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

US08433558B2 Methods and systems for natural language understanding using human knowledge and collected data 有权
标题翻译：使用人类知识和收集数据进行自然语言理解的方法和系统
公开(公告)号：US08433558B2
公开(公告)日：2013-04-30
申请号：US11188825
申请日：2005-07-25
申请人： Srinivas Bangalore , Mazin Gilbert , Narendra K. Gupta
发明人： Srinivas Bangalore , Mazin Gilbert , Narendra K. Gupta
IPC分类号： G06F17/20 , G06F17/27 , G06F17/21 , G10L15/28 , G10L15/18 , G10L15/14 , G10L21/00
CPC分类号： G10L15/183 , G06F17/2818 , G10L15/14 , G10L15/19
摘要： Disclosed herein are systems and methods to incorporate human knowledge when developing and using statistical models for natural language understanding. The disclosed systems and methods embrace a data-driven approach to natural language understanding which progresses seamlessly along the continuum of availability of annotated collected data, from when there is no available annotated collected data to when there is any amount of annotated collected data.
摘要翻译：这里公开的是在开发和使用自然语言理解的统计模型时将人类知识结合在一起的系统和方法。所公开的系统和方法包含一种数据驱动的自然语言理解方法，其从注释收集的数据的可用性的连续性无缝地进行，从没有可用的注释收集的数据到当有任何数量的注释收集的数据时。

2. 发明授权

US08190436B2 System and method of spoken language understanding in human computer dialogs 有权
标题翻译：在人机对话中口语理解的系统和方法
公开(公告)号：US08190436B2
公开(公告)日：2012-05-29
申请号：US10310596
申请日：2002-12-05
申请人： Srinivas Bangalore , Narendra K. Gupta , Mazin G Rahim
发明人： Srinivas Bangalore , Narendra K. Gupta , Mazin G Rahim
IPC分类号： G10L21/00 , G06F17/20 , G06F17/27
CPC分类号： G10L15/1815 , G06F17/2785 , G10L13/043 , G10L15/02 , G10L15/1822 , G10L15/265
摘要： A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.
摘要翻译：公开了一种提高口语对话系统中的自动语音识别的系统和方法。该方法包括将语音识别器输出划分为独立子句，识别每个自包含子句中的对话行为，通过识别当前域对象和/或当前域动作进行限定对话行为，以及确定是否可进一步限定对于当前域对象和/或当前域操作。如果可以进一步鉴定，则该方法包括识别与当前域对象和/或当前域操作相关联的另一域操作和/或另一域对象，将另一域操作和/或另一域对象重新分配为当前域操作，以及 /或当前域对象，然后递归地限定新的当前域操作和/或当前对象。这个过程一直持续到没有什么是剩下的资格。

3. 发明申请

US20120239383A1 SYSTEM AND METHOD OF SPOKEN LANGUAGE UNDERSTANDING IN HUMAN COMPUTER DIALOGS 有权
标题翻译：人类语言对话中语言语言理解的系统与方法
公开(公告)号：US20120239383A1
公开(公告)日：2012-09-20
申请号：US13481031
申请日：2012-05-25
申请人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
发明人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
IPC分类号： G06F17/27 , G10L15/00
CPC分类号： G10L15/1815 , G06F17/2785 , G10L13/043 , G10L15/02 , G10L15/1822 , G10L15/265
摘要： A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.
摘要翻译：公开了一种提高口语对话系统中的自动语音识别的系统和方法。该方法包括将语音识别器输出划分为独立子句，识别每个自包含子句中的对话行为，通过识别当前域对象和/或当前域动作进行限定对话行为，以及确定是否可进行进一步的限定对于当前域对象和/或当前域操作。如果可以进一步鉴定，则该方法包括识别与当前域对象和/或当前域操作相关联的另一域操作和/或另一域对象，将另一域操作和/或另一域对象重新分配为当前域操作，以及 /或当前域对象，然后递归地限定新的当前域操作和/或当前对象。这个过程一直持续到没有什么是剩下的资格。

4. 发明授权

US08849648B1 System and method of extracting clauses for spoken language understanding 有权
公开(公告)号：US08849648B1
公开(公告)日：2014-09-30
申请号：US10329138
申请日：2002-12-24
申请人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
发明人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
IPC分类号： G06F17/27
CPC分类号： G06F17/2705 , G06F17/218 , G06F17/27 , G06F17/2775 , G10L15/05 , G10L15/26 , G10L2015/025 , G10L2015/081 , G10L2015/088
摘要： A clausifier and method of extracting clauses for spoken language understanding are disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.

5. 发明授权

US08818793B1 System and method of extracting clauses for spoken language understanding 有权
标题翻译：提取语言理解条款的系统和方法
公开(公告)号：US08818793B1
公开(公告)日：2014-08-26
申请号：US10446489
申请日：2003-05-28
申请人： Srinivas Bangalore , Narendra K. Gupta , Mazin G Rahim
发明人： Srinivas Bangalore , Narendra K. Gupta , Mazin G Rahim
IPC分类号： G06F17/27
CPC分类号： G10L15/063 , G06F17/271 , G06F17/277 , G10L2015/0635
摘要： A clausifier and method of extracting clauses for spoken language understanding are disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.
摘要翻译：公开了一种提取语言理解条款的分类器和方法。该方法涉及从语音话语文本生成一组子句，并且包括在与句子边界相关的语音话语文本中插入至少一个边界标签，插入至少一个编辑标签，该编辑标签指示语音话语文本的一部分以去除并插入讲话话语文本内的至少一个连接标签。结果是可以根据插入的至少一个边界标签，至少一个编辑标签和至少一个连接标签在语音发音文本内识别的一组子句。所公开的分类器包括句子边界分类器，编辑检测器分类器和连接检测器分类器。克隆器可以包括单个分类器或多个分类器，以执行识别句子边界，编辑文本以及识别文本内的连词的步骤。

6. 发明授权

US08386262B2 System and method of spoken language understanding in human computer dialogs 有权
公开(公告)号：US08386262B2
公开(公告)日：2013-02-26
申请号：US13481031
申请日：2012-05-25
申请人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
发明人： Srinivas Bangalore , Narendra K. Gupta , Mazin G. Rahim
IPC分类号： G10L21/00 , G06F17/20 , G06F17/27
CPC分类号： G10L15/1815 , G06F17/2785 , G10L13/043 , G10L15/02 , G10L15/1822 , G10L15/265
摘要： A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.

7. 发明申请

US20070280215A1 Method and apparatus for providing a click-to-talk service for advertisements 审中-公开
标题翻译：为广告提供点击通话服务的方法和装置
公开(公告)号：US20070280215A1
公开(公告)日：2007-12-06
申请号：US11444882
申请日：2006-05-31
申请人： Mazin Gilbert , Narendra K. Gupta , Benjamin J. Stern
发明人： Mazin Gilbert , Narendra K. Gupta , Benjamin J. Stern
IPC分类号： H04L12/66
CPC分类号： H04L29/06027 , H04L65/1069 , H04N21/234318 , H04N21/235 , H04N21/2542 , H04N21/435 , H04N21/44222 , H04N21/47202 , H04N21/4725 , H04N21/4788 , H04N21/643 , H04N21/812
摘要： A method and apparatus for providing a click-to-talk service for advertisements carried over packet networks such as digital cable networks, Voice over Internet Protocol (VoIP) and Service over Internet Protocol (SoIP) networks are disclosed. For example, an enterprise customer subscribes to a service with a service provider that provides a click-to-talk feature with its advertisements on television channels. In one embodiment, the network service provider obtains meta-information from a video content and transmits the meta-information and the video content to a set-top box. The network service provider also enables consumers while viewing the advertisements to click on their remote control to initiate a call to talk to the advertising enterprise entity. Thus, when the consumer clicks-to-talk to the enterprise entity, the network service provider enables the consumer to reach the enterprise entity immediately.
摘要翻译：公开了一种用于为诸如数字有线网络，因特网协议语音（VoIP）和因特网协议（SoIP）网络之类的分组网络承载的广播提供点击通话服务的方法和装置。例如，企业客户与服务提供商订阅服务，该服务提供商在电视频道上向其广告提供点击通话功能。在一个实施例中，网络服务提供商从视频内容获取元信息，并将元信息和视频内容发送到机顶盒。网络服务提供商还可以在查看广告时使消费者点击他们的遥控器以发起与广告企业实体通话的呼叫。因此，当消费者与企业实体点击通话时，网络服务提供商使消费者能够立即到达企业实体。

