公开(公告)号：US09015172B2

公开(公告)日：2015-04-21

申请号：US13524178

申请日：2012-06-15

申请人： Jonathan Thompson ,  Vijay Chemburkar ,  David Bargeron ,  Soam Acharya

发明人： Jonathan Thompson ,  Vijay Chemburkar ,  David Bargeron ,  Soam Acharya

IPC分类号： G06F17/30 ,  G06K9/54

CPC分类号： G06F17/30852 ,  G06F17/30666 ,  G06F17/30734 ,  G06F17/30796 ,  G06F17/30817

摘要： Various embodiments of the present invention include concept-service components of content-search-service systems which employ ontologies and vocabularies prepared for particular categories of content at particular times in order to score transcripts prepared from content items to enable a search-service component of a content-search-service system to assign estimates of the relatedness of portions of a content item to search criteria in order to render search results to clients of the content-search-service system. The concept-service component processes a search request to generate lists of related terms, and then employs the lists of related terms to process transcripts in order to score transcripts based on information contained in the ontologies.

摘要翻译： 本发明的各种实施例包括内容搜索服务系统的概念服务组件，其在特定时间采用为特定类别的内容准备的本体和词汇，以便从内容项目中分配准备的记录，以使搜索服务组件能够 内容搜索服务系统来分配内容项目的部分的相关性的估计以搜索标准，以便将搜索结果呈现给内容搜索服务系统的客户端。 概念服务组件处理搜索请求以生成相关术语列表，然后使用相关术语列表来处理成绩单，以便根据本体中包含的信息来评分成绩单。

公开(公告)号：US20130060784A1

公开(公告)日：2013-03-07

申请号：US13245855

申请日：2011-09-26

申请人： Soam Acharya ,  David Bargeron ,  Vijay Chemburkar ,  Jonathan Thompson

发明人： Soam Acharya ,  David Bargeron ,  Vijay Chemburkar ,  Jonathan Thompson

IPC分类号： G06F17/30

CPC分类号： G06F16/739 ,  G06F16/7844

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

摘要翻译： 描述用于生成视频文件的自动标签的技术。 所述方法包括：至少部分地基于所述一个或多个手动输入的标签接收与视频文件相关联的一个或多个手动生成的标签，确定所述视频文件的初步类别，以及基于所述初步类别，生成目标记录 的视频文件，其中所述目标文本记录包括多个单词。 该方法还包括基于目标抄本生成多个单词的本体，基于多个评分因子对本体中的多个单词进行排序，并且基于多个单词的排序，生成一个或多个自动化 与视频文件相关联的标签。

公开(公告)号：US20130013305A1

公开(公告)日：2013-01-10

申请号：US13524178

申请日：2012-06-15

申请人： Jonathan Thompson ,  Vijay Chemburkar ,  David Bargeron ,  Soam Acharya

发明人： Jonathan Thompson ,  Vijay Chemburkar ,  David Bargeron ,  Soam Acharya

IPC分类号： G10L15/26

CPC分类号： G06F17/30852 ,  G06F17/30666 ,  G06F17/30734 ,  G06F17/30796 ,  G06F17/30817

摘要： Various embodiments of the present invention include concept-service components of content-search-service systems which employ ontologies and vocabularies prepared for particular categories of content at particular times in order to score transcripts prepared from content items to enable a search-service component of a content-search-service system to assign estimates of the relatedness of portions of a content item to search criteria in order to render search results to clients of the content-search-service system. The concept-service component processes a search request to generate lists of related terms, and then employs the lists of related terms to process transcripts in order to score transcripts based on information contained in the ontologies.

