Abstract
Existing educational media content consumed on connected televisions (CTVs) and smart television (TV) platforms remains isolated from personal productivity ecosystems due to information-capture friction, lack of ambient context extraction, and passive viewing limitations. To address these deficiencies, the disclosed technology provides an operating-system-level knowledge capture and active learning bridge connecting a smart television platform with a cloud-based artificial intelligence (AI) tool. When a user issues a voice command during media content playback on the CTV or smart television platform, an on-device assistant along with operating system services scrape active media content metadata, exact playback timestamps, and closed-caption transcript text snippets to generate a structured payload for the media content. Cloud-based backend services receive and then route the structured payload to an AI tool account of the user for semantic workspace organization. Furthermore, an AI tool associated with the AI tool account of the user processes closed-caption transcript text to dynamically generate interactive on-screen quizzes, flashcards, and ambient audio overviews formatted for television interfaces.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Gupta, Richa, "Cross-Surface Multimodal Knowledge Ingestion, Semantic Notebook Synthesis, and On-Screen Interactive Assessments from Ambient Media Displays", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12369