专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明授权

US06618716B1 Computational architecture for managing the transmittal and rendering of information, alerts, and notifications 有权
标题翻译：用于管理信息，警报和通知的传输和呈现的计算架构
公开(公告)号：US06618716B1
公开(公告)日：2003-09-09
申请号：US09365287
申请日：1999-07-30
申请人： Eric Horvitz
发明人： Eric Horvitz
IPC分类号： G06N500
CPC分类号： G06F9/453 , G06F9/451 , Y10S706/902
摘要： An architecture for managing alerts, notifications, and peripheral information is disclosed. In one embodiment, a computerized system includes three modules, an attentional status module, a peripheral information notification and alerts module, and an notifications decision-making module. The attentional-status module generates a probability distribution over the user's focus of attention. In one embodiment the module also provides a probability distribution over the period of time until the user will become available to review alerts zero or minimal cost, or will review them without prompting. In one embodiment, this module utilizes a decision-theoretic analysis to identify ideal actions about the timing and rendering of notifications or alerts. The peripheral information notification and alerts module receives alerts from different sources, including the operating system, standard applications, special plug-ins designed to work with the architecture, and, in particular embodiments, from special sensory apparatus including ambient acoustical information. The notification decision-making module is to alert the user of the alerts received by the peripheral information notification and alerts module, based on the probability generated by the attentional status module.
摘要翻译：公开了用于管理警报，通知和外围设备信息的架构。在一个实施例中，计算机化系统包括三个模块，注意状态模块，外围信息通知和警报模块以及通知决策模块。注意状态模块在用户关注的焦点上产生概率分布。在一个实施例中，模块还在一段时间内提供概率分布，直到用户将可用于查看警报为零或最小成本，或者将在不提示的情况下对其进行审查。在一个实施例中，该模块利用决策理论分析来识别关于通知或警报的定时和呈现的理想动作。外围信息通知和警报模块从不同来源接收警报，包括操作系统，标准应用程序，设计为与架构一起工作的特殊插件，特别是实施例中，来自包括环境声学信息的特殊感觉设备。通知决策模块基于由注意状态模块产生的概率来向用户提醒由外围信息通知和警报模块接收到的警报。

72. 发明授权

US06553358B1 Decision-theoretic approach to harnessing text classification for guiding automated action 有权
标题翻译：用于指导自动化操作的决策理论方法来利用文本分类
公开(公告)号：US06553358B1
公开(公告)日：2003-04-22
申请号：US09295088
申请日：1999-04-20
申请人： Eric Horvitz
发明人： Eric Horvitz
IPC分类号： G06N502
CPC分类号： G06Q10/109 , G06Q10/107 , G06Q20/10
摘要： A decision-theoretic approach for guiding automated actions. In one embodiment, a computer-implemented method first determines a text to analyze. The method then determines an action probability based on the text. Words and phrases as well as information in special fields, such as distinctions and patterns in the header of email, observations about recent user activity, and organizational information are considered in classification. Based on the inferred probability that a user has a goal under consideration, the method selects one of the following options: (1) inaction, (2) automatic action, or (3) suggested action with user approval. Upon the method selecting either the (1) automatic action option or the (2) suggested action with user approval option—the latter also in conjunction with receiving actual user approval—the method performs an action based on the text.
摘要翻译：指导自动化行动的决策理论方法。在一个实施例中，计算机实现的方法首先确定要分析的文本。然后，该方法基于文本确定动作概率。在分类中考虑词和短语以及特殊字段中的信息，例如电子邮件标题中的区别和模式，关于最近用户活动的观察以及组织信息。基于用户考虑目标的推测概率，该方法选择以下选项之一：（1）无效，（2）自动动作，或（3）用户批准建议的动作。在方法选择（1）自动动作选项或（2）建议动作与用户批准选项 - 后者也结合接收实际用户批准 - 该方法基于文本执行动作。

