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

US20140040272A1 Disambiguation and Tagging of Entities 有权
标题翻译：消除歧视和实体标签
公开(公告)号：US20140040272A1
公开(公告)日：2014-02-06
申请号：US14012289
申请日：2013-08-28
申请人： David F. Houghton
发明人： David F. Houghton
IPC分类号： G06F17/30
CPC分类号： G06F17/30598 , G06F17/241 , G06F17/277 , G06F17/2775 , G06F17/278 , G06F17/2785
摘要： Tagging of content items and entities identified therein may include a matching process, a classification process and a disambiguation process. Matching may include the identification of potential matching candidate entities in a content item whereas the classification process may categorize or group identified candidate entities according to known entities to which they are likely a match. In some instances, a candidate entity may be categorized with multiple known entities. Accordingly, a disambiguation process may be used to reduce the potential matches to a single known entity. In one example, the disambiguation process may include ranking potentially matching known entities according to a hierarchy of criteria.
摘要翻译：在其中识别的内容项目和实体的标签可以包括匹配过程，分类过程和消歧过程。匹配可以包括在内容项目中潜在的匹配候选实体的识别，而分类过程可以根据它们可能匹配的已知实体对所标识的候选实体进行分类或分组。在某些情况下，候选实体可以被分类为多个已知实体。因此，可以使用消歧过程来减少与单个已知实体的潜在匹配。在一个示例中，消歧过程可以包括根据标准的层级来潜在地匹配已知实体。

2. 发明申请

US20100293195A1 Disambiguation and Tagging of Entities 有权
标题翻译：消除歧视和实体标签
公开(公告)号：US20100293195A1
公开(公告)日：2010-11-18
申请号：US12464392
申请日：2009-05-12
申请人： David F. Houghton
发明人： David F. Houghton
IPC分类号： G06F17/30
CPC分类号： G06F17/30598 , G06F17/241 , G06F17/277 , G06F17/2775 , G06F17/278 , G06F17/2785
摘要： Tagging of content items and entities identified therein may include a matching process, a classification process and a disambiguation process. Matching may include the identification of potential matching candidate entities in a content item whereas the classification process may categorize or group identified candidate entities according to known entities to which they are likely a match. In some instances, a candidate entity may be categorized with multiple known entities. Accordingly, a disambiguation process may be used to reduce the potential matches to a single known entity. In one example, the disambiguation process may include ranking potentially matching known entities according to a hierarchy of criteria.
摘要翻译：在其中识别的内容项目和实体的标签可以包括匹配过程，分类过程和消歧过程。匹配可以包括在内容项目中潜在的匹配候选实体的识别，而分类过程可以根据它们可能匹配的已知实体对所标识的候选实体进行分类或分组。在某些情况下，候选实体可以被分类为多个已知实体。因此，可以使用消歧过程来减少与单个已知实体的潜在匹配。在一个示例中，消歧过程可以包括根据标准的层级来潜在地匹配已知实体。

3. 发明授权

US09442933B2 Identification of segments within audio, video, and multimedia items 有权
标题翻译：识别音频，视频和多媒体项目中的段
公开(公告)号：US09442933B2
公开(公告)日：2016-09-13
申请号：US12343779
申请日：2008-12-24
申请人： Evelyne Tzoukermann , Leslie Eugene Chipman , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
发明人： Evelyne Tzoukermann , Leslie Eugene Chipman , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
IPC分类号： H04N9/80 , G06F17/30
CPC分类号： G06F17/30038
摘要： The invention pertains to methods, systems, and apparatus for identifying segments within a media item, the media segment including at least one of audio content and video content, comprising segmenting the media item into a plurality of segments as a function of subject matter, storing data identifying each segment and its subject matter, and organizing each segment within an ontology based on its subject matter.
摘要翻译：本发明涉及用于识别媒体项目内的片段的方法，系统和装置，所述媒体片段包括音频内容和视频内容中的至少一个，包括根据主题将媒体项划分成多个片段，存储识别每个片段及其主题的数据，以及基于其主题来组织本体内的每个片段。

