公开(公告)号：US20110313953A1

公开(公告)日：2011-12-22

申请号：US12818877

申请日：2010-06-18

申请人： Nicholas D. Lane ,  David Chiyuan Chu ,  Jing Zhao ,  Feng Zhao

发明人： Nicholas D. Lane ,  David Chiyuan Chu ,  Jing Zhao ,  Feng Zhao

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  G06K9/00973

摘要： An architecture and techniques to enable a mobile device to efficiently classify raw sensor data into useful high level inferred data is discussed. Classification efficiency is achieved by tuning the mobile device's raw sensor data classification pipeline to attain a balance of accuracy, latency and energy suitable for mobile devices. The tuning of the classification pipeline is accomplished via a multi-pipeline tuning approach that uses Statistical Machine Learning Tools (SMLTs) and a classification cost modeler.

摘要翻译： 讨论了使移动设备有效地将原始传感器数据分类为有用的高级推断数据的架构和技术。 通过调整移动设备的原始传感器数据分类流水线达到适合移动设备的精度，延迟和能量的平衡来实现分类效率。 分类流水线的调整是通过使用统计机器学习工具（SMLT）和分类成本建模器的多管线调整方法实现的。

公开(公告)号：US09020871B2

公开(公告)日：2015-04-28

申请号：US12818877

申请日：2010-06-18

申请人： Nicholas D. Lane ,  David Chiyuan Chu ,  Jing Zhao ,  Feng Zhao

发明人： Nicholas D. Lane ,  David Chiyuan Chu ,  Jing Zhao ,  Feng Zhao

IPC分类号： G06N99/00 ,  G06K9/00

CPC分类号： G06N99/005 ,  G06K9/00973

摘要： An architecture and techniques to enable a mobile device to efficiently classify raw sensor data into useful high level inferred data is discussed. Classification efficiency is achieved by tuning the mobile device's raw sensor data classification pipeline to attain a balance of accuracy, latency and energy suitable for mobile devices. The tuning of the classification pipeline is accomplished via a multi-pipeline tuning approach that uses Statistical Machine Learning Tools (SMLTs) and a classification cost modeler.

摘要翻译： 讨论了使移动设备有效地将原始传感器数据分类为有用的高级推断数据的架构和技术。 通过调整移动设备的原始传感器数据分类流水线达到适合移动设备的精度，延迟和能量的平衡来实现分类效率。 分类流水线的调整是通过使用统计机器学习工具（SMLT）和分类成本建模器的多管线调整方法实现的。

公开(公告)号：US20110313954A1

公开(公告)日：2011-12-22

申请号：US12819080

申请日：2010-06-18

申请人： Feng Zhao ,  Nicholas D. Lane ,  Dimitrios Lymperopoulos ,  Jing Zhao

发明人： Feng Zhao ,  Nicholas D. Lane ,  Dimitrios Lymperopoulos ,  Jing Zhao

IPC分类号： G06F17/30 ,  G06F15/18

CPC分类号： G06F16/35 ,  G06F16/335 ,  G06F16/9535 ,  G06F16/9537

摘要： The present disclosure describes a community model based point of interest local search platform. Specifically, logs of users that store selections while accessing a point of interest application are loaded into a database. The logs are of users that have similar demographic or other community attributes. The logs are then mined for contextual parameters, including, but not limited to time of day, day of week, distance, activity, environment, popularity, and personal preferences. The point of interest selections are then mapped to a multi-dimensional map where each dimension corresponds to a contextual parameter. Clusters are evaluated by a classifier and classes of users of the community are identified. When a user then queries the community model based point of interest local search platform, contextual parameters are submitted with the query, relevant classes identified, and the corresponding point of interest information is displayed to the user.

摘要翻译： 本公开描述了基于社区模型的兴趣点本地搜索平台。 具体来说，在访问兴趣点应用程序时存储选择的用户的日志被加载到数据库中。 日志是具有类似人口统计或其他社区属性的用户。 然后为日志参数挖掘日志，包括但不限于一天中的时间，星期几，距离，活动，环境，人气和个人喜好。 然后将兴趣点选择映射到多维映射，其中每个维度对应于上下文参数。 集群由分类器评估，并且识别社区的用户类。 当用户随后查询基于社区模型的兴趣点本地搜索平台时，上下文参数与查询一起提交，识别相关类，并将相应的兴趣点信息显示给用户。