73. 发明授权

US6161130A Technique which utilizes a probabilistic classifier to detect "junk" e-mail by automatically updating a training and re-training the classifier based on the updated training set 失效
标题翻译：利用概率分类器通过自动更新训练集并基于更新的训练集来重新训练分类器来检测“垃圾”电子邮件的技术
公开(公告)号：US6161130A
公开(公告)日：2000-12-12
申请号：US102837
申请日：1998-06-23
申请人： Eric Horvitz , David E. Heckerman , Susan T. Dumais , Mehran Sahami , John C. Platt
发明人： Eric Horvitz , David E. Heckerman , Susan T. Dumais , Mehran Sahami , John C. Platt
IPC分类号： G06F17/30 , G06K9/62 , G06Q10/10 , H04L12/58 , G06F15/16 , G06F15/173
CPC分类号： G06F17/30707 , G06K9/6269 , G06Q10/107 , H04L51/12 , Y10S707/99935 , Y10S707/99936
摘要： A technique, specifically a method and apparatus that implements the method, which through a probabilistic classifier (370) and, for a given recipient, detects electronic mail (e-mail) messages, in an incoming message stream, which that recipient is likely to consider "junk". Specifically, the invention discriminates message content for that recipient, through a probabilistic classifier (e.g., a support vector machine) trained on prior content classifications. Through a resulting quantitative probability measure, i.e., an output confidence level, produced by the classifier for each message and subsequently compared against a predefined threshold, that message is classified as either, e.g., spam or legitimate mail, and, e.g., then stored in a corresponding folder (223, 227) for subsequent retrieval by and display to the recipient. Based on the probability measure, the message can alternatively be classified into one of a number of different folders, depicted in a pre-defined visually distinctive manner or simply discarded in its entirety.
摘要翻译：一种实现该方法的技术，特别是一种方法和装置，其通过概率分类器（370）以及对于给定的接收者在接收到的消息流中检测电子邮件（电子邮件）消息，该接收者可能考虑“垃圾”。具体地，本发明通过在先前内容分类上训练的概率分类器（例如，支持向量机）来区分该接收者的消息内容。通过由每个消息的分类器产生的随后与预定阈值进行比较的结果定量概率测度，即输出置信水平，该消息被分类为例如垃圾邮件或合法邮件，并且例如存储在相应的文件夹（223,227），用于随后由接收者检索和显示。基于概率测量，该消息可替代地被分类为多个不同文件夹中的一个，以预先定义的视觉区别方式描绘，或者完全被丢弃。

74. 发明授权

US5784616A Apparatus and methods for optimally using available computer resources for task execution during idle-time for future task instances exhibiting incremental value with computation 失效
标题翻译：用于在空闲时间期间最佳地利用可用的计算机资源进行任务执行的装置和方法，用于在未来的任务实例中通过计算显示增量值
公开(公告)号：US5784616A
公开(公告)日：1998-07-21
申请号：US850621
申请日：1997-05-02
申请人： Eric Horvitz
发明人： Eric Horvitz
IPC分类号： G06F9/50 , G06F9/46
CPC分类号： G06F9/485 , G06F9/4881
摘要： Apparatus and accompanying methods for optimally using available computer resources, illustratively processing time, and which can be advantageously used for selecting task(s) instances to be precomputed during idle time as well as during other periods of processing activity. Specifically, at an onset of each idle-time interval, processing time is allocated to precompute during the remainder of that interval a future task instance, from among a group of such instances then available for precomputation, that will provide the highest fixed or incremental utility. For those task instances which exhibit constant or varying value with time, task selection is based on maximum probability of future occurrence, or net expected value (NEV), respectively, of each such instance. NEV is evaluated as a product of the task instance probability multiplied by a rate of change in the value (EVC flux) to be provided by that task with continued computation time, respectively. This product is assessed, for task instances that exhibit linearly changing value with time, at the onset of each idle-time interval, or, for task instances that exhibit non-linearly changing value, at the onset of each time slice occurring during such an interval.
摘要翻译：用于最佳地利用可用计算机资源的装置和伴随方法，说明性地处理时间，并且其可以有利地用于选择在空闲时间期间以及在其他处理活动期间预先计算的任务实例。具体来说，在每个空闲时间间隔开始时，处理时间被分配给在该间隔的剩余时间内的预计算，一个未来的任务实例（从一组这样的实例中可用于预先计算）将提供最高的固定或增量效用。对于那些随着时间呈现恒定值或变化值的任务实例，任务选择基于每个这样的实例的未来发生的最大概率或净期望值（NEV）。 NEV被评估为任务实例概率乘以由该任务提供的持续计算时间的值（EVC通量）的变化率的乘积。对于在每个空闲时间间隔开始时呈现出随时间呈线性变化的值的任务实例，或者对于在这样的时间间隔期间发生的每个时间片的开始，对于表现出非线性变化的值的任务实例，对该产品进行评估。间隔。

