USING A GENERIC CLASSIFIER TO TRAIN A PERSONALIZED CLASSIFIER FOR WEARABLE DEVICES
    1.
    发明申请
    USING A GENERIC CLASSIFIER TO TRAIN A PERSONALIZED CLASSIFIER FOR WEARABLE DEVICES 有权
    使用一般分类器来培训个性化分类器,用于可穿戴设备

    公开(公告)号:US20150379421A1

    公开(公告)日:2015-12-31

    申请号:US14318555

    申请日:2014-06-27

    IPC分类号: G06N99/00 G06N5/04

    摘要: Systems and methods may provide for using one or more generic classifiers to generate self-training data based on a first plurality of events associated with a device, and training a personal classifier based on the self-training data. Additionally, the one or more generic classifiers and the personal classifier to may be used to generate validation data based on a second plurality of events associated with the device. In one example, the personal classifier is substituted for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.

    摘要翻译: 系统和方法可以提供使用一个或多个通用分类器基于与设备相关联的第一多个事件来生成自训练数据,以及基于自训练数据训练个人分类器。 另外,可以使用一个或多个通用分类器和个人分类器来基于与设备相关联的第二多个事件来生成验证数据。 在一个示例中,如果验证数据指示个人分类器相对于一个或多个通用分类器满足置信条件,则个人分类器被替换为一个或多个通用分类器。

    AUDIBLE LIST TRAVERSAL
    3.
    发明申请
    AUDIBLE LIST TRAVERSAL 有权
    可视列表TRAVERSAL

    公开(公告)号:US20100169097A1

    公开(公告)日:2010-07-01

    申请号:US12347998

    申请日:2008-12-31

    IPC分类号: G10L21/00

    摘要: Many embodiments may comprise logic such as hardware and/or code to implement user interface for traversal of long sorted lists, via audible mapping of the lists, using sensor based gesture recognition, audio and tactile feedback and button selection while on the go. In several embodiments, such user interface modalities are physically small in size, enabling a user to be truly mobile by reducing the cognitive load required to operate the device. For some embodiments, the user interface may be divided across multiple worn devices, such as a mobile device, watch, earpiece, and ring. Rotation of the watch may be translated into navigation instructions, allowing the user to traverse the list while the user receives audio feedback via the earpiece to describe items in the list as well as audio feedback regarding the navigation state. Many embodiments offer the user a simple user interface to traverse the list without visual feedback.

    摘要翻译: 许多实施例可以包括诸如硬件和/或代码的逻辑,以通过列表的可听映射,使用基于传感器的手势识别,音频和触觉反馈以及按钮选择来实现用于遍历长排序列表的用户界面。 在几个实施例中,这样的用户接口模态在物理上尺寸较小,使用户能够通过减少操作设备所需的认知负载来真正地移动。 对于一些实施例,用户界面可以在多个磨损的设备(例如移动设备,手表,耳机和环)上被划分。 手表的旋转可以转换为导航指令,允许用户遍历列表,同时用户经由耳机接收音频反馈以描述列表中的项目以及关于导航状态的音频反馈。 许多实施例为用户提供了一个简单的用户界面来遍历列表而无需视觉反馈。

    CONTEXT-RICH COMMUNICATION BETWEEN A DEVICE AND A VEHICLE
    4.
    发明申请
    CONTEXT-RICH COMMUNICATION BETWEEN A DEVICE AND A VEHICLE 审中-公开
    设备与车辆之间的上下文通信

    公开(公告)号:US20140229568A1

    公开(公告)日:2014-08-14

    申请号:US13763261

    申请日:2013-02-08

    IPC分类号: H04L29/08

    CPC分类号: H04W4/44

    摘要: Aspects of the disclosure render safer a communication between a caller within a vehicle and a callee located remotely. In one aspect, context information associated with such communication can be shared among the caller and the callee. Accordingly, in another aspect, a context-rich, immersive communication between the in-vehicle communicator (or local communicator) and the remote communicator can be effected. In yet another aspect, proactive creation of safer vehicular operation can be provided by engaging the vehicle in communication with a remote device in response to unsafe vehicular contexts.