摘要翻译： 本发明的各种实施例包括内容搜索服务系统的概念服务组件，其在特定时间采用为特定类别的内容准备的本体和词汇，以便从内容项目中分配准备的记录，以使搜索服务组件能够 内容搜索服务系统来分配内容项目的部分的相关性的估计以搜索标准，以便将搜索结果呈现给内容搜索服务系统的客户端。 概念服务组件处理搜索请求以生成相关术语列表，然后使用相关术语列表来处理成绩单，以便根据本体中包含的信息来评分成绩单。

公开(公告)号：US08396878B2

公开(公告)日：2013-03-12

申请号：US13245840

申请日：2011-09-26

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： G06F17/30 ,  G10L15/26 ,  H04N7/18

CPC分类号： G06F17/3053 ,  G06F17/30796 ,  G06F17/30817 ,  G06F17/30843

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

公开(公告)号：US20120278337A1

公开(公告)日：2012-11-01

申请号：US13245840

申请日：2011-09-26

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： G06F17/30

CPC分类号： G06F17/3053 ,  G06F17/30796 ,  G06F17/30817 ,  G06F17/30843

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

摘要翻译： 描述用于生成视频文件的自动标签的技术。 所述方法包括：至少部分地基于所述一个或多个手动输入的标签接收与视频文件相关联的一个或多个手动生成的标签，确定所述视频文件的初步类别，以及基于所述初步类别，生成目标记录 的视频文件，其中所述目标文本记录包括多个单词。 该方法还包括基于目标抄本生成多个单词的本体，基于多个评分因子对本体中的多个单词进行排序，并且基于多个单词的排序，生成一个或多个自动化 与视频文件相关联的标签。

公开(公告)号：US08214374B1

公开(公告)日：2012-07-03

申请号：US13245843

申请日：2011-09-26

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： G06F17/30

CPC分类号： G06F17/30787

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

摘要翻译： 描述用于生成视频文件的自动标签的技术。 所述方法包括：至少部分地基于所述一个或多个手动输入的标签接收与视频文件相关联的一个或多个手动生成的标签，确定所述视频文件的初步类别，以及基于所述初步类别，生成目标记录 的视频文件，其中所述目标文本记录包括多个单词。 该方法还包括基于目标抄本生成多个单词的本体，基于多个评分因子对本体中的多个单词进行排序，并且基于多个单词的排序，生成一个或多个自动化 与视频文件相关联的标签。

公开(公告)号：US07783623B2

公开(公告)日：2010-08-24

申请号：US11848973

申请日：2007-08-31

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： G06F17/30

CPC分类号： G06F17/30758 ,  G06F17/30749 ,  G06F17/30761 ,  G06F17/30772

摘要： A system and method, operable by a processor running on a computing device and stored on a tangible computer readable medium, the system and method creating continuous, fixed duration, fixed size, or other such playlists for use on an individual listener's portable music player, as a programming guide for an Internet radio station, or the like. Information can be drawn from a number of recommendation sources to help generate such playlists based on a dictionary of terms. Recommendation sources are sources available via the internet or other published information that identify the order in which songs are presented or played, and which may be aggregated and processed into song sequence data that allows the instant system and method to utilize the experience, effort and musical expertise of others to generate a continuous playlist. Exemplary recommendation sources include, but are not limited to, published Disc Jockey (“DJ”) playlists, radio (terrestrial, satellite or internet) station websites from which playlists can be extracted or derived, individual listener playlists, or the like.

摘要翻译： 一种由运行在计算设备上并存储在有形计算机可读介质上的处理器操作的系统和方法，所述系统和方法创建连续，固定持续时间，固定大小或其他此类播放列表，以在单个听众的便携式音乐播放器上使用， 作为互联网广播电台的节目指南等。 可以从许多推荐来源获取信息，以帮助根据术语词典生成这样的播放列表。 推荐来源是通过互联网获得的来源或其他已发布的信息，其中标识了歌曲呈现或播放的顺序，并且其可被聚合和处理成歌曲序列数据，其允许即时系统和方法利用体验，努力和音乐 其他人的专业知识来生成连续播放列表。 示例性的推荐来源包括但不限于公开的唱片骑师（“DJ”）播放列表，可从中提取或导出播放列表的无线电（地面，卫星或互联网）站点网站，个人收听者播放列表等。

