首页|Patent Application Titled 'Generative Content Based On User Session Signals' Pub lished Online (USPTO 20240338746)
Patent Application Titled 'Generative Content Based On User Session Signals' Pub lished Online (USPTO 20240338746)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Ahuja, Chakshu (San Jose, CA, US); Ahuja, Karuna (San Francisco, CA, US); Narlikar, Girija (Palo Alto, CA, US); Subramaniam, Apurvaa (Renton, WA, US), fil ed on April 4, 2024, was made available online on October 10, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: "An online system may provide recommendations to users of cont ent to interact with. For example, an online system may recommend items that may be of interest to a user for the user to order from the online system. However, recommendations commonly include content that encourages the user to interact w ith the content. This content, especially images and video, can be incredibly co stly for an online system to generate. This means that online systems generally reuse content for recommendations in many different contexts, but there may be i nstances where that content is not well suited for the context in which the reco mmendation is being made. For example, if a user is searching for items for a pa rty, a recommendation for a bag of chips would likely perform better with the us er if it included an image of multiple people enjoying the bag of chips, rather than two people sitting down to watch a movie. It is traditionally infeasible to generate the amount of content needed to cover the myriad different contexts in which users may be interacting with an online system, and thus online systems c ommonly use ineffective content to recommend interactions to users."
NETL
NSTL