4. 发明授权

US08989499B2 Detection of transitions between text and non-text frames in a video stream 有权
标题翻译：检测视频流中文本和非文本帧之间的转换
公开(公告)号：US08989499B2
公开(公告)日：2015-03-24
申请号：US12908048
申请日：2010-10-20
申请人： Oliver Jojic , David F. Houghton
发明人： Oliver Jojic , David F. Houghton
IPC分类号： G06K9/46 , G06K9/34 , G06F3/00 , H04N9/80 , H04N5/14 , G11B27/034 , G06K9/32 , G11B27/036 , H04N5/76
CPC分类号： H04N5/445 , G06K9/3266 , G11B27/034 , G11B27/036 , H04N5/76 , H04N21/4316 , H04N21/4334 , H04N21/44008 , H04N21/4583 , H04N21/47214 , H04N21/488 , H04N21/812
摘要： Detecting the start of a credit roll within video program may allow for the automatic extension of video recordings among other functions. The start of the credit roll may be detected by determining the number of text blocks within a sequence of frames and identifying a point in the sequence of frames where a difference between the number of text blocks in frames occurring before the point and the number of text blocks in frames occurring after the point is greatest and exceeds a specified threshold. Text blocks may be identified within each frame by partitioning the frame into one or more segments and recording the segments having a pixel of a sufficiently high contrast. Contiguous segments may be merged or combined into single blocks, which may then be filtered to remove noise and false positives. Additional content may be inserted into the credit roll frames.
摘要翻译：检测视频节目内信用卷的开始可能允许视频录像的自动扩展等功能。可以通过确定帧序列内的文本块的数量来识别信用卷的开始，并且识别帧序列中的点之间的点与文本块之间出现的帧中的文本块的数量之间的差异点之后发生的帧最大并超过指定阈值。通过将帧划分成一个或多个段并记录具有足够高的对比度的像素的段，可以在每个帧内识别文本块。相邻的段可以被合并或组合成单个块，然后可以对其进行滤波以去除噪声和误报。附加内容可能会插入到信用信息框中。

5. 发明申请

US20100158470A1 IDENTIFICATION OF SEGMENTS WITHIN AUDIO, VIDEO, AND MULTIMEDIA ITEMS 有权
标题翻译：识别音频，视频和多媒体项目中的部分
公开(公告)号：US20100158470A1
公开(公告)日：2010-06-24
申请号：US12343779
申请日：2008-12-24
申请人： Evelyne TZOUKERMANN , Leslie Eugene CHIPMAN , Anthony R. DAVIS , David F. HOUGHTON , Ryan M. FARRELL , Hongzhong ZHOU , Oliver JOJIC , Vladimir KRONROD , Bageshree SHEVADE , Geetu Ambwani
发明人： Evelyne TZOUKERMANN , Leslie Eugene CHIPMAN , Anthony R. DAVIS , David F. HOUGHTON , Ryan M. FARRELL , Hongzhong ZHOU , Oliver JOJIC , Vladimir KRONROD , Bageshree SHEVADE , Geetu Ambwani
IPC分类号： H04N7/00
CPC分类号： G06F17/30038
摘要： The invention pertains to methods, systems, and apparatus for identifying segments within a media item, the media segment including at least one of audio content and video content, comprising segmenting the media item into a plurality of segments as a function of subject matter, storing data identifying each segment and its subject matter, and organizing each segment within an ontology based on its subject matter.
摘要翻译：本发明涉及用于识别媒体项目内的片段的方法，系统和装置，所述媒体片段包括音频内容和视频内容中的至少一个，包括根据主题将媒体项划分成多个片段，存储识别每个片段及其主题的数据，以及基于其主题来组织本体内的每个片段。

6. 发明授权

US08533223B2 Disambiguation and tagging of entities 有权
标题翻译：消除和标注实体
公开(公告)号：US08533223B2
公开(公告)日：2013-09-10
申请号：US12464392
申请日：2009-05-12
申请人： David F. Houghton
发明人： David F. Houghton
IPC分类号： G06F17/30
CPC分类号： G06F17/30598 , G06F17/241 , G06F17/277 , G06F17/2775 , G06F17/278 , G06F17/2785
摘要： Tagging of content items and entities identified therein may include a matching process, a classification process and a disambiguation process. Matching may include the identification of potential matching candidate entities in a content item whereas the classification process may categorize or group identified candidate entities according to known entities to which they are likely a match. In some instances, a candidate entity may be categorized with multiple known entities. Accordingly, a disambiguation process may be used to reduce the potential matches to a single known entity. In one example, the disambiguation process may include ranking potentially matching known entities according to a hierarchy of criteria.
摘要翻译：在其中识别的内容项目和实体的标签可以包括匹配过程，分类过程和消歧过程。匹配可以包括在内容项目中潜在的匹配候选实体的识别，而分类过程可以根据它们可能匹配的已知实体对所标识的候选实体进行分类或分组。在某些情况下，候选实体可以被分类为多个已知实体。因此，可以使用消歧过程来减少与单个已知实体的潜在匹配。在一个示例中，消歧过程可以包括根据标准的层级来潜在地匹配已知实体。