公开(公告)号：US08098976B1

公开(公告)日：2012-01-17

申请号：US13245850

申请日：2011-09-26

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： H04N9/80 ,  H04N5/93

CPC分类号： H04N21/84 ,  G06F17/30796 ,  G06F17/3082 ,  H04N21/4756 ,  H04N21/6582 ,  H04N21/8456

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

公开(公告)号：US08213767B1

公开(公告)日：2012-07-03

申请号：US13312373

申请日：2011-12-06

申请人： Soam Acharya

发明人： Soam Acharya

IPC分类号： H04N9/80 ,  H04N5/93

CPC分类号： H04N21/84 ,  G06F17/30796 ,  G06F17/3082 ,  H04N21/4756 ,  H04N21/6582 ,  H04N21/8456

摘要： Techniques for generating automated tags for a video file are described. The method includes receiving one or more manually generated tags associated with a video file, based at least in part on the one or more manually entered tags, determining a preliminary category for the video file, and based on the preliminary category, generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words. The method further includes generating an ontology of the plurality of words based on the targeted transcript, ranking the plurality of words in the ontology based on a plurality of scoring factors, and based on the ranking of the plurality of words, generating one or more automated tags associated with the video file.

摘要翻译： 描述用于生成视频文件的自动标签的技术。 所述方法包括：至少部分地基于所述一个或多个手动输入的标签接收与视频文件相关联的一个或多个手动生成的标签，确定所述视频文件的初步类别，以及基于所述初步类别，生成目标记录 的视频文件，其中所述目标文本记录包括多个单词。 该方法还包括基于目标抄本生成多个单词的本体，基于多个评分因子对本体中的多个单词进行排序，并且基于多个单词的排序，生成一个或多个自动化 与视频文件相关联的标签。

公开(公告)号：US20090171728A1

公开(公告)日：2009-07-02

申请号：US11965002

申请日：2007-12-27

申请人： Tak W. Yan ,  Prabhakar Krishnamurthy ,  Ketan Deshpande ,  Chih-Chao Chang ,  Soam Acharya

发明人： Tak W. Yan ,  Prabhakar Krishnamurthy ,  Ketan Deshpande ,  Chih-Chao Chang ,  Soam Acharya

IPC分类号： G06Q10/00 ,  G06F17/30 ,  G06Q30/00

CPC分类号： G06Q30/02 ,  G06F16/951 ,  G06Q30/0249 ,  G06Q30/0256 ,  G06Q30/0275 ,  G06Q40/12

摘要： The present invention provides a method and apparatus for sponsored Internet-based search simulation. The present invention includes receiving a search query sequence that represents a search query and selecting one or more advertisements based on the search query sequence. The present invention further includes filtering the plurality of advertisements based on advertising budget data and determining a number of user-selections on the advertisements using a pre-calculated user-selection model. The present invention further includes updating advertiser account information regarding advertising rates in response to the number of user-selections and generating simulation log data reflecting the advertisings, user-selections and advertising account information. This technique thereby performs the simulation based on user search queries, in response to user-selection models and references the user-selection and advertisement with advertisement budget data, consistent with live sponsored search result operations.

摘要翻译： 本发明提供了一种用于赞助的基于因特网的搜索模拟的方法和装置。 本发明包括接收表示搜索查询并基于搜索查询序列选择一个或多个广告的搜索查询序列。 本发明还包括基于广告预算数据来过滤多个广告，并且使用预先计算的用户选择模型来确定广告上的用户选择数量。 本发明还包括响应于用户选择的数量更新关于广告费用的广告商帐户信息，并且生成反映广告，用户选择和广告账户信息的模拟日志数据。 该技术由此基于用户搜索查询进行仿真，响应于用户选择模型，并根据实况赞助的搜索结果操作参考用户选择和广告与广告预算数据。