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. 发明授权

US07734471B2 Online learning for dialog systems 有权
标题翻译：在线学习对话系统
公开(公告)号：US07734471B2
公开(公告)日：2010-06-08
申请号：US11170999
申请日：2005-06-29
申请人： Timothy S. Paek , David M. Chickering , Eric J. Horvitz
发明人： Timothy S. Paek , David M. Chickering , Eric J. 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. 发明授权

US07707131B2 Thompson strategy based online reinforcement learning system for action selection 失效
标题翻译：基于Thompson战略的在线强化学习系统的行动选择
公开(公告)号：US07707131B2
公开(公告)日：2010-04-27
申请号：US11169503
申请日：2005-06-29
申请人： David M. Chickering , Timothy S. Paek , Eric J. Horvitz
发明人： David M. Chickering , Timothy S. Paek , Eric J. Horvitz
IPC分类号： G06N5/04 , G06N7/00 , G06N7/02
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。

3. 发明授权

US06931384B1 System and method providing utility-based decision making about clarification dialog given communicative uncertainty 有权
标题翻译：提供基于效用的决策的系统和方法关于澄清对话给定交际不确定性
公开(公告)号：US06931384B1
公开(公告)日：2005-08-16
申请号：US09832274
申请日：2001-04-10
申请人： Eric J. Horvitz , Timothy S. Paek
发明人： Eric J. Horvitz , Timothy S. Paek
IPC分类号： G06N7/00 , G10L15/18 , G06F15/18
CPC分类号： G06N7/005 , G10L15/1822
摘要： An interactive communications system is provided in accordance with the present invention. The system includes a component for analyzing sequential communications including speech, gestures and other modalities related to an underlying communicative intention. The component concurrently employs at least two of the communications in determining an action to facilitate achieving the intention.
摘要翻译：根据本发明提供一种交互式通信系统。系统包括用于分析顺序通信的组件，包括语音，手势和与底层通信意图相关的其他模式。该组件同时采用至少两个通信来确定促进实现意图的动作。

4. 发明授权

US07580908B1 System and method providing utility-based decision making about clarification dialog given communicative uncertainty 有权
标题翻译：提供基于效用的决策的系统和方法关于澄清对话给定交际不确定性
公开(公告)号：US07580908B1
公开(公告)日：2009-08-25
申请号：US11100699
申请日：2005-04-07
申请人： Eric J. Horvitz , Timothy S. Paek
发明人： Eric J. Horvitz , Timothy S. Paek
IPC分类号： G06F17/00 , G06N5/00
CPC分类号： G06N7/005 , G10L15/1822
摘要： An interactive communications system is provided in accordance with the present invention. The system includes a component for analyzing sequential communications including speech, gestures and other modalities related to an underlying communicative intention. The component concurrently employs at least two of the communications in determining an action to facilitate achieving the intention.
摘要翻译：根据本发明提供一种交互式通信系统。系统包括用于分析顺序通信的组件，包括语音，手势和与底层通信意图相关的其他模式。该组件同时采用至少两个通信来确定促进实现意图的动作。

5. 发明授权

US08244545B2 Dialog repair based on discrepancies between user model predictions and speech recognition results 有权
标题翻译：基于用户模型预测和语音识别结果之间的差异的对话框修复
公开(公告)号：US08244545B2
公开(公告)日：2012-08-14
申请号：US11393321
申请日：2006-03-30
申请人： Timothy S. Paek , David M. Chickering
发明人： Timothy S. Paek , David M. Chickering
IPC分类号： G10L21/00
CPC分类号： G10L15/22 , G10L2015/228
摘要： An architecture is presented that leverages discrepancies between user model predictions and speech recognition results by identifying discrepancies between the predictive data and the speech recognition data and repairing the data based in part on the discrepancy. User model predictions predict what goal or action speech application users are likely to pursue based in part on past user behavior. Speech recognition results indicate what goal speech application users are likely to have spoken based in part on words spoken under specific constraints. Discrepancies between the predictive data and the speech recognition data are identified and a dialog repair is engaged for repairing these discrepancies. By engaging in repairs when there is a discrepancy between the predictive results and the speech recognition results, and utilizing feedback obtained via interaction with a user, the architecture can learn about the reliability of both user model predictions and speech recognition results for future processing.
摘要翻译：提出了一种通过识别预测数据和语音识别数据之间的差异以及部分地基于差异来修复数据来利用用户模型预测和语音识别结果之间的差异的架构。用户模型预测部分地基于过去的用户行为来预测用户可能追求的目标或动作语音应用程序。语音识别结果表明，目标语音应用程序用户可能部分地基于特定约束条件下所说的话语言。识别预测数据和语音识别数据之间的差异，并进行对话修复以修复这些差异。通过在预测结果和语音识别结果之间存在差异并利用通过与用户的交互获得的反馈来进行维修，架构可以了解用户模型预测和语音识别结果的可靠性以供将来处理。

