利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

19 条记录 (耗时 0.024 秒)

    Belief tracking and action selection in spoken dialog systems
    3.
    发明授权
    Belief tracking and action selection in spoken dialog systems 有权
    在口语对话系统中的信念跟踪和动作选择

    公开(公告)号：US08676583B2

    公开(公告)日：2014-03-18

    申请号：US13221155

    申请日：2011-08-30

    申请人： Rakesh Gupta ,  Deepak Ramachandran ,  Antoine Raux ,  Neville Mehta ,  Stefan Krawczyk ,  Matthew Hoffman

    发明人： Rakesh Gupta ,  Deepak Ramachandran ,  Antoine Raux ,  Neville Mehta ,  Stefan Krawczyk ,  Matthew Hoffman

    IPC分类号： G10L15/22

    CPC分类号： G10L15/22

    摘要： An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.

    摘要翻译： 响应于用户的说话话语，在口语对话系统中执行动作。 检索或创建将用户意图的信念状态映射到动作的策略。 信仰状态是根据口语说出来确定的，并且基于确定的信念状态和策略选择动作。 该动作被执行，并且在一个实施例中，涉及请求澄清来自用户的说话话语。 创建策略可以包括模拟用户输入和对话系统交互，并且迭代地修改策略参数，直到满足策略阈值。 在一个实施例中，通过将口语发音转换成文本来确定置信状态，将文本分配给与概率本体树（POT）中的节点相关联的一个或多个对话时隙，以及基于概率分布表中的概率分布表确定联合概率 POT和对话框插槽分配。

    FAMILIARITY MODELING
    4.
    发明申请
    FAMILIARITY MODELING 有权
    家族建模

    公开(公告)号：US20150032424A1

    公开(公告)日：2015-01-29

    申请号：US13951015

    申请日：2013-07-25

    申请人： Rakesh Gupta ,  Igor V. Karpov ,  Antoine Raux ,  Deepak Ramachandran

    发明人： Rakesh Gupta ,  Igor V. Karpov ,  Antoine Raux ,  Deepak Ramachandran

    IPC分类号： G06F17/50 ,  G06N7/00

    CPC分类号： G01C21/00 ,  G01C21/3484 ,  G01C21/3641 ,  G06N99/005

    摘要： One or more embodiments of techniques or systems for modeling familiarity for a traveler are provided herein. Familiarity evidence can be received, indicative of how familiar a traveler is with an area or road segment, and based on a number of visits the traveler has made to that area. The familiarity evidence can be used to generate one or more familiarity models indicative of a predicted familiarity of locations around the area. Familiarity models can be based on kernels, graph distances, Markov random fields (MRFs), etc. When route directions are generated from an origin location to a destination location, one or more of the directions can be provided based on one or more of the familiarity models. For example, if a familiarity model indicates that a traveler is familiar with a route, driving directions of the route can be adapted to be more succinct.

    摘要翻译： 本文提供了用于建模旅客的熟悉度的技术或系统的一个或多个实施例。 可以接收到熟悉的证据，指示旅行者在区域或路段中的熟悉程度，以及旅客对该地区的访问次数。 熟悉证据可用于产生一个或多个熟悉模型，表明该地区周边地区的熟悉程度。 熟悉度模型可以基于内核，图形距离，马尔可夫随机场（MRFs）等。当从原点位置到目标位置生成路线方向时，可以基于一个或多个方向来提供一个或多个方向 熟悉模式。 例如，如果熟悉模式表明旅行者熟悉路线，路线的驾驶方向可以更加简洁。

    LANDMARK-BASED LOCATION BELIEF TRACKING FOR VOICE-CONTROLLED NAVIGATION SYSTEM
    5.
    发明申请
    LANDMARK-BASED LOCATION BELIEF TRACKING FOR VOICE-CONTROLLED NAVIGATION SYSTEM 有权
    用于语音控制导航系统的基于LANDMARK的位置直接跟踪

    公开(公告)号：US20130297321A1

    公开(公告)日：2013-11-07

    申请号：US13801441

    申请日：2013-03-13

    申请人： Antoine Raux ,  Rakesh Gupta ,  Deepak Ramachandran ,  Yi Ma

    发明人： Antoine Raux ,  Rakesh Gupta ,  Deepak Ramachandran ,  Yi Ma

    IPC分类号： G01C21/26

    CPC分类号： G01C21/26 ,  G01C21/3608 ,  G01C21/3644

    摘要： An utterance is received from a user specifying a location attribute and a landmark. A set of candidate locations is identified based on the specified location attribute, and a confidence score can be determined for each candidate location. A set of landmarks is identified based on the specified landmark, and confidence scores can be determined for the landmarks. An associated kernel model is generated for each landmark. Each kernel model is centered at the location of the associated landmark on a map, and the amplitude of the kernel model can be based on landmark attributes, landmark confidence scores, characteristics of the user, and the like. The candidate locations are ranked based on the amplitudes of overlapping kernel models at the candidate locations, and can also be ranked based on confidence scores associated with the candidate locations. A candidate location is selected and presented to the user based on the candidate location ranking