8. 发明申请

US20080235740A1 System and method for storing advertising data 有权
标题翻译：用于存储广告数据的系统和方法
公开(公告)号：US20080235740A1
公开(公告)日：2008-09-25
申请号：US11725995
申请日：2007-03-20
申请人： Narendra K. Gupta , Mazin Gilbert
发明人： Narendra K. Gupta , Mazin Gilbert
IPC分类号： H04N7/173
CPC分类号： H04N21/812 , G06Q30/0242 , H04N21/2668 , H04N21/42204 , H04N21/4331 , H04N21/4332 , H04N21/44213 , H04N21/4532 , H04N21/64322
摘要： A computerized method is disclosed for presenting advertising data extracted from a video data stream, the method including storing a plurality of advertising data items extracted from the video data stream at an end user device; and displaying a plurality of sorted advertising indicator data items at the end user device, wherein each of the advertising indicator data items indicates one of the plurality of stored advertising data items. A system is disclosed for performing the method. A data structure is disclosed providing a functional and structural interrelationship between a processor in the system and data in the data structure.
摘要翻译：公开了一种用于呈现从视频数据流提取的广告数据的计算机化方法，所述方法包括：在最终用户设备处存储从视频数据流提取的多个广告数据项; 以及在所述终端用户设备处显示多个排序广告指示符数据项，其中所述广告指示符数据项中的每一个指示所述多个存储的广告数据项中的一个。公开了一种用于执行该方法的系统。公开了提供系统中的处理器与数据结构中的数据之间的功能和结构相互关系的数据结构。

9. 发明授权

US09106974B2 System and method for storing advertising data 有权
标题翻译：用于存储广告数据的系统和方法
公开(公告)号：US09106974B2
公开(公告)日：2015-08-11
申请号：US11725995
申请日：2007-03-20
申请人： Narendra K. Gupta , Mazin Gilbert
发明人： Narendra K. Gupta , Mazin Gilbert
IPC分类号： H04N7/173 , H04N21/81 , H04N21/433
CPC分类号： H04N21/812 , G06Q30/0242 , H04N21/2668 , H04N21/42204 , H04N21/4331 , H04N21/4332 , H04N21/44213 , H04N21/4532 , H04N21/64322
摘要： A computerized method is disclosed for presenting advertising data extracted from a video data stream, the method including storing a plurality of advertising data items extracted from the video data stream at an end user device; and displaying a plurality of sorted advertising indicator data items at the end user device, wherein each of the advertising indicator data items indicates one of the plurality of stored advertising data items. A system is disclosed for performing the method. A data structure is disclosed providing a functional and structural interrelationship between a processor in the system and data in the data structure.
摘要翻译：公开了一种用于呈现从视频数据流提取的广告数据的计算机化方法，所述方法包括：在最终用户设备处存储从视频数据流提取的多个广告数据项; 以及在所述终端用户设备处显示多个排序广告指示符数据项，其中所述广告指示符数据项中的每一个指示所述多个存储的广告数据项中的一个。公开了一种用于执行该方法的系统。公开了提供系统中的处理器与数据结构中的数据之间的功能和结构相互关系的数据结构。

10. 发明申请

US20120022950A1 Systems and Methods for Targeted Advertising in Voicemail to Text Systems 审中-公开
标题翻译：语音邮件到文本系统中的目标广告系统和方法
公开(公告)号：US20120022950A1
公开(公告)日：2012-01-26
申请号：US12843836
申请日：2010-07-26
申请人： Mazin Gilbert , Narendra K. Gupta , Dan Melamed
发明人： Mazin Gilbert , Narendra K. Gupta , Dan Melamed
IPC分类号： G06Q30/00 , G06F17/27 , H04M11/00
CPC分类号： H04M3/53333 , G06Q30/0241 , G06Q30/0269 , G06Q30/0273
摘要： Systems and methods are provided for a voice message to text system supporting targeted advertisements. Voice messages received from users are converted to raw text messages that are normalized to insert proper punctuation and extract entity information. The normalized text and entity information are processed to extract concepts, such as critical phrases, from the normalized text. Extracted concepts are then matched to advertisements on an advertisement database having user selection criteria. Advertisements having selection criteria matching the extracted concepts are transmitted to the users, and the advertisers that placed the advertisements are charged fees for the advertisements. User profile information and user context information can additionally be used to select advertisements for transmission to users.
摘要翻译：系统和方法被提供用于支持目标广告的文本系统的语音消息。从用户接收的语音消息被转换为原始文本消息，其被标准化以插入适当的标点符号并提取实体信息。处理归一化的文本和实体信息以从标准化文本中提取概念，例如关键短语。然后将提取的概念与具有用户选择标准的广告数据库上的广告相匹配。将具有与所提取的概念相匹配的选择标准的广告传送给用户，并且放置广告的广告商对广告收取费用。用户简档信息和用户上下文信息可另外用于选择用于传输给用户的广告。

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