At Ignite 2024, Microsoft announced a new service called Azure AI Content Understanding, which they claim is groundbreaking. This new AI service can understand and process unstructured data, including documents, images, videos, and audio, and transform it into meaningful insights.
Most AI services in the market right now are targeted toward specific data types. You can have language understanding using text-based APIs, OCR using image APIs, and more. Azure AI Content Understanding addresses this problem by offering a unified service that can accept any form of data.
To extract information from unstructured data, this new Azure AI service offers prebuilt schemas, which can be further customized to extract the data needed. To further improve the app over time, the service offers confidence scores for minimal human intervention and enables continuous improvement through user feedback.
Since Azure AI Content Understanding integrates different modalities into a unified workflow, Microsoft claims that the overall cost for enterprises to develop AI applications will come down significantly.
Microsoft highlighted the following example scenarios where this new service can be used effectively.
- Post call analytics: Extract analytics on call center or recorded meeting call data, allowing you to aggregate data on the sentiment, speakers, and content discussed, including specific names, companies, user data, and more.
- Tax process automation: Analyze tax documentation to extract key content and expedite the process of tax filing. It can extract content from common tax documentation and can also be customized for specific needs.
- Media asset management and content creation assistance: Extract key features from images and videos to better manage media assets and enable search on your data for entities like brands, setting, key products, people, and more.
- Insurance claims: Analyze and process insurance claims and other low-latency batch processing scenarios to automate previously time-intensive processes.
- Highlight video reel generation: Identify key moments in a video to extract the highlights and summarize the full content. One example could be showcasing the scoring drives in a sporting event, and other key moments in the game. To learn more about how Content Understanding addresses this scenario, check out this blog by Joe Filcik
The Azure AI Content Understanding service is now available in preview.