首页|'Predicting Replacement Items using a Machine-Learning Replacement Model'in Pat ent Application Approval Process (USPTO 20240403938)
'Predicting Replacement Items using a Machine-Learning Replacement Model'in Pat ent Application Approval Process (USPTO 20240403938)
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
This patent application has not been assigned to a company or institution.The following quote was obtained by the news editors from the background informa tion supplied bythe inventors: “Online systems present content to a user with w hich the user interacts. For example, an online concierge system presents items to a user for the user to add to an order. Online systems may tryto predict wha t content a user would be most interested in interacting with and present conten t withthe highest likelihood of interaction by the user. However, online system s generally limit the informationthey use for selecting content to information on actions that occurred before the user interaction with thecontent. For examp le, a video streaming platform may consider information on which videos a user has watched in the past to determine whether a user would be interested in a part icular video. However,while a user’s historical interactions may indicate what a user tends to be interested in, it does not directlyidentify a user’s interes ts. Thus, online systems that solely use historical interaction information by a usertend to be ineffective at selecting content based on a user’s current inte rests.”
NETL
NSTL
