Amazon Comprehend Customers and Partners

We strive to combine technology and business domain expertise to help our customers understand compliance risks in their supply chain. We needed a way to process compliance documents at scale. Our process is to read images and PDF documents with forms, tables, and free-form text and extract data of interest from within those documents. Amazon Textract's OCR technology enabled us to extract text from documents. Amazon Comprehend's context-aware NLP APIs extracted business-specific entities and their values from the text. We also incorporated humans in our workflow using Amazon Augmented AI (Amazon A2I), to have our teams review extracted data and provide feedback to the ML models and help improve them over time. Using this efficient mix of human and machine learning along with AppSync and Amplify provided us more accurate insights into our customers' supply chain risk and saved them hundreds of hours in manually reviewing documents. They can now get immediate feedback on whether their company is at compliance risk.

AWS and Amazon Business digital implementations into ExxonMobil's procurement organization is enhancing its global operations and preparing them for unexpected disruptions.  "We’ve worked with the Amazon ML Solutions Lab to develop a proof of concept aimed at maximizing contract utilization and further reduction of costs. One approach leverages Amazon SageMaker to improve identification of best-matched catalog items from free text entries in ExxonMobil’s eProcurement system, Smart by GEP. When catalog item descriptions are not readily available, we use Amazon Comprehend to create a bespoke classification model to map free text entries to supplier contract agreements.

FINRA receives millions of documents with unstructured data to support investigative, examination, and compliance processes. Our investigators and examiners had to manually go through documents page by page or run very targeted searches to find what they needed. With Amazon Comprehend, we can quickly extract individuals and organization, match extracted entities to FINRA records, flag individual of interest, and detect similarities with other documents.

We provide legal professionals with insightful research and analytics to help them make informed decisions. Therefore, we are always looking for better ways to discover insights from legal documents. Thanks to Amazon Comprehend's automatic machine learning (ML), we can now build accurate custom entity recognition models without getting into the complexities associated with ML. The entities that we care about the most, such as judge and attorney, can be identified quickly from over 200 million documents at above 92% accuracy.

Procuring human processing and analysis of past employee surveys cost multiple euros per interview. By using Amazon Comprehend and other AWS services, we are getting translation, processing, and analysis for less than one euro per interview.

Using Comprehend to put a customer problem in front of the right person really gives us the best chance of retaining that customer going forward.

 

Our Sparq platform connects your most important customer data from any source—including transaction, attitude, emotion, and intent data—to build dynamic customer profiles that give every team and business system a unified view of the customer. By integrating with Amazon Comprehend’s sentiment analysis capability, the platform now turns qualitative customer feedback into actionable insight, determining whether their feedback is positive, negative, or neutral at over 90% accuracy.

Understanding customer sentiment across various products or services are key to understanding the health of the business. Amazon Comprehend Targeted Sentiment allows our customers to not only understand sentiment for a conversation but also drill down to specific areas of product or business at scale.

We are very excited about the Amazon Comprehend Targeted Sentiment feature because it will enhance our existing open-ended survey response reporting in Gallup Access. We currently report overall sentiment related metrics and with this new feature, we will be able to provide more targeted sentiment within those survey responses. This will enhance the value proposition of our overall reporting and provide our users with more accurate and actionable data.

Our business is focused on delivering the best marketing content possible for the brands that depend on us. Using Amazon Comprehend, we were able to significantly increase the quality and accuracy of our platform’s content analytics capabilities, which identifies the right content for the most impactful marketing campaigns. Amazon Comprehend allows us to focus on our core product and not worry about the heavy lifting associated with building our own machine learning models.

Mobile messaging connects brands and consumers in a way that is direct, personal and authentic. At Vibes, we process billions of mobile messages every month and there are deep insights latent in the vast number of messages we process. Amazon Comprehend enables us to quickly extract key phrases, detect sentiment, and model topics from unstructured message content—providing marketers with a deeper understanding of their performance and actionable insights to deliver rewarding customer experiences.