    摘要翻译： 从指定位置属性和地标的用户接收到话语。 基于指定的位置属性来识别一组候选位置，并且可以为每个候选位置确定可信度得分。 基于指定的地标识别一组地标，并且可以为地标确定置信度得分。 为每个地标生成相关的内核模型。 每个核心模型集中在地图上相关联的地标的位置，并且内核模型的幅度可以基于地标属性，地标置信度得分，用户特征等。 候选位置基于候选位置处的重叠核心模型的幅度进行排序，并且还可以基于与候选位置相关联的置信度得分进行排名。 基于候选位置排名，选择候选位置并呈现给用户

    Landmark-based location belief tracking for voice-controlled navigation system
    6.
    发明授权
    Landmark-based location belief tracking for voice-controlled navigation system 有权
    用于语音控制导航系统的地标位置信念跟踪

    公开(公告)号：US09127950B2

    公开(公告)日：2015-09-08

    申请号：US13801441

    申请日：2013-03-13

    申请人： Antoine Raux ,  Rakesh Gupta ,  Deepak Ramachandran ,  Yi Ma

    发明人： Antoine Raux ,  Rakesh Gupta ,  Deepak Ramachandran ,  Yi Ma

    IPC分类号： G01C21/26 ,  G01C21/36

    CPC分类号： G01C21/26 ,  G01C21/3608 ,  G01C21/3644

    摘要： An utterance is received from a user specifying a location attribute and a landmark. A set of candidate locations is identified based on the specified location attribute, and a confidence score can be determined for each candidate location. A set of landmarks is identified based on the specified landmark, and confidence scores can be determined for the landmarks. An associated kernel model is generated for each landmark. Each kernel model is centered at the location of the associated landmark on a map, and the amplitude of the kernel model can be based on landmark attributes, landmark confidence scores, characteristics of the user, and the like. The candidate locations are ranked based on the amplitudes of overlapping kernel models at the candidate locations, and can also be ranked based on confidence scores associated with the candidate locations. A candidate location is selected and presented to the user based on the candidate location ranking.

    摘要翻译： 从指定位置属性和地标的用户接收到话语。 基于指定的位置属性来识别一组候选位置，并且可以为每个候选位置确定可信度得分。 基于指定的地标识别一组地标，并且可以为地标确定置信度得分。 为每个地标生成相关的内核模型。 每个核心模型集中在地图上相关联的地标的位置，并且内核模型的幅度可以基于地标属性，地标置信度得分，用户特征等。 候选位置基于候选位置处的重叠核心模型的幅度进行排序，并且还可以基于与候选位置相关联的置信度得分进行排名。 候选位置被选择并且基于候选位置排名呈现给用户。

    BELIEF TRACKING AND ACTION SELECTION IN SPOKEN DIALOG SYSTEMS
    7.
    发明申请
    BELIEF TRACKING AND ACTION SELECTION IN SPOKEN DIALOG SYSTEMS 有权
    双语对话系统中的直接跟踪和行动选择

    公开(公告)号：US20120053945A1

    公开(公告)日：2012-03-01

    申请号：US13221155

    申请日：2011-08-30

    申请人： Rakesh Gupta ,  Deepak Ramachandran ,  Antoine Raux ,  Neville Mehta ,  Stefan Krawczyk ,  Matthew Hoffman

    发明人： Rakesh Gupta ,  Deepak Ramachandran ,  Antoine Raux ,  Neville Mehta ,  Stefan Krawczyk ,  Matthew Hoffman

    IPC分类号： G10L15/18

    CPC分类号： G10L15/22

    摘要： An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.

    摘要翻译： 响应于用户的说话话语，在口语对话系统中执行动作。 检索或创建将用户意图的信念状态映射到动作的策略。 信仰状态是根据口语说出来确定的，并且基于确定的信念状态和策略选择动作。 该动作被执行，并且在一个实施例中，涉及请求澄清来自用户的说话话语。 创建策略可以包括模拟用户输入和对话系统交互，并且迭代地修改策略参数，直到满足策略阈值。 在一个实施例中，通过将口语发音转换成文本来确定置信状态，将文本分配给与概率本体树（POT）中的节点相关联的一个或多个对话时隙，以及基于概率分布表中的概率分布表确定联合概率 POT和对话框插槽分配。