75. 发明授权

US08966613B2 Multi-frame depth image information identification 有权
标题翻译：多帧深度图像信息识别
公开(公告)号：US08966613B2
公开(公告)日：2015-02-24
申请号：US13250542
申请日：2011-09-30
申请人： Eric Horvitz , Desney S. Tan , James Chia-Ming Liu
发明人： Eric Horvitz , Desney S. Tan , James Chia-Ming Liu
IPC分类号： G06F21/00 , H04L9/32 , G06F21/32 , H04L29/06
CPC分类号： H04L9/3231 , G06F21/32 , G06K9/00335 , H04L63/0861
摘要： Embodiments of the present invention relate to systems, methods, and computer storage media for identifying, authenticating, and authorizing a user to a device. A dynamic image, such as a video captured by a depth camera, is received. The dynamic image provides data from which geometric information of a portion of a user may be identified as well as motion information of a portion of the user may be identified. Consequently, a geometric attribute is identified from the geometric information. A motion attribute may also be identified from the motion information. The geometric attribute is compared to one or more geometric attributes associated with authorized users. Additionally, the motion attribute may be compared to one or more motion attributes associated with the authorized users. A determination may be made that the user is an authorized user. As such the user is authorized to utilize functions of the device.
摘要翻译：本发明的实施例涉及用于识别，认证和授权用户到设备的系统，方法和计算机存储介质。接收动态图像，例如由深度相机拍摄的视频。动态图像提供可以识别用户的一部分的几何信息的数据，并且可以识别用户的一部分的运动信息。因此，从几何信息中识别几何属性。也可以根据运动信息识别运动属性。将几何属性与与授权用户相关联的一个或多个几何属性进行比较。另外，运动属性可以与与授权用户相关联的一个或多个运动属性进行比较。可以确定用户是授权用户。因此，用户被授权利用该设备的功能。

76. 发明授权

US08805010B2 Gesture identification using an ad-hoc multidevice network 有权
标题翻译：使用自组织多设备网络的手势识别
公开(公告)号：US08805010B2
公开(公告)日：2014-08-12
申请号：US13352487
申请日：2012-01-18
申请人： Eric Horvitz , Kenneth P. Hinckley , Hrvoje Benko
发明人： Eric Horvitz , Kenneth P. Hinckley , Hrvoje Benko
IPC分类号： G06K9/00
CPC分类号： G06K9/00771 , G06K9/00335
摘要： Methods, systems, and computer-readable media for establishing an ad hoc network of devices that can be used to interpret gestures. Embodiments of the invention use a network of sensors with an ad hoc spatial configuration to observe physical objects in a performance area. The performance area may be a room or other area within range of the sensors. Initially, devices within the performance area, or with a view of the performance area, are indentified. Once identified, the sensors go through a discovery phase to locate devices within an area. Once the discovery phase is complete and the devices within the ad hoc network are located, the combined signals received from the devices may be used to interpret gestures made within the performance area.
摘要翻译：用于建立可用于解释手势的设备的自组织网络的方法，系统和计算机可读介质。本发明的实施例使用具有自组织空间配置的传感器网络来观察性能区域中的物理对象。性能区域可以是传感器范围内的房间或其他区域。最初，表现区域内的设备或者表现区域的设备都被识别。一旦识别，传感器就会经过一个发现阶段来定位一个区域内的设备。一旦发现阶段完成并且自组织网络中的设备被定位，则从设备接收的组合信号可以用于解释在性能区域内做出的手势。

