When viewing online videos, users can engage in additional activities such as making notes, researching, summarizing, or seeking help in understanding the material. However, performing such actions can need frequent context switching which can be frustrating and time-consuming. Further, users may lose interest in certain videos if the content is difficult to understand or lacks context. This disclosure describes techniques for enhancing the online video viewing experience by providing an artificial intelligence (AI) powered assistant (chatbot) that assists users in tasks such as note taking, summarization, video bookmarking, etc. and that can also support contextual interaction. The AI assistant can be powered by a large language model which can be made available as an option specifically provided the video hosting platform or as a local user interface generated by a client operating system. The large language model can be customized on the particular provider’s video content. The AI assistant can be multimodal, e.g., accessible via voice as well as text-based user interfaces. Summaries or answers provided by the AI chatbot can be accompanied by links to other videos (e.g., from the same provider, or other providers), search engine results, or other online resources, to enable the user to access source references for the answers.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.