    摘要翻译: 本公开的方面使得车辆内的呼叫者与远程定位的被呼叫者之间的通信变得更安全。 在一个方面,与这种通信相关联的上下文信息可以在呼叫者和被叫者之间共享。 因此,在另一方面,可以实现车载通信器(或本地通信器)和远程通信器之间的上下文丰富的沉浸式通信。 在另一方面,可以通过使车辆响应于不安全的车辆上下文而与远程设备通信来提供主动创建更安全的车辆操作。

    SOCIALLY AND CONTEXTUALLY APPROPRIATE RECOMMENDATION SYSTEMS
    5.
    发明申请
    SOCIALLY AND CONTEXTUALLY APPROPRIATE RECOMMENDATION SYSTEMS 有权
    社会和相对适当的推荐系统

    公开(公告)号:US20150379406A1

    公开(公告)日:2015-12-31

    申请号:US14316878

    申请日:2014-06-27

    IPC分类号: G06N5/04 G06N99/00

    摘要: Systems and methods may provide for conducting an interest analysis of data associated with a user, wherein the interest analysis distinguishes between abstract interests and social interests. Additionally, one or more recommendations may be generated for the user based on the interest analysis and a current context of the user, wherein the one or more recommendations may be presented to the user. In one example, the abstract interests identify types of topics and types of objects, and the social interests identify types of social groups.

    摘要翻译: 系统和方法可以提供对与用户相关联的数据的兴趣分析,其中兴趣分析区分抽象兴趣和社会兴趣。 此外,可以基于兴趣分析和用户的当前上下文为用户生成一个或多个建议,其中可以向用户呈现一个或多个建议。 在一个例子中,抽象兴趣识别对象的主题和类型的类型,社会兴趣识别社会群体的类型。

    FACILITATING INTELLIGENT GATHERING OF DATA AND DYNAMIC SETTING OF EVENT EXPECTATIONS FOR EVENT INVITEES ON COMPUTING DEVICES
    7.
    发明申请
    FACILITATING INTELLIGENT GATHERING OF DATA AND DYNAMIC SETTING OF EVENT EXPECTATIONS FOR EVENT INVITEES ON COMPUTING DEVICES 审中-公开
    促进智能数据收集和动态设置活动邀请对计算机设备的期望

    公开(公告)号:US20160086104A1

    公开(公告)日:2016-03-24

    申请号:US14491718

    申请日:2014-09-19

    IPC分类号: G06Q10/02 G06Q50/00 G06Q10/10

    摘要: A mechanism is described for facilitating data gathering and expectations setting according to one embodiment. A method of embodiments, as described herein, includes detecting an invitation relating to an event, where the invitation may include an invitation to an invitee to attend the event. The method may further include obtaining data relating to the event from a plurality of sources, where the data further relates to other invitees of the event. The method may further include interpreting the obtained data based on one or more of filtering factors and relevancy factors, generating recommendations based on the interpreted data, where the recommendations may include expectations relating to the event. The method may further include facilitating communication of the recommendations to set the expectations for the invitee in anticipation of the event.

    摘要翻译: 描述了根据一个实施例的用于促进数据收集和期望设置的机制。 如本文所述的实施例的方法包括检测与事件相关的邀请,其中邀请可以包括邀请被邀请人参加该事件的邀请。 该方法还可以包括从多个源获得与事件有关的数据,其中数据还与事件的其他受邀者相关。 该方法还可以包括基于过滤因子和相关性因素中的一个或多个来解释所获得的数据,基于解释数据生成推荐,其中建议可以包括与事件有关的期望。 该方法可以进一步包括促进建议的通信以针对受访者预期事件设定期望。