AWS Adds AI Capabilities to Texttract, Transcribe, and Kendra

Amazon Web Services (AWS) on Tuesday added new artificial intelligence (AI) capabilities to some of its services, including Textract, Transcribe, Kendra, CodeWhisperer and HealthLake.

The new updates, the company says, should enhance AWS’ AI services portfolio and sit atop its three-layered machine learning stack, which includes libraries of learning hardware and software. automatic, and Amazon SageMaker, a fully managed ML. development environment.

Businesses can use the updated out-of-the-box AI services without any machine learning expertise, the company said.

Amazon Textract Lending to Improve Document Processing

Offered as part of Amazon Textract Lending, an AI service for extracting text, handwriting, and data from scanned documents, including tables, Amazon Textract Lending is designed to speed up the processing of loan documents in a cost-effective way, said Bratin Saha, vice president of AI and machine learning. at Amazon, wrote in a blog post.

The Analyze Lending feature brings together multiple machine learning models to classify various documents that commonly occur in mortgage loan processing, and then extracts required information from those documents to improve loan document processing workflows, the company said. society. Texttract Lending can process a 3,000-page mortgage application in less than five minutes, AWS said.

Other features include identifying missing signatures and documents in mortgage applications.

Although the company does not charge any upfront fees for the services, businesses must pay between $1.50 per 1,000 pages and $70 per 1,000 pages, depending on the services used.

Amazon Transcribe Call Analytics to Improve Customer Experience

To help businesses deliver better service and a better customer experience, AWS has updated its automatic speech recognition (ASR) service, Amazon Transcribe, to provide real-time call analytics.

Offered as part of the voice recognition service, Amazon Transcribe Call Analytics relies on models trained in natural language processing (NLP) to provide real-time insights such as call reason detection, sentiment analysis and detection of issues such as repeated requests to speak to the manager, the company said.

“With Amazon Transcribe Call Analytics, developers can create a real-time system that provides contact center agents with relevant information to resolve customer issues or alert supervisors to potential issues,” Saha wrote in the blog post. .

The service, which generates call summaries to help agents, protects sensitive customer data by identifying and removing personal information during live calls, AWS said.

Amazon Transcribe Call Analytics is offered on a consumption-based pricing model and comes with a free tier.

Amazon Kendra gets new search capabilities

AWS has updated its AI-powered enterprise search service Amazon Kendra to add new functionality that supports tabular search in HTML.

“Clients can find more specific answers faster in HTML documents, whether in the narrative body or in table form, using natural language questions,” Saha wrote, adding that the capability uses templates. deep learning to interpret relevant column and row data. .

Amazon Kendra is typically used by enterprise users to search content repositories using natural language queries. The service connects to all repositories through its built-in connectors.

AWS announced that it has added support for queries in seven languages, including French, Spanish, German, Portuguese, Japanese, Korean, and Chinese.

Kendra, too, is based on a consumption-based pricing model and comes with a free tier.

Amazon HealthLake gets an analytics update

AWS also on Tuesday updated HealthLake, its HIPAA-compliant service for storing, transforming, and querying health data, to offer analytics.

Amazon HealthLake Analytics, according to the company, will enable healthcare and life sciences companies to query and gain insights from various types of datasets, such as imagery, text or genetics, both at the individual and population level, the company said.

“This removes the need for healthcare providers to perform complex data exports and data transformations,” Saha wrote, adding that the capability normalizes all raw data from disparate data sources into an analytical format. and interoperable in minutes.

AWS has priced the HealthLake service based on consumption.

The company also added the ability to store, access, and analyze petabyte-scale medical images from the HealthLake service.

Amazon HealthLake Imaging, the new capability, is designed to be combined into clinical workflows to retrieve images through any device, Saha wrote.

AWS says this feature will help healthcare companies reduce costs because healthcare systems typically store multiple copies of the same imaging data in clinical and research systems, driving up storage costs.

In contrast, the imaging feature only stores a single copy of the image in the cloud.

CodeWhisperer now supports Builder ID

The cloud service provider said Tuesday that Amazon CodeWhisperer, its machine learning-based service that generates code recommendations, now supports AWS Builder ID, allowing any developer to securely sign up with their address. email and enable CodeWhisperer for their development environment from AWS Toolkit. .

In addition to Python, Java, and JavaScript, Amazon CodeWhisperer now supports

TypeScript and C# languages, the company said. The service has been added to the AWS Management Console, a portal for managing all AWS services used by a business.