Abstract
Discussions related to shared digital media may be disconnected from the visual content, which can fragment the user experience and delink comments from specific visual details. Systems and methods are described that can augment media with an interactive, context-aware conversational layer. A user can affix an annotation to a specific spatial location within visual media, such as an image, and this annotation may serve as a contextual prompt for a multimodal artificial intelligence (AI) model. The AI model can process the annotation's text in conjunction with the visual data of the underlying media region to generate and present relevant follow-up suggestions as interactive elements. This approach can embed discussions onto the visual media, creating a contextual record that may facilitate a more integrated and collaborative user experience for activities such as trip planning or social commerce.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Sharma, Harshita, "System for AI-Generated Interactive Suggestions on Spatially Annotated Digital Media", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12069