7. 发明申请

US20110004462A1 Generating Topic-Specific Language Models 有权
标题翻译：生成主题特定语言模型
公开(公告)号：US20110004462A1
公开(公告)日：2011-01-06
申请号：US12496081
申请日：2009-07-01
申请人： David F. Houghton , Seth Michael Murray , Sibley Verbeck Simon
发明人： David F. Houghton , Seth Michael Murray , Sibley Verbeck Simon
IPC分类号： G06F17/27 , G10L15/04 , G06F17/30
CPC分类号： G10L15/183
摘要： Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.
摘要翻译：可以通过生成和使用主题特定语言模型来改善语音识别。可以通过使用通用或基本语言模型对音频信号执行初始传递来创建主题特定语言模型。语音识别装置然后可以基于在初始通过中识别的单词来确定与音频信号相关的主题，并且检索与这些主题相关的文本语料库。使用检索的文本语料库，语音识别设备可以创建主题特定语言模型。在一个示例中，语音识别装置可以基于检索到的文本语料库来适应或以其他方式修改通用语言模型。

8. 发明申请

US20100161580A1 METHOD AND APPARATUS FOR ORGANIZING SEGMENTS OF MEDIA ASSETS AND DETERMINING RELEVANCE OF SEGMENTS TO A QUERY 有权
标题翻译：组织媒体资产部分的方法和装置，并确定部分与查询的相关性
公开(公告)号：US20100161580A1
公开(公告)日：2010-06-24
申请号：US12343790
申请日：2008-12-24
申请人： Leslie Eugene Chipman , Evelyne Tzoukermann , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
发明人： Leslie Eugene Chipman , Evelyne Tzoukermann , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
IPC分类号： G06F17/30
CPC分类号： G06F17/30058 , G06F17/30038 , G06F17/3005 , G06F17/3053
摘要： The invention pertains to methods, systems, and apparatus for identifying media items relevant to a selected subject matter, the method comprising determining the subject matter of a first media item, the first media item comprising at least one of audio content and video content, determining the classification within an ontology of the subject matter of the first media item, analyzing the ontology to identify other subject matter related to the subject matter of the first media item, and performing a search for other media items relevant to the subject matter of the first media item as a function of at least the other related subject matter according to the ontology.
摘要翻译：本发明涉及用于识别与所选主题相关的媒体项目的方法，系统和装置，该方法包括确定第一媒体项目的主题，第一媒体项包括音频内容和视频内容中的至少一个，确定在第一媒体项目的主题的本体内的分类，分析本体以识别与第一媒体项的主题相关的其他主题，以及执行与第一媒体项的主题相关的其他媒体项的搜索作为根据本体的至少另一相关主题的函数的媒体项目。

9. 发明授权

US09892730B2 Generating topic-specific language models 有权
公开(公告)号：US09892730B2
公开(公告)日：2018-02-13
申请号：US12496081
申请日：2009-07-01
申请人： David F. Houghton , Seth Michael Murray , Sibley Verbeck Simon
发明人： David F. Houghton , Seth Michael Murray , Sibley Verbeck Simon
IPC分类号： G10L15/183
CPC分类号： G10L15/183
摘要： Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.

10. 发明授权

US08713016B2 Method and apparatus for organizing segments of media assets and determining relevance of segments to a query 有权
标题翻译：用于组织媒体资产片段并确定片段与查询的相关性的方法和装置
公开(公告)号：US08713016B2
公开(公告)日：2014-04-29
申请号：US12343790
申请日：2008-12-24
申请人： Leslie Eugene Chipman , Evelyne Tzoukermann , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
发明人： Leslie Eugene Chipman , Evelyne Tzoukermann , Anthony R. Davis , David F. Houghton , Ryan M. Farrell , Hongzhong Zhou , Oliver Jojic , Vladimir Kronrod , Bageshree Shevade , Geetu Ambwani
IPC分类号： G06F17/30
CPC分类号： G06F17/30058 , G06F17/30038 , G06F17/3005 , G06F17/3053
摘要： The invention pertains to methods, systems, and apparatus for identifying media items relevant to a selected subject matter, the method comprising determining the subject matter of a first media item, the first media item comprising at least one of audio content and video content, determining the classification within an ontology of the subject matter of the first media item, analyzing the ontology to identify other subject matter related to the subject matter of the first media item, and performing a search for other media items relevant to the subject matter of the first media item as a function of at least the other related subject matter according to the ontology.
摘要翻译：本发明涉及用于识别与所选主题相关的媒体项目的方法，系统和装置，该方法包括确定第一媒体项目的主题，第一媒体项包括音频内容和视频内容中的至少一个，确定在第一媒体项目的主题的本体内的分类，分析本体以识别与第一媒体项的主题相关的其他主题，以及执行与第一媒体项的主题相关的其他媒体项的搜索作为根据本体的至少另一相关主题的函数的媒体项目。

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