6. 发明申请

US20090054123A1 INFORMATION COLLECTION DURING GAME PLAY 有权
标题翻译：游戏中的信息收集
公开(公告)号：US20090054123A1
公开(公告)日：2009-02-26
申请号：US11843468
申请日：2007-08-22
申请人： Anton Mityagin , Aparna Lakshmiratan , Asela J. Gunawardana , Christopher A. Meek , David M. Chickering , Paul N. Bennett , Timothy S. Paek
发明人： Anton Mityagin , Aparna Lakshmiratan , Asela J. Gunawardana , Christopher A. Meek , David M. Chickering , Paul N. Bennett , Timothy S. Paek
IPC分类号： G06F19/00 , A63F13/00
CPC分类号： A63F13/798 , A63F13/12 , A63F13/23 , A63F13/33 , A63F13/46 , A63F13/75 , A63F13/85 , A63F2300/558 , A63F2300/5586 , G06Q10/10 , G06Q30/02 , G07F17/3225 , G07F17/3244
摘要： Systems and methods allow an on-line game to extract information relevant to a specific need of a game platform or service platform. The specific need relates to management and use of digital content, and is addressed by designing and playing an on-line collaborative game. The rules of the game intend to solve a specific task dictated by the specific need. Players' responses to the game generate a wealth of information related to a specific task objective, such as ranking, sorting, and evaluating a set of digital content items. To compel participation in a game, players can be rewarded with monetary value rewards. As a game illustration, an image selection game (ISG) that exploits human contextual inference is described in detail. The information extracted from ISG is a list of key-image associations, relevant for the task of image sorting and ranking.
摘要翻译：系统和方法允许在线游戏提取与游戏平台或服务平台的特定需要相关的信息。具体需要涉及数字内容的管理和使用，并通过设计和播放在线协作游戏来解决。游戏规则旨在解决具体需求所指定的特定任务。玩家对游戏的反应产生与特定任务目标相关的大量信息，例如排序，排序和评估一组数字内容项目。为了强制参与游戏，玩家可以奖励货币价值奖励。作为游戏说明，详细描述了利用人类背景推理的图像选择游戏（ISG）。从ISG提取的信息是与图像排序和排序任务相关的关键图像关联的列表。

7. 发明申请

US20080010124A1 MANAGING COMMITMENTS OF TIME ACROSS A NETWORK 审中-公开
标题翻译：管理网络时间的承诺
公开(公告)号：US20080010124A1
公开(公告)日：2008-01-10
申请号：US11426679
申请日：2006-06-27
申请人： Timothy S. Paek , Christopher A. Meek , David M. Chickering
发明人： Timothy S. Paek , Christopher A. Meek , David M. Chickering
IPC分类号： G06Q30/00
CPC分类号： G06Q30/02 , G06Q30/0208 , G06Q30/0273
摘要： A service manager manages connection tokens in a network of users. The connection token has a plurality of defined terms and can be representative of a commitment of time for a user in the network. Connection tokens can be used to engage in a real-time communication with another user in exchange for a fee. The service manager manages possession of the connection tokens amongst the users of the network and executes the connection token in accordance with the defined terms. Additionally, the service manager can facilitate real-time communication among users based on the connection tokens.
摘要翻译：服务管理器管理用户网络中的连接令牌。连接令牌具有多个定义的术语，并且可以代表网络中用户对时间的承诺。连接令牌可用于与其他用户进行实时通信，以交换费用。服务管理器管理在网络的用户中拥有连接令牌，并根据定义的术语执行连接令牌。此外，服务管理器可以促进基于连接令牌的用户之间的实时通信。

8. 发明申请

US20080005011A1 MANAGING INFORMATION SOLICITATIONS ACROSS A NETWORK 审中-公开
标题翻译：通过网络管理信息索引
公开(公告)号：US20080005011A1
公开(公告)日：2008-01-03
申请号：US11424120
申请日：2006-06-14
申请人： Christopher A. Meek , David M. Chickering , Timothy S. Paek
发明人： Christopher A. Meek , David M. Chickering , Timothy S. Paek
IPC分类号： G06Q40/00
CPC分类号： G06Q30/08 , G06Q40/04
摘要： A service manager manages information solicitations in a network of users. An information solicitation is posted that is received from an information consumer. The posted information solicitation is provided to at least a portion of the users of the network for auction. The information solicitation includes a request to engage in a real-time communication with an information provider about a particular subject. Bids are received from a plurality of information providers. The bids are provided to the information consumer for selection. The information consumer is connected with a selected one of the plurality of information providers.
摘要翻译：服务管理器管理用户网络中的信息请求。从信息消费者那里收到信息请求。发布的信息请求被提供给用于拍卖的网络的至少一部分用户。信息征集包括与信息提供商就特定主题进行实时通信的请求。从多个信息提供者接收出价。出价提供给信息消费者进行选择。所述信息使用者与所述多个信息提供者中选择的一个相关联。

