Information about a particular topic, e.g., in response to a search query, is sometimes presented in a concise user interface (UI) such as a knowledge card or panel. Such panels are typically text intensive and can be unsuitable for certain users, e.g., users that have limited reading capability, or those who prefer visual content. This disclosure describes techniques to render a visual knowledge panel, e.g., one that primarily includes images, videos, and other visual content. Per the techniques, the visual knowledge panel is algorithmically created by mapping a text knowledge panel to existing video or image content such as video Q&A, a short video, a story illustrated by slideshow, etc.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Dey, Atreyee; Shah, Tanvi; Singla, Aditi; Ray, Zoltan; King, Rich; and Patel, Payal, "Algorithmically Generated Visual Knowledge Panels", Technical Disclosure Commons, (September 27, 2021)