Abstract
On-demand digital media streaming systems may experience playback latency, such as buffering, as content can be retrieved reactively after a user makes a selection. The described systems and methods can address this by using a presence signal to trigger a predictive process. A presence signal can be generated, for example, when a user’s computing device (e.g., a smartphone, smart watch, or wearable device) connects to a local network (e.g., a Wi-Fi network) or enters a geofence. Upon receiving this trigger, and with appropriate user permissions being granted, a predictive modeling engine can analyze the user’s content consumption history and context to identify media items the user is likely to select. An initial segment of one or more predicted items can then be proactively downloaded and cached on a media playback device (e.g., a smart television, streaming stick, or set-top box). Making a portion of the content locally available before a user interaction may reduce buffering delays and decrease the time between content selection and playback.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Shin, D, "Presence-Triggered Predictive Caching of Media Content", Technical Disclosure Commons, (November 17, 2025)
https://www.tdcommons.org/dpubs_series/8881