9. 发明授权

US08032375B2 Using generic predictive models for slot values in language modeling 有权
标题翻译：在语言建模中使用时隙值的通用预测模型
公开(公告)号：US08032375B2
公开(公告)日：2011-10-04
申请号：US11378202
申请日：2006-03-17
申请人： David M. Chickering , Timothy S. Paek
发明人： David M. Chickering , Timothy S. Paek
IPC分类号： G10L11/00 , G10L15/00 , G06N3/08
CPC分类号： G06Q10/10
摘要： A generic predictive argument model that can be applied to a set of shot values to predict a target slot value is provided. The generic predictive argument model can predict whether or not a particular value or item is the intended target of the user command given various features. A prediction for each of the slot values can then be normalized to infer a distribution over all values or items. For any set of slot values (e.g., contacts), a number of binary variable s are created that indicate whether or not each specific slot value was the intended target. For each slot value, a set of input features can be employed to predict the corresponding binary variable. These input features are generic properties of the contact that are “instantiated” based o n properties of the contact (e.g., contact-specific features). These contact-specific features can be stored in a user data store.
摘要翻译：提供了可应用于一组镜头值以预测目标时隙值的通用预测参数模型。通用预测参数模型可以预测特定值或项目是否是给定各种特征的用户命令的预期目标。然后可以对每个时隙值的预测进行归一化以推断所有值或项目上的分布。对于任何一组时隙值（例如，联系人），创建指示每个特定时隙值是否为预期目标的多个二进制变量。对于每个时隙值，可以采用一组输入特征来预测相应的二进制变量。这些输入特征是基于联系人的“实例化”属性的联系人的通用属性（例如联系人特定的特征）。这些联系人特定的功能可以存储在用户数据存储中。

10. 发明授权

US09283476B2 Information collection during game play 有权
标题翻译：在游戏中收集信息
公开(公告)号：US09283476B2
公开(公告)日：2016-03-15
申请号：US11843468
申请日：2007-08-22
申请人： Anton Mityagin , Aparna Lakshmiratan , Asela J. Gunawardana , Christopher A. Meek , David M. Chickering , Paul N. Bennett , Timothy S. Paek
发明人： Anton Mityagin , Aparna Lakshmiratan , Asela J. Gunawardana , Christopher A. Meek , David M. Chickering , Paul N. Bennett , Timothy S. Paek
IPC分类号： G06F17/00 , A63F13/30 , G06Q10/10 , G06Q30/02
CPC分类号： A63F13/798 , A63F13/12 , A63F13/23 , A63F13/33 , A63F13/46 , A63F13/75 , A63F13/85 , A63F2300/558 , A63F2300/5586 , G06Q10/10 , G06Q30/02 , G07F17/3225 , G07F17/3244
摘要： Systems and methods allow an on-line game to extract information relevant to a specific need of a game platform or service platform. The specific need relates to management and use of digital content, and is addressed by designing and playing an on-line collaborative game. The rules of the game intend to solve a specific task dictated by the specific need. Players' responses to the game generate a wealth of information related to a specific task objective, such as ranking, sorting, and evaluating a set of digital content items. To compel participation in a game, players can be rewarded with monetary value rewards. As a game illustration, an image selection game (ISG) that exploits human contextual inference is described in detail. The information extracted from ISG is a list of key-image associations, relevant for the task of image sorting and ranking.
摘要翻译：系统和方法允许在线游戏提取与游戏平台或服务平台的特定需要相关的信息。具体需要涉及数字内容的管理和使用，并通过设计和播放在线协作游戏来解决。游戏规则旨在解决具体需求所指定的特定任务。玩家对游戏的反应产生与特定任务目标相关的大量信息，例如排序，排序和评估一组数字内容项目。为了强制参与游戏，玩家可以奖励货币价值奖励。作为游戏说明，详细描述了利用人类背景推理的图像选择游戏（ISG）。从ISG提取的信息是与图像排序和排序任务相关的关键图像关联的列表。

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