Improve customer service efficiency with AI-powered summarization using Amazon Transcribe Call Analytics

Machine Learning


In the fast-paced world of customer service, efficiency and accuracy are paramount. After each call, contact center agents often spend up to one-third of the total call time summarizing the conversation with the customer. Additionally, manual summarization can result in inconsistencies in style and level of detail due to different interpretations of note-taking guidelines. Not only does this post-contact work increase wait times for customers, but it can also put pressure on some agents to avoid note-taking altogether. Supervisors also often listen to call recordings and read transcripts to understand the key points of customer conversations when investigating customer issues or evaluating agent performance. It takes a lot of time. This can make it difficult to scale quality control within your 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 that generates highly accurate call transcripts and extracts conversation insights to improve customer experience, agent productivity, and supervisor productivity. Powered by Amazon Bedrock, a fully managed service that provides high-performance foundation model (FM) choices through a single API, Transcribe Call Analytics' generative call summarization helps agents capture notes after each conversation. Generate call summaries that reduce the time you spend summarizing. . This reduces customer wait times and increases agent productivity. Generative call summaries also allow supervisors to gain quick insights into conversations without having to listen to the entire call recording or read the entire transcript.

Praphul Kumar, Chief Product Officer, SuccessKPI said:

“The Amazon Transcribe Call Analytics API's generative call summarization allows us to add generative AI capabilities to our platform more quickly. This feature automatically summarizes calls and eliminates the need for agents to write notes after a call. We look forward to bringing this valuable functionality into the hands of even more large enterprises.”

We previously published how you can use generated AI to improve agent productivity through automated call summarization. This new generative call summarization feature automatically integrates with multiple services and handles the necessary configuration, making it easy and seamless to get started and realize the benefits. There is no need to manually integrate with services or perform any additional configuration. Simply turn on this feature from the Amazon Transcribe console or using the start_call_analytics_job API. You can also generate post-call summaries through Amazon Transcribe Post Call Analytics Solution.

This post explains how to use the new generation call summarization feature.

Solution overview

The following diagram shows the solution architecture.

You can upload call recordings to Amazon S3 and start a Transcribe Call Analytics job. A summary is generated and uploaded to S3 as a single JSON along with the transcript and analysis.

The following high-level steps demonstrate how to use the Generated Call Summarization feature using a sample call that inquires about used cars.

  1. Create a new post-call analysis job and turn on the generative call summarization feature.
  2. Check the summary results of the generate call.

Prerequisites

First, upload the recorded file or the provided sample file to your Amazon Simple Storage Service (Amazon S3) bucket.

Create a new post-call analysis job

To create a new post-call analysis job, follow these steps:

  1. In the Amazon Transcribe console, Post-call analysis below the navigation pane Amazon Transcribe call analysis.
  2. choose Create a job.
  3. for nameinput summarysample.
  4. inside Language settings and model type section, leave the default settings.
  5. for Input file location on S3browse to and select the S3 bucket containing the uploaded audio file choose.
  6. inside Output data sectionleave the default.
  7. Create a new AWS Identity and Access Management (IAM) role named . summarysamplerole This provides Amazon Transcribe service permissions to read audio files from your S3 bucket.
  8. inside Role privilege details section, leave the default and select Next.
  9. toggle Generate call summary Please turn on and select Create a job.

Check transcription and summary

If the job status is completionselect the job name to see the transcription and summary. summarysample.of sentence The tabs display clear separation of agent and customer statements.

of Generate call summary The tab provides a concise summary of the call.

choose Download transcript For JSON output with transcript and summary.

conclusion

The world of customer service is constantly evolving and organizations must adapt to meet the increasing demands of their clients. Amazon Transcribe Call Analytics introduces an innovative solution that streamlines the post-call process and improves productivity. Generative call summaries allow contact center agents to spend more time with customers and supervisors to quickly gain insights without extensive call reviews. This feature increases efficiency and enables companies to scale their quality control efforts and deliver a superior customer experience.

Amazon Transcribe Call Analytics generated call summaries are now generally available in English in US East (N. Virginia) and US West (Oregon). Please share your thoughts and questions in the comments section.

learn more:


About the author

Amidani I'm a senior technical program manager at AWS with a focus on AI/ML services. During her career, she has focused on delivering innovative software development projects to the federal government and large corporations in a variety of industries, including advertising, entertainment, and finance. Ami has experience driving business growth, implementing innovative training programs, and successfully managing complex, high-impact projects. She is a strategic problem solver, a collaborative partner, and consistently delivers results that exceed expectations.

Gopikrishnan Anilkumar I am a Senior Technical Product Manager on the Amazon Transcribe team. He has his 10 years of product management experience across various fields and is passionate about AI/ML. Outside of work, Gopikrishnan loves to travel and likes to play cricket.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *