Indico Data, the unstructured data company, unveiled Indico 5, a major release of its AI-powered Unstructured Data Platform. Indico 5 addresses the rapidly growing market demand for software solutions that drive efficiency and accelerate automation and intelligent document processing (IDP) initiatives using unstructured data.
The Indico Unstructured Data Platform, through a combination of a proprietary training data corpus, composite AI technology, and machine teaching application interface, drives an AI success rate, with more than 90% of projects in production.
Indico 5 was purpose-built to streamline some of the toughest unstructured data automation problems in IDP, such as document unbundling of PDFs, and ensuring the human training corrections of models made in the review cycle can be automated in future situations. The addition of linked relationship labeling and a new, more intuitive visual interface empowers organizations to easily automate, analyze, and apply unstructured data, illuminating opportunities, improving efficiency, and reducing risk. New features include: Automatic Document Unbundling, Linked Labels, Staggered Loop Training, Universal Document Support, and Workflow Canvas.
Access Innovations, Inc. announced Video/Audio to Text to Tagging (VATT), a solution that translates audio files to time stamped text transcripts for indexing, classifying, and enriching by Data Harmony Hub. Originally developed to improve search precision on training videos for a large chemical manufacturer, the new tagging capabilities can be used on any video or audio content from lectures, demonstrations, conferences, and more. Once metadata tagging is completed by Data Harmony Hub, a “point in time” search allows for users to find the precise time within the video/audio where the speaker or narrator discusses a specific topic, without wasting time browsing and scrolling through the entire video to find the information they need.
Organizations are generating video content and placing it on YouTube and other video aggregation service platforms. If transcripts are not available and searchable, the viewer is disappointed when they attempt to search a library of videos. In most cases, search is only available on the video title, the speaker or performer name, and possibly the date. With the video/audio to text to tagging solution, viewers enjoy a more robust search experience, reduce noise within the search results, and pinpoint topics and concepts of interest.