    Smoothed Sarsa: Reinforcement Learning for Robot Delivery Tasks
    8.
    发明申请
    Smoothed Sarsa: Reinforcement Learning for Robot Delivery Tasks 有权
    平滑Sarsa：加强学习机器人传送任务

    公开(公告)号：US20100094786A1

    公开(公告)日：2010-04-15

    申请号：US12578574

    申请日：2009-10-13

    申请人： Rakesh Gupta ,  Deepak Ramachandran

    发明人： Rakesh Gupta ,  Deepak Ramachandran

    IPC分类号： G06F15/18

    CPC分类号： G06N99/005

    摘要： The present invention provides a method for learning a policy used by a computing system to perform a task, such delivery of one or more objects by the computing system. During a first time interval, the computing system determines a first state, a first action and a first reward value. As the computing system determines different states, actions and reward values during subsequent time intervals, a state description identifying the current sate, the current action, the current reward and a predicted action is stored. Responsive to a variance of a stored state description falling below a threshold value, the stored state description is used to modify one or more weights in the policy associated with the first state.

    摘要翻译： 本发明提供了一种用于学习由计算系统用于执行任务的策略的方法，所述任务由计算系统传送一个或多个对象。 在第一时间间隔期间，计算系统确定第一状态，第一动作和第一回报值。 随着计算系统在随后的时间间隔期间确定不同的状态，动作和奖励值，存储识别当前状态，当前动作，当前奖励和预测动作的状态描述。 响应于低于阈值的存储状态描述的方差，存储的状态描述用于修改与第一状态相关联的策略中的一个或多个权重。

    TORO: TRACKING AND OBSERVING ROBOT
    9.
    发明申请
    TORO: TRACKING AND OBSERVING ROBOT 有权
    TORO：跟踪和观察机器人

    公开(公告)号：US20090147994A1

    公开(公告)日：2009-06-11

    申请号：US12249849

    申请日：2008-10-10

    申请人： Rakesh Gupta ,  Deepak Ramachandran

    发明人： Rakesh Gupta ,  Deepak Ramachandran

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00295 ,  G06T7/143 ,  G06T7/277 ,  G06T2207/10016

    摘要： The present invention provides a method for tracking entities, such as people, in an environment over long time periods. A region-based model is generated to model beliefs about entity locations. Each region corresponds to a discrete area representing a location where an entity is likely to be found. Each region includes one or more positions which more precisely specify the location of an entity within the region so that the region defines a probability distribution of the entity residing at different positions within the region. A region-based particle filtering method is applied to entities within the regions so that the probability distribution of each region is updated to indicate the likelihood of the entity residing in a particular region as the entity moves.

    摘要翻译： 本发明提供了一种用于在长时间的环境中跟踪诸如人之类的实体的方法。 生成基于区域的模型来模拟关于实体位置的信念。 每个区域对应于表示实体可能被找到的位置的离散区域。 每个区域包括一个或多个位置，其更精确地指定区域内的实体的位置，使得该区域定义驻留在区域内的不同位置的实体的概率分布。 基于区域的粒子滤波方法被应用于区域内的实体，使得每个区域的概率分布被更新，以指示实体在实体移动时驻留在特定区域中的可能性。

    Toro: tracking and observing robot
    10.
    发明授权
    Toro: tracking and observing robot 有权
    托罗：跟踪和观察机器人

    公开(公告)号：US08077919B2

    公开(公告)日：2011-12-13

    申请号：US12249849

    申请日：2008-10-10

    申请人： Rakesh Gupta ,  Deepak Ramachandran

    发明人： Rakesh Gupta ,  Deepak Ramachandran

    IPC分类号： G06K9/00 ,  G06F11/00

    CPC分类号： G06K9/00295 ,  G06T7/143 ,  G06T7/277 ,  G06T2207/10016

    摘要： The present invention provides a method for tracking entities, such as people, in an environment over long time periods. A region-based model is generated to model beliefs about entity locations. Each region corresponds to a discrete area representing a location where an entity is likely to be found. Each region includes one or more positions which more precisely specify the location of an entity within the region so that the region defines a probability distribution of the entity residing at different positions within the region. A region-based particle filtering method is applied to entities within the regions so that the probability distribution of each region is updated to indicate the likelihood of the entity residing in a particular region as the entity moves.

    摘要翻译： 本发明提供了一种用于在长时间的环境中跟踪诸如人之类的实体的方法。 生成基于区域的模型来模拟关于实体位置的信念。 每个区域对应于表示实体可能被找到的位置的离散区域。 每个区域包括一个或多个位置，其更精确地指定区域内的实体的位置，使得该区域定义驻留在区域内的不同位置的实体的概率分布。 基于区域的粒子滤波方法被应用于区域内的实体，使得每个区域的概率分布被更新，以指示实体在实体移动时驻留在特定区域中的可能性。