专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20060206337A1 Online learning for dialog systems 有权
标题翻译：在线学习对话系统
公开(公告)号：US20060206337A1
公开(公告)日：2006-09-14
申请号：US11170999
申请日：2005-06-29
申请人： Timothy Paek , David Chickering , Eric Horvitz
发明人： Timothy Paek , David Chickering , Eric Horvitz
IPC分类号： G10L21/00
CPC分类号： G10L15/065
摘要： An online dialog system and method are provided. The dialog system receives speech input and outputs an action according to its models. After executing the action, the system receives feedback from the environment or user. The system immediately utilizes the feedback to update its models in an online fashion.
摘要翻译：提供在线对话系统和方法。对话系统接收语音输入，并根据其模型输出动作。执行该操作后，系统会收到来自环境或用户的反馈。系统立即利用反馈以在线方式更新其模型。

2. 发明申请

US20060206333A1 Speaker-dependent dialog adaptation 审中-公开
标题翻译：与扬声器相关的对话框适应
公开(公告)号：US20060206333A1
公开(公告)日：2006-09-14
申请号：US11170998
申请日：2005-06-29
申请人： Timothy Paek , David Chickering , Eric Horvitz
发明人： Timothy Paek , David Chickering , Eric Horvitz
IPC分类号： G10L13/00
CPC分类号： G10L15/22 , G10L15/07
摘要： A simulation environment for adapting a speech model (e.g., baseline model) to a user is provided. The user can interact with a base parametric speech model (e.g., statistical model with learnable parameters such as a Bayesian network) and give positive and/or negative feedback when the dialog system has performed what the user considers to be appropriate and/or inappropriate action(s). From the user feedback, the dialog system learns to take actions customized for the particular user. Speaker-dependent adaptation can be extended to the dialog level by performing maximum likelihood linear regression (MLLR) adaptation simultaneously with dialog personalization. Users are immediately able to observe how their feedback has caused the dialog system to adapt, and can quit training whenever they feel that the dialog system has adapted enough for current purposes.
摘要翻译：提供了一种用于将语音模型（例如，基准模型）适配到用户的模拟环境。用户可以与基本参数语音模型（例如，具有诸如贝叶斯网络的可学习参数的统计模型）交互，并且当对话系统执行用户认为是适当的和/或不适当的动作时给出正和负反馈（s）。从用户反馈中，对话系统学习采取针对特定用户定制的动作。通过与对话个性化同时执行最大似然线性回归（MLLR）适应，可以将扬声器依赖的适应扩展到对话级。用户可以立即观察他们的反馈如何使对话系统适应，并且只要他们觉得对话系统已经足够适应当前的目的，就可以退出训练。

3. 发明申请

US20060224535A1 Action selection for reinforcement learning using influence diagrams 失效
标题翻译：使用影响图强化学习的行动选择
公开(公告)号：US20060224535A1
公开(公告)日：2006-10-05
申请号：US11169503
申请日：2005-06-29
申请人： David Chickering , Timothy Paek , Eric Horvitz
发明人： David Chickering , Timothy Paek , Eric Horvitz
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： A system and method for online reinforcement learning is provided. In particular, a method for performing the explore-vs.-exploit tradeoff is provided. Although the method is heuristic, it can be applied in a principled manner while simultaneously learning the parameters and/or structure of the model (e.g., Bayesian network model). The system includes a model which receives an input (e.g., from a user) and provides a probability distribution associated with uncertainty regarding parameters of the model to a decision engine. The decision engine can determine whether to exploit the information known to it or to explore to obtain additional information based, at least in part, upon the explore-vs.-exploit tradeoff (e.g., Thompson strategy). A reinforcement learning component can obtain additional information (e.g., feedback from a user) and update parameter(s) and/or the structure of the model. The system can be employed in scenarios in which an influence diagram is used to make repeated decisions and maximization of long-term expected utility is desired.
摘要翻译：提供了一种在线强化学习的系统和方法。特别地，提供了用于执行探索与利用的权衡的方法。尽管该方法是启发式的，但是它可以以原则的方式应用，同时学习模型的参数和/或结构（例如，贝叶斯网络模型）。该系统包括接收输入（例如，来自用户）并且向决策引擎提供与关于模型的参数的不确定性相关联的概率分布的模型。决策引擎可以确定是否利用已知的信息，或者至少部分地基于探索与利用权衡（Thompson策略）来探索获取附加信息。强化学习组件可以获得附加信息（例如，来自用户的反馈）和更新参数和/或模型的结构。该系统可用于使用影响图进行重复决策的场景，并期望实现长期预期效用的最大化。

