Abstract
Media consumption may be fragmented across various application-based services, and centralized recommendation engines can operate within separate ecosystems, which may introduce privacy considerations. This disclosure relates to systems and methods for dynamically compiling a personalized media stream on a client device (e.g., a smartphone, smart watch, television, or wearable device). The approach can utilize an on-device, multi-agent bidding protocol where a user agent may initiate a content auction by broadcasting abstracted, locally-derived context tokens to multiple streaming service agents that can represent different providers. These agents may then submit bids containing relevant content, and the user agent can select a sequence for playback from the submitted bids. This client-centric model may facilitate a contextually-aware media channel by interleaving content from various sources, which could reduce the transmission of certain user data to external servers.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Kushwaha, Vivek, "On-Device Bidding Protocol for Context-Aware Dynamic Media Stream Sequencing", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12066