Real time context learning by software agents
    31.
    发明授权
    Real time context learning by software agents 有权
    软件代理实时上下文学习

    公开(公告)号:US07296007B1

    公开(公告)日:2007-11-13

    申请号:US10885495

    申请日:2004-07-06

    IPC分类号: G06F17/00 G06N5/00

    摘要: Providing dynamic learning for software agents in a simulation. Software agents with learners are capable of learning from examples. When a non-player character queries the learner, it can provide a next action similar to the player character. The game designer provides program code, from which compile-time steps determine a set of raw features. The code might identify a function (like computing distances). At compile-time steps, determining these raw features in response to a scripting language, so the designer can specify which code should be referenced. A set of derived features, responsive to the raw features, might be relatively simple, more complex, or determined in response to a learner. The set of such raw and derived features form a context for a learner. Learners might be responsive to (more basic) learners, to results of state machines, to calculated derived features, or to raw features. The learner includes a machine learning technique.

    摘要翻译: 在模拟中为软件代理提供动态学习。 具有学习者的软件代理能够从示例中学习。 当非玩家角色查询学习者时,它可以提供类似于玩家角色的下一个动作。 游戏设计师提供程序代码,编译时步骤确定一组原始特征。 代码可能会识别一个函数(如计算距离)。 在编译时步骤中,根据脚本语言确定这些原始特征,因此设计人员可以指定哪些代码应该被引用。 响应于原始特征的一组派生特征可能相对简单,更复杂或响应于学习者而确定。 这些原始和派生特征的集合形成了学习者的上下文。 学习者可以对(更基础的)学习者,状态机的结果,计算的导出特征或者原始特征进行响应。 学习者包括机器学习技术。

    Motion pattern classification and gesture recognition
    32.
    发明授权
    Motion pattern classification and gesture recognition 有权
    运动模式分类和手势识别

    公开(公告)号:US09110510B2

    公开(公告)日:2015-08-18

    申请号:US13153374

    申请日:2011-06-03

    IPC分类号: G09G5/00 G06F3/01 G06K9/00

    摘要: Methods, program products, and systems for gesture classification and recognition are disclosed. In general, in one aspect, a system can determine multiple motion patterns for a same user action (e.g., picking up a mobile device from a table) from empirical training data. The system can collect the training data from one or more mobile devices. The training data can include multiple series of motion sensor readings for a specified gesture. Each series of motion sensor readings can correspond to a particular way a user performs the gesture. Using clustering techniques, the system can extract one or more motion patterns from the training data. The system can send the motion patterns to mobile devices as prototypes for gesture recognition.

    摘要翻译: 公开了用于手势分类和识别的方法,程序产品和系统。 通常,在一个方面,系统可以根据经验训练数据确定用于相同用户动作(例如,从表中拾取移动设备)的多个运动模式。 该系统可以从一个或多个移动设备收集训练数据。 训练数据可以包括用于指定手势的多个运动传感器读数。 每个系列的运动传感器读数可以对应于用户执行手势的特定方式。 使用聚类技术,系统可以从训练数据中提取一个或多个运动模式。 系统可以将运动模式发送到移动设备作为用于手势识别的原型。

    Activity detection
    33.
    发明授权
    Activity detection 有权
    活动检测

    公开(公告)号:US08892391B2

    公开(公告)日:2014-11-18

    申请号:US13153361

    申请日:2011-06-03

    IPC分类号: G01P15/00 G01D1/16

    CPC分类号: G01D1/16

    摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a presumed activity associated with a mobile device. A plurality of sensor values detected by one or more sensors onboard the mobile device is received over a period of time. A plurality of derived values is calculated from the plurality of sensor values. The derived values are selectively combined to generate one or more abstract values. A presumed activity is identified from a plurality of possible activities based on a level of similarity between the one or more abstract values and expected values of each of the plurality of possible activities that correspond to the one or more abstract values.