4. 发明授权

US06490698B1 Multi-level decision-analytic approach to failure and repair in human-computer interactions 有权
标题翻译：多层次的决策分析方法在人机交互中失败和修复
公开(公告)号：US06490698B1
公开(公告)日：2002-12-03
申请号：US09326043
申请日：1999-06-04
申请人： Eric Horvitz , Timothy Paek
发明人： Eric Horvitz , Timothy Paek
IPC分类号： G06F1100
CPC分类号： G10L15/1822 , G06N7/005
摘要： A multi-level decision-analytic approach to failure and repair within computer-user communications is disclosed. In one embodiment, a computerized system for repairing communication failure within a computer-user interaction context includes a maintenance module, an intention module, and a conversation control subsystem. The maintenance module manages uncertainty regarding signal identification and channel fidelity. The intention module is supported by the maintenance module, and manages uncertainty about the recognition of user's goals from signals. The conversation control subsystem surrounds both the modules, and manages the joint activity between the computer and the user, and one or more high-level events regarding the joint activity.
摘要翻译：公开了一种用于计算机用户通信中的故障和修复的多层决策分析方法。在一个实施例中，用于修复计算机 - 用户交互环境内的通信故障的计算机化系统包括维护模块，意图模块和会话控制子系统。维护模块管理信号识别和信道保真度的不确定性。意图模块由维护模块支持，并且管理从信号识别用户目标的不确定性。会话控制子系统围绕两个模块，并管理计算机和用户之间的联合活动，以及关于联合活动的一个或多个高级事件。

5. 发明授权

US09086292B2 Routing, alerting, and transportation guidance based on preferences and learned or inferred risks and desirabilities 有权
标题翻译：基于偏好和学习或推断的风险和需求的路由，警报和交通指导
公开(公告)号：US09086292B2
公开(公告)日：2015-07-21
申请号：US12493131
申请日：2009-06-26
申请人： Eric Horvitz , John Krumm
发明人： Eric Horvitz , John Krumm
IPC分类号： G01C21/34 , G01C21/00 , G01C21/36
CPC分类号： G01C21/3484 , G01C21/3697
摘要： Techniques and systems are disclosed that provide a risk-based assessment for a user based on user location information. Incident data is acquired for incidents that involve potential risks (e.g., to people and/or property) from a plurality of locations and contexts, considering such factors as date, time, weather, traffic, and velocity. The incident data is matched to the user's location and context directly or indirectly to provide one or more potential outcomes of interest (e.g., accidents, injuries, fatalities), and inferences regarding the likelihood of events are made available. These measures are compared to desired risk thresholds for the user. In one embodiment, routes, times, and conditions of travel may be preferred over others routes, times, and conditions. In another embodiment, users may be notified of a condition or a vehicle's maximum velocity may be reduced when the matched incident data meets/exceeds a user's risk threshold.
摘要翻译：公开了基于用户位置信息为用户提供基于风险的评估的技术和系统。考虑到诸如日期，时间，天气，交通和速度等因素，从多个位置和情境中获取涉及潜在风险（例如对人和/或财产）的事件的事件数据。事件数据与用户的位置和环境直接或间接地匹配，以提供一个或多个潜在的感兴趣的结果（例如，事故，伤害，死亡），并且关于事件的可能性可用的推论。将这些措施与用户的期望风险阈值进行比较。在一个实施例中，旅行的路线，时间和条件可能优于其他路线，时间和条件。在另一个实施例中，可以向用户通知条件，或者当匹配的事件数据满足/超过用户的风险阈值时，可以减少车辆的最大速度。