77. 发明授权

US08732222B2 Integrating specialized knowledge sources into a general search service 有权
标题翻译：将专业知识来源整合到一般搜索服务中
公开(公告)号：US08732222B2
公开(公告)日：2014-05-20
申请号：US12827370
申请日：2010-06-30
申请人： Eric Horvitz , Johnson Apacible
发明人： Eric Horvitz , Johnson Apacible
IPC分类号： G06F7/00 , G06F17/00 , G06F17/30
CPC分类号： G06F17/30702 , G06N5/043 , G06N99/005
摘要： Embodiments are described for a system for integrating expert sources of knowledge into a general search service. The method can include a general search engine interface to receive a search query with at least one search term from a user. An expert knowledge engine can enable retrieval of expert information and analyzes. A predictive model module can be used to determine a probability that an expert knowledge engine may provide a valuable response to the query. The search query can be routed to the expert knowledge engine based on a cost-benefit analysis. A query reformulation module can reformulate a query for use by the expert knowledge engine. A display module can be employed to combine the expert search results with other search results.
摘要翻译：描述了用于将专家知识来源整合成一般搜索服务的系统的实施例。该方法可以包括通用搜索引擎接口，用于从用户接收具有至少一个搜索词的搜索查询。专家知识引擎可以检索专家信息和分析。可以使用预测模型模块来确定专家知识引擎可以向查询提供有价值的响应的概率。搜索查询可以基于成本效益分析路由到专家知识引擎。查询重组模块可重新构建专家知识引擎使用的查询。可以使用显示模块来组合专家搜索结果与其他搜索结果。

78. 发明申请

US20130006738A1 SHARED ELECTRONIC INCENTIVES AND COUPONS LEVERAGING SOCIAL CONNECTIONS AND SHEPHERDING 审中-公开
标题翻译：共享的电子激励机制和优势触发社会关系和创造力
公开(公告)号：US20130006738A1
公开(公告)日：2013-01-03
申请号：US13174255
申请日：2011-06-30
申请人： Eric Horvitz , Roger Barga , Lili Cheng , Doug Burger , Vinay Gupta , Xuedong Huang , Zachary Apter
发明人： Eric Horvitz , Roger Barga , Lili Cheng , Doug Burger , Vinay Gupta , Xuedong Huang , Zachary Apter
IPC分类号： G06Q30/00
CPC分类号： G06Q50/01 , G06Q30/0207
摘要： Systems and methods for distributing shared electronic coupons are provided. According to one aspect, the electronic coupon may include a coupon benefit display region displaying a textual and/or graphical representation of a coupon benefit. The electronic coupon may further include a candidate display region displaying a list of one or more friends of the user who are determined to be redeemer candidates from among friends in a social network profile or address book of the user. Each redeemer candidate friend in the list has an associated selector, and selection by the user of a selector corresponding to a friend causes the client device to send a message to a coupon server to instruct the coupon server to send the electronic coupon to a client device of the selected friend. Predictive models generated through machine learning may aid in selecting the user to which coupons are distributed and the redeemer candidates.
摘要翻译：提供了分发共享电子优惠券的系统和方法。根据一个方面，电子优惠券可以包括显示优惠券利益的文本和/或图形表示的优惠券利益显示区域。电子优惠券还可以包括候选显示区域，其显示在用户的社交网络配置文件或地址簿中从朋友中确定为救赎者候选者的用户的一个或多个朋友的列表。列表中的每个兑换者候选朋友具有关联的选择器，并且用户对与朋友相对应的选择器的选择导致客户端设备向优惠券服务器发送消息以指示优惠券服务器将电子优惠券发送到客户端设备的所选朋友。通过机器学习产生的预测模型可能有助于选择分发优惠券的用户和兑换者候选人。