    摘要翻译: 方法,系统和装置,包括在计算机存储介质上编码的计算机程序,用于确定与移动装置相关联的推测活动。 在一段时间内接收由移动设备上的一个或多个传感器检测到的多个传感器值。 从多个传感器值计算多个导出值。 导出值被选择性地组合以生成一个或多个抽象值。 基于与一个或多个抽象值对应的多个可能活动中的每一个的一个或多个抽象值和预期值之间的相似度级别,从多个可能的活动中识别推定的活动。

    Magnetometer Calibration
    34.
    发明申请
    Magnetometer Calibration 有权
    磁力计校准

    公开(公告)号:US20120086438A1

    公开(公告)日:2012-04-12

    申请号:US12899392

    申请日:2010-10-06

    申请人: Xiaoyuan Tu

    发明人: Xiaoyuan Tu

    IPC分类号: G01R35/00 G06F19/00

    摘要: A real-time calibration system and method for a mobile device having an onboard magnetometer uses an estimator to estimate magnetometer calibration parameters and a magnetic field external to the mobile device (e.g., the earth magnetic field). The calibration parameters can be used to calibrate uncalibrated magnetometer readings output from the onboard magnetometer. The external magnetic field can be modeled as a weighted combination of a past estimate of the external magnetic field and the asymptotic mean of that magnetic field, perturbed by a random noise (e.g., Gaussian random noise). The weight can be adjusted based on a measure of the statistical uncertainty of the estimated calibration parameters and the estimated external magnetic field. The asymptotic mean of the external magnetic field can be modeled as a time average of the estimated external magnetic field.

    摘要翻译: 具有车载磁力计的移动设备的实时校准系统和方法使用估计器来估计磁力计校准参数和移动设备外部的磁场(例如,地球磁场)。 校准参数可用于校准从车载磁力计输出的未校准磁力计读数。 外部磁场可以被建模为外部磁场的过去估计和由随机噪声(例如,高斯随机噪声)扰动的该磁场的渐近均值的加权组合。 可以基于估计的校准参数和估计的外部磁场的统计不确定度的量度来调整重量。 外部磁场的渐近均值可以建模为估计的外部磁场的时间平均值。

    Using clustering techniques to improve magnetometer bias estimation
    39.
    发明授权
    Using clustering techniques to improve magnetometer bias estimation 有权
    使用聚类技术提高磁力计偏差估计

    公开(公告)号:US09423252B2

    公开(公告)日:2016-08-23

    申请号:US13610678

    申请日:2012-09-11

    摘要: In some implementations, a computer-implemented method includes receiving a reading from a magnetometer of a mobile device. A cluster from a plurality of clusters of bias offsets generated from previously-calibrated readings is selected. The selected cluster has a representative bias offset, a mean of magnitudes in the selected cluster, and a magnitude threshold. An external magnetic field is estimated based on the reading and the representative bias offset for the selected cluster. Whether a magnitude of the estimated external field is within a magnitude range defined by the mean magnitude and the mean magnitude plus the magnitude threshold is determined.

    摘要翻译: 在一些实现中,计算机实现的方法包括从移动设备的磁力计接收读取。 选择从先前校准的读数产生的多个偏移偏移簇的簇。 所选择的簇具有代表性的偏置偏移,所选择的簇中的大小的平均值和幅度阈值。 基于所选择的集群的读取和代表偏移偏移来估计外部磁场。 确定估计的外部场的大小是否在由平均幅度和平均幅度加上幅度阈值所限定的幅度范围内。

    Multi-Stage Device Orientation Detection
    40.
    发明申请
    Multi-Stage Device Orientation Detection 有权
    多级设备定向检测

    公开(公告)号:US20130328935A1

    公开(公告)日:2013-12-12

    申请号:US13492691

    申请日:2012-06-08

    申请人: Xiaoyuan Tu

    发明人: Xiaoyuan Tu

    IPC分类号: G09G5/34

    摘要: In general, in one aspect, a method includes receiving data from one or more motion sensors of a mobile device and calculating, after the period of time, a statistical measurement of the motion sensor data. The method also includes comparing the calculated statistical measurement to one or more threshold values, and, based on the comparing, determining a dynamic state of the mobile device. The method also includes, based on the determined dynamic state, determining an orientation of the mobile device.

    摘要翻译: 通常,在一个方面,一种方法包括从移动设备的一个或多个运动传感器接收数据,并且在该时间段之后计算运动传感器数据的统计测量。 该方法还包括将计算的统计测量值与一个或多个阈值进行比较,并且基于比较,确定移动设备的动态状态。 该方法还包括基于所确定的动态状态来确定移动设备的定向。