AGENT_AndrewK_DT2023-02-20T07-55-51.wav” target=”_blank” rel=”noopener”>call sample Inquire about a used car through the following high-level steps:
- Create a new post-call analysis job and activate the generative call summary feature.
- Review the results of the generative call summary.
Previous requirements
To get started, upload your recorded file or the provided sample file to an amazon Simple Storage Service (amazon S3) bucket.
Create a new post-call analysis job
Complete the following steps to create a new post-call analysis job:
- In the amazon Transcribe console, choose Post-call analysis in the navigation panel below amazon Transcribe Call Analysis.
- Choose create job.
- For Nameget into
summarysample. - In it Language settings and Model type sections, leave the default settings.
- For Input file location in S3Find the S3 bucket that contains the uploaded audio file and choose Choose.
- In it Output data sectionleave it as default.
- Create a new AWS Identity and Access Management (IAM) role named
summarysamplerolewhich provides permissions for the amazon Transcribe service to read audio files from the S3 bucket.
- In it Role permission details section, leave it as default and choose Next.
- Lever Generative call summary on and choose create job.
Review the transcript and summary.
When the job status is Completeyou can review the transcript and summary by choosing the name of the work summarysample. He Text The tab shows the Agent and Customer sentences clearly separated.
He Generative call summary The tab provides a concise summary of the call.
Choose Download transcript for the JSON output containing the transcript and summary.
Conclusion
The world of customer service is constantly evolving and organizations must adapt to meet the growing demands of their customers. amazon Transcribe Call Analytics presents an innovative solution to optimize the post-call process and improve productivity. With generative call summarization, contact center agents can spend more time interacting with customers and supervisors can quickly obtain information without extensive call reviews. This feature improves efficiency and allows companies to expand their quality management efforts, allowing them to deliver exceptional customer experiences.
Generative call summarization in amazon Transcribe Call Analytics is generally available today in English in the Eastern US (Northern Virginia) and Western US (Oregon). We invite you to share your thoughts and questions in the comments section.
Learn more:
About the authors
amy dani is a Senior Technical Program Manager at AWS focusing on ai/ML services. Throughout his career, he has focused on delivering transformative software development projects for the federal government and large enterprises in industries as diverse as advertising, entertainment, and finance. Ami has experience driving business growth, implementing innovative training programs, and successfully managing complex, high-impact projects. She is a collaborative partner and strategic problem solver, consistently delivering results that exceed expectations.
Gopikrishnan Anilkumar is a Senior Technical Product Manager on the amazon Transcribe team. He has 10 years of product management experience across a variety of domains and is passionate about ai/ML. Outside of work, Gopikrishnan loves to travel and likes to play cricket.
