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
    • 49. 发明授权
    • Robot simulation device for generating motion path of robot
    • 机器人模拟装置,用于产生机器人的运动路径
    • US09573273B2
    • 2017-02-21
    • US14629728
    • 2015-02-24
    • FANUC CORPORATION
    • Toshiya Takeda
    • B25J9/16G06N99/00G06N7/00
    • B25J9/1605G06N7/00G06N99/005Y10S901/03
    • A robot simulation device for automatically generating a practical interference avoiding motion path, regardless of the level of skill of an operator. The device includes: a motion path obtaining part which obtains a first motion path by simulating a robot motion program; a teaching point specifying part which detects whether a robot interferes with a peripheral object on the first path, and specifies first and second teaching points immediately before and after the interference occurs, respectively; a motion path generating part which automatically inserts a third teaching point between the first and second points and generates second motion paths for avoiding the interference, based on a search direction and distance determined by a random number; an evaluating part which evaluates each second path based on a predetermined parameter; and a motion path selecting part which selects an optimum motion path from the second paths based on an evaluation result.
    • 一种用于自动生成实际的避免干扰运动路径的机器人模拟装置,而不管操作者的技能水平如何。 该装置包括:运动路径获取部,其通过模拟机器人运动程序获得第一运动路径; 教导点指定部,其检测机器人是否干扰第一路径上的周边物体,并且分别指定在发生干扰之前和之后的第一和第二教学点; 基于由随机数确定的搜索方向和距离,自动地在第一和第二点之间插入第三教学点并产生用于避免干扰的第二运动路径的运动路径产生部分; 评估部,其基于预定参数来评估每个第二路径; 以及基于评价结果从第二路径选择最优运动路径的运动路径选择部。
    • 50. 发明授权
    • Hierarchical statistical model for behavior prediction and classification
    • 行为预测和分类的层次统计模型
    • US09558452B2
    • 2017-01-31
    • US14076106
    • 2013-11-08
    • Microsoft Corporation
    • John GuiverJohn WinnJames Edelen
    • G06F17/50G06N7/00G06Q10/00G06Q10/10
    • G06N7/00G06F17/5009G06N7/005G06Q10/00G06Q10/107
    • Technologies are generally provided far a hierarchical, feature teed statistical model that cm be used for personalized classification or predictions within a community of users. Personalization refers to learning about the habits and characteristics of individual users and adapting user experiences based on that learning. The model may be used in a communication application to predict user actions on incoming email messages and to help users triage email by making personalized suggestions based on the model predictions. A community of users associated together with the communication application may be incorporated together into a single model to enable for continuous fine-grain interaction between intelligence learned from the community of users as a whole and that learned from individual users. The single model may allow a seamless progression between predictions for a completely new user based on community observations and highly personalized predictions for a long-term user based on individual observations.
    • 技术通常提供远远的层次结构,特征比特统计模型,cm可用于个体化分类或用户社区内的预测。 个性化是指学习个人用户的习惯和特征,并根据学习情况调整用户体验。 该模型可用于通信应用程序中,以预测用户对传入电子邮件的操作,并通过基于模型预测的个性化建议帮助用户分类电子邮件。 与通信应用程序相关联的用户社区可以并入到单个模型中,以实现从整体上的用户群体学习的智能和从个体用户学到的智能之间的连续细粒度交互。 单个模型可以允许基于社区观察的全新用户的预测和基于个体观察的对长期用户的高度个性化预测的无缝进展。