79. 发明申请

US20120011511A1 METHODS FOR SUPPORTING USERS WITH TASK CONTINUITY AND COMPLETION ACROSS DEVICES AND TIME 有权
标题翻译：通过设备和时间支持任务持续使用的方法和完成
公开(公告)号：US20120011511A1
公开(公告)日：2012-01-12
申请号：US12832083
申请日：2010-07-08
申请人： Eric Horvitz , Shamsi Tamara Iqbal , Amy Kathleen Karlson
发明人： Eric Horvitz , Shamsi Tamara Iqbal , Amy Kathleen Karlson
IPC分类号： G06F9/46
CPC分类号： G06F9/4806 , G06F9/461 , G06F9/485
摘要： Concepts and technologies are described herein for providing task continuity and supporting task completion across devices and time. A task management application is configured to monitor one or more interactions between a user and a device. The interactions can include the use of the device, the use of one or more applications, and/or other tasks, subtasks, or other operations. Predictive models constructed from data or logical models can be used to predict the attention resources available or allocated to a task or subtask as well as the attention and affordances available within a context for addressing the task and these inferences can be used to mark or route the task for later reminding and display. In some embodiments, the task management application is configured to remind or execute a follow-up action when a session is resumed. Embodiments include providing users with easy to use gestures and mechanisms for providing input about desired follow up on the same or other devices.
摘要翻译：本文描述了概念和技术，用于提供任务连续性并支持跨设备和时间的任务完成。任务管理应用程序被配置为监视用户和设备之间的一个或多个交互。交互可以包括使用设备，使用一个或多个应用程序，和/或其他任务，子任务或其他操作。从数据或逻辑模型构建的预测模型可用于预测可用或分配给任务或子任务的注意力资源以及上下文中可用的注意和可用性以解决任务，并且这些推论可用于标记或路由任务后来提醒和显示。在一些实施例中，任务管理应用被配置为当会话被恢复时提醒或执行后续动作。实施例包括向用户提供易于使用的手势和机制，用于在相同或其它设备上提供关于期望跟进的输入。

80. 发明申请

US20120005148A1 INTEGRATING SPECIALIZED KNOWLEDGE SOURCES INTO A GENERAL SEARCH SERVICE 有权
标题翻译：将专业知识来源整合到一般搜索服务中
公开(公告)号：US20120005148A1
公开(公告)日：2012-01-05
申请号：US12827370
申请日：2010-06-30
申请人： Eric Horvitz , Johnson Apacible
发明人： Eric Horvitz , Johnson Apacible
IPC分类号： G06N5/02
CPC分类号： G06F17/30702 , G06N5/043 , G06N99/005
摘要： Embodiments are described for a system for integrating expert sources of knowledge into a general search service. The method can include a general search engine interface to receive a search query with at least one search term from a user. An expert knowledge engine can enable retrieval of expert information and analyses. A predictive model module can be used to determine a probability that an expert knowledge engine may provide a valuable response to the query. The search query can be routed to the expert knowledge engine based on a cost-benefit analysis. A query reformulation module can reformulate a query for use by the expert knowledge engine. A display module can be employed to combine the expert search results with other search results.
摘要翻译：描述了用于将专家知识来源整合成一般搜索服务的系统的实施例。该方法可以包括通用搜索引擎接口，用于从用户接收具有至少一个搜索词的搜索查询。专家知识引擎可以检索专家信息和分析。可以使用预测模型模块来确定专家知识引擎可以向查询提供有价值的响应的概率。搜索查询可以基于成本效益分析路由到专家知识引擎。查询重组模块可重新构建专家知识引擎使用的查询。可以使用显示模块来组合专家搜索结果与其他搜索结果。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式