会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 7. 发明授权
    • Feedback system
    • 反馈系统
    • US08812419B1
    • 2014-08-19
    • US13158305
    • 2011-06-10
    • Eric TellerClaes-Fredrik MannbyKevin Anthony FurrCheryl Grunbock
    • Eric TellerMartin T. KingClaes-Fredrik MannbyKevin Anthony Furr
    • G06F17/00
    • G06Q10/10
    • Exemplary methods and systems are disclosed that apply feedback-based machine learning in order to more intelligently use context information to automate certain actions. An exemplary method involves: determining a first context based on a combination of two or more context signals, using a context-to-action mapping to determine a first action that corresponds to the first context, initiating the first action, after initiating the first action, receiving a data signal corresponding to a user-action, analyzing the data signal to determine a feedback relationship between the user-action and the first action, and based at least in part on the feedback relationship, updating the context-to-action mapping.
    • 公开了示例性方法和系统,其应用基于反馈的机器学习,以便更智能地使用上下文信息来自动化某些动作。 一种示例性方法包括:基于两个或更多个上下文信号的组合来确定第一上下文,使用上下文动作映射来确定对应于第一上下文的第一动作,在启动第一动作之后启动第一动作 ,接收对应于用户动作的数据信号,分析数据信号以确定用户动作与第一动作之间的反馈关系,并且至少部分地基于所述反馈关系,更新所述上下文动作映射 。