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

US20160350412A1 MULTIPLE ROUNDS OF RESULTS SUMMARIZATION FOR IMPROVED LATENCY AND RELEVANCE 审中-公开
标题翻译：结果改进的更新和相关性的综合结果的多个结果
公开(公告)号：US20160350412A1
公开(公告)日：2016-12-01
申请号：US14720964
申请日：2015-05-25
申请人： Microsoft Technology Licensing, LLC
发明人： Gianluca Donato , Ara Avanesyan , Aparna Rajaraman
IPC分类号： G06F17/30 , G06F17/24
CPC分类号： G06F17/30719 , G06F17/243 , G06F17/30654 , G06F17/30905
摘要： Architecture that splits the generation of results summaries into at least two phases for reduced latency and improved relevance. A first phase generates a summary quickly and thereby enables subsequent modules to begin processing. A second round then executes in parallel to these other modules to offset the latency. The second round can also provide additional contextual information to the summarization module to improve the quality (relevance) of the summaries. Ultimately, the summaries generated in the two phases are merged. The multiple rounds of summarization enable the first round to be cheaper in processing resources to save overall latency, whereas the second phase can be more expensive, since the second phase can be run in parallel with other modules. Additionally, contextual information can be used to build the full content summaries in the second round.
摘要翻译：将结果摘要分解为至少两个阶段的架构，以减少延迟和改进的相关性。第一阶段快速生成摘要，从而使后续模块能够开始处理。然后第二轮并行执行这些其他模块以抵消延迟。第二轮还可以向摘要模块提供附加的上下文信息，以提高摘要的质量（相关性）。最终，两个阶段产生的摘要合并。多轮总结使得第一轮在处理资源方面更便宜以节省总体延迟，而第二阶段可能更昂贵，因为第二阶段可以与其他模块并行运行。此外，上下文信息可用于在第二轮中构建完整的内容摘要。

2. 发明授权

US10296644B2 Salient terms and entities for caption generation and presentation 有权
公开(公告)号：US10296644B2
公开(公告)日：2019-05-21
申请号：US15070989
申请日：2016-03-15
申请人： Microsoft Technology Licensing, LLC
发明人： Yiping Zhou , Gianluca Donato , Aparna Rajaraman , Oana Nicolov
IPC分类号： G06F7/00 , G06F17/30
摘要： Architecture that enables the extraction of document-specific salient terms from documents for use improving the result summaries on a search engine result page (SERP), and methods to extract the salient terms from the documents using search engine logs, document metadata, and other algorithms. Document-specific salient terms can provide additional information and significantly improve user success in finding relevant documents while disregarding non-relevant documents. The architecture also enables the extraction of entity information from a variety of sources, some of which are at a query level, and other sources that are specific to a single document. All the entities available are aggregated for a set of results and the most relevant results are identified. The final set of results is then used to determine where in the document summary to apply visual emphasis or cues (e.g., bolding).

3. 发明授权

US10095783B2 Multiple rounds of results summarization for improved latency and relevance 有权
公开(公告)号：US10095783B2
公开(公告)日：2018-10-09
申请号：US14720964
申请日：2015-05-25
申请人： Microsoft Technology Licensing, LLC
发明人： Gianluca Donato , Ara Avanesyan , Aparna Rajaraman
IPC分类号： G06F17/30 , G06F17/24
摘要： Architecture that splits the generation of results summaries into at least two phases for reduced latency and improved relevance. A first phase generates a summary quickly and thereby enables subsequent modules to begin processing. A second round then executes in parallel to these other modules to offset the latency. The second round can also provide additional contextual information to the summarization module to improve the quality (relevance) of the summaries. Ultimately, the summaries generated in the two phases are merged. The multiple rounds of summarization enable the first round to be cheaper in processing resources to save overall latency, whereas the second phase can be more expensive, since the second phase can be run in parallel with other modules. Additionally, contextual information can be used to build the full content summaries in the second round.

4. 发明申请

US20160283593A1 SALIENT TERMS AND ENTITIES FOR CAPTION GENERATION AND PRESENTATION 审中-公开
标题翻译：声明条款和表达生成和陈述的实体
公开(公告)号：US20160283593A1
公开(公告)日：2016-09-29
申请号：US15070989
申请日：2016-03-15
申请人： Microsoft Technology Licensing, LLC
发明人： Yiping Zhou , Gianluca Donato , Aparna Rajaraman , Oana Nicolov
IPC分类号： G06F17/30
CPC分类号： G06F17/30864 , G06F17/30401
摘要： Architecture that enables the extraction of document-specific salient terms from documents for use improving the result summaries on a search engine result page (SERP), and methods to extract the salient terms from the documents using search engine logs, document metadata, and other algorithms. Document-specific salient terms can provide additional information and significantly improve user success in finding relevant documents while disregarding non-relevant documents. The architecture also enables the extraction of entity information from a variety of sources, some of which are at a query level, and other sources that are specific to a single document. All the entities available are aggregated for a set of results and the most relevant results are identified. The final set of results is then used to determine where in the document summary to apply visual emphasis or cues (e.g., bolding).
摘要翻译：能够从搜索引擎结果页（SERP）中提取结果摘要的文档中提取特定于文档的突出术语的体系结构，以及使用搜索引擎日志，文档元数据和其他算法从文档中提取显着项的方法。特定于文档的突出术语可以提供更多的信息，并显着提高用户在查找相关文档时的成功，同时忽略不相关的文档。该体系结构还能够从各种来源（其中一些来自查询级别）以及特定于单个文档的其他来源提取实体信息。所有可用的实体将汇总一组结果，并确定最相关的结果。然后，最后一组结果用于确定文档摘要中的哪里应用视觉强调或提示（例如粗体）。

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