6. 发明授权

US08825304B2 Mediation of tasks based on assessments of competing cognitive loads and needs 有权
标题翻译：基于评估竞争认知负荷和需求的任务调停
公开(公告)号：US08825304B2
公开(公告)日：2014-09-02
申请号：US12827037
申请日：2010-06-30
申请人： Eric Horvitz , Shamsi Tamara Iqbal
发明人： Eric Horvitz , Shamsi Tamara Iqbal
IPC分类号： B60R22/00 , E05F15/00 , G05D1/00 , G05D3/00 , G06F17/00
CPC分类号： G06N99/005
摘要： Among other things, one or more techniques and/or systems are disclosed for mediating tasks in real-time for safety-related concerns. A nature for a safety-related primary task, such as contextual elements of the task, is determined; and a nature of a secondary task that draws attention away from the primary task is also determined. A risk factor for a potential lack of cognitive resources which may be needed by the primary task is determined by applying the nature of the primary task and the nature of the secondary task to a trained risk factor model. The risk factor is applied to one or more safety-related systems in real-time, for example, to mitigate potential safety concerns.
摘要翻译：除其他之外，公开了一种或多种技术和/或系统用于实时安全地涉及安全性关注的任务。确定安全相关主要任务的性质，如任务的上下文元素; 还要确定提请注意远离主要任务的次要任务的性质。主要任务可能需要的潜在缺乏认知资源的风险因素是通过将主要任务的性质和次要任务的性质应用于训练有素的风险因子模型来确定的。风险因素实时应用于一个或多个安全相关系统，例如，以减轻潜在的安全问题。

7. 发明授权

US08768763B2 Online marketplace with shipping incentives 有权
标题翻译：在线市场与航运激励
公开(公告)号：US08768763B2
公开(公告)日：2014-07-01
申请号：US13174309
申请日：2011-06-30
申请人： Eric Horvitz , Gur Kimchi , Lili Cheng , Doug Burger , Stelios Paparizos , Marc Davis
发明人： Eric Horvitz , Gur Kimchi , Lili Cheng , Doug Burger , Stelios Paparizos , Marc Davis
IPC分类号： G06Q30/00
CPC分类号： G06Q30/0222 , G06Q10/0832 , G06Q10/08355 , G06Q30/06
摘要： A marketplace server and method for facilitating purchase transactions are provided. A marketplace server may include a routing engine configured to receive an order for goods from a first computing device associated with a first customer, with the order including a first delivery address of the customer. The routing engine also calculates a delivery route to the first delivery address. An offer engine is configured to create an offer for other goods. The offer includes a shipping incentive associated with a second delivery address of a second customer. The offer may be targeted to the second customer based on a proximity of the second delivery address to the delivery route. The offer engine sends the offer to a second computing device associated with the second customer. Upon receiving an acceptance of the offer from the computing device, the offer engine processes a purchase transaction for the offer.
摘要翻译：提供了一种用于促进采购交易的市场服务器和方法。市场服务器可以包括路由引擎，路由引擎被配置为从与第一客户相关联的第一计算设备接收货物的订单，该订单包括客户的第一传送地址。路由引擎还计算到第一个传送地址的传输路由。优惠引擎被配置为为其他商品创建报价。该优惠包括与第二客户的第二送货地址相关联的运送激励。基于第二递送地址与递送路线的接近度，该优惠可以针对第二客户。报价引擎将报价发送给与第二客户相关联的第二计算设备。在接收到来自计算设备的报价的接收之后，报价引擎处理该报价的购买交易。

8. 发明申请

US20130006754A1 MULTI-STEP IMPRESSION CAMPAIGNS 审中-公开
标题翻译：多阶段印象裁判
公开(公告)号：US20130006754A1
公开(公告)日：2013-01-03
申请号：US13174329
申请日：2011-06-30
申请人： Eric Horvitz , Lili Cheng , Roger Barga , Xuedong Huang , Zachary Apter , Semiha Ece Kamar
发明人： Eric Horvitz , Lili Cheng , Roger Barga , Xuedong Huang , Zachary Apter , Semiha Ece Kamar
IPC分类号： G06Q30/00
CPC分类号： G06Q30/00 , G06Q30/0251
摘要： Various embodiments are described for computerized advertising systems and methods. The system may include an ad server that includes an impression campaign engine configured to associate a target user profile with a plurality of computing devices. The ad server is also configured to receive a multi-step impression plan including a plurality of triggers from an advertiser. Each trigger is associated with a different advertisement to be served to at least one of the plurality of devices. The system also includes an ad serving engine configured to serve a first advertisement to a first device in response to making an inference from sensors or detecting a first trigger, and a second advertisement to a second device in response to a second inference or detecting a second trigger, according to the impression plan. A predictive model developed from machine learning may be used to develop a learning-based multi-step impression plan.
摘要翻译：针对计算机广告系统和方法描述了各种实施例。系统可以包括广告服务器，其包括被配置为将目标用户简档与多个计算设备相关联的印象活动引擎。广告服务器还被配置为接收包括来自广告主的多个触发器的多步展示计划。每个触发器与要被提供给多个设备中的至少一个的不同广告相关联。该系统还包括一个广告服务引擎，该广告服务引擎被配置为响应于从传感器进行推断或检测第一触发而向第一设备发送第一广告，并响应于第二推断或检测第二个推断，向第二设备发送第二广告触发，按照印象计划。可以使用从机器学习开发的预测模型来开发基于学习的多步印象计划。

9. 发明授权

US08346749B2 Balancing the costs of sharing private data with the utility of enhanced personalization of online services 有权
标题翻译：平衡共享私有数据的成本与增强的个性化在线服务的效用
公开(公告)号：US08346749B2
公开(公告)日：2013-01-01
申请号：US12147557
申请日：2008-06-27
申请人： Ranier Andreas Krause , Eric Horvitz
发明人： Ranier Andreas Krause , Eric Horvitz
IPC分类号： G06F17/30
CPC分类号： G06F17/30867 , G06Q30/02
摘要： Described herein is a method that includes determining a utility to a user of sharing a set of attributes for use in connection with personalized searching or other online services. The method further includes determining a cost to the user of sharing the set of attributes. The method also includes outputting an indication of a net benefit to the user of sharing the set of attributes based at least in part upon the determined utility and the determined cost.
摘要翻译：这里描述了一种方法，其包括确定用户共享用于结合个性化搜索或其他在线服务的一组属性的实用程序。该方法还包括确定用户共享该属性集的成本。该方法还包括至少部分地基于确定的效用和确定的成本，向用户输出净利益的指示，以共享该组属性。

10. 发明授权

US08340689B2 Commercially subsidized mobile communication devices and services 有权
标题翻译：商业补贴的移动通信设备和服务
公开(公告)号：US08340689B2
公开(公告)日：2012-12-25
申请号：US12701539
申请日：2010-02-06
申请人： Eric Horvitz , Xuedong Huang , Kamal Jain , Milind Vasudeo Mahajan
发明人： Eric Horvitz , Xuedong Huang , Kamal Jain , Milind Vasudeo Mahajan
IPC分类号： H04W24/00
CPC分类号： G06Q30/0267 , G06Q30/0261 , H04M15/00 , H04M15/09 , H04M2215/0192 , H04W4/00 , H04W4/025 , H04W4/24 , H04W48/02 , H04W64/00
摘要： Mobile communication devices, such as mobile phones, may be capable of recommending to a user various providers of one or more solicited services, e.g., by identifying a user location and identifying providers near the user location that provide the services, and by initiating a call between the user and a selected provider. However, the equipment and service costs of such devices may be prohibitive, particularly for mid-range mobile communication devices that may appeal to cost-conscious users. The prohibitive costs may be diminished by redirecting part or all of the cost of providing the recommendation service from the providers, e.g., by charging the provider a service cost upon initiating a call from the user to the provider, or upon representing the provider in a provider database. In one such embodiment, all service costs may be borne by providers, providing to the user a free recommendation service via the mobile communication device.
摘要翻译：诸如移动电话的移动通信设备可以能够向用户推荐一个或多个被请求的服务的各种提供者，例如通过识别用户位置并识别用户位置附近的提供服务的提供者，并且通过发起呼叫在用户和选定的提供商之间。然而，这些设备的设备和服务成本可能是过高的，特别是对于可能吸引具有成本意识的用户的中档移动通信设备。通过将提供推荐服务的成本的部分或全部重定向到提供者，例如，通过在向用户发起呼叫到提供者的呼叫中向服务商收取服务成本，或者以提供者数据库。在一个这样的实施例中，所有服务成本可以由提供商承担，经由移动通信设备向用户提供免费的推荐服务。

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