公开(公告)号：EP3155542A1

公开(公告)日：2017-04-19

申请号：EP14894449.9

申请日：2014-06-11

申请人： Hewlett-Packard Development Company, L.P.

发明人： SIMSKE, Steven J ,  VANS, Marie ,  STURGILL, Malgorzata M ,  HURLEY, Julie E

IPC分类号： G06F19/00 ,  G06F9/44

CPC分类号： G06F17/30719 ,  G06F17/2725 ,  G06F17/277 ,  G06F17/30707 ,  G06F17/30997 ,  G16H50/70

摘要： Functional summarization of non-textual content based on a meta-algorithmic pattern is disclosed. One example is a system including a converter, a plurality of summarization engines and/or meta-algorithmic patterns, an extractor, and an evaluator. The converter converts the non-textual content into a plurality of tokens. Combinations of summarization engines and/or meta-algorithm patterns are applied to the plurality of tokens to provide a meta-summary. The extractor extracts at least one summarization term from the meta-summary, and at least one class term for each given class of a plurality of classes of non-textual content. The evaluator determines similarity values of the non-textual content over each given class, each similarity value indicative of a similarity between the at least one summarization term and the at least one class term for each given class. The selector selects a class of the plurality of classes, the selecting based on the determined similarity values.

摘要翻译： 公开了基于元算法模式的非文本内容的功能概括。 一个示例是包括转换器，多个汇总引擎和/或元算法模式的系统，提取器和评估器。 转换器将非文本内容转换为多个令牌。 汇总引擎和/或元算法模式的组合被应用于多个令牌以提供元总结。 提取器从元总结中提取至少一个摘要术语，以及至少一个类术语，用于多个类别的非文本内容的每个给定类别。 评估者确定每个给定类别上的非文本内容的相似度值，每个相似性值指示至少一个汇总项和每个给定类的至少一个类项之间的相似度。 选择器选择多个类别的类别，基于所确定的相似度值进行选择。

公开(公告)号：EP3147801A1

公开(公告)日：2017-03-29

申请号：EP16189693.1

申请日：2016-09-20

申请人： Northern Light Group, LLC

发明人： SEUSS, David C. ,  VOSKRESENSKIY, Anton

IPC分类号： G06F17/30

CPC分类号： G06F17/30675 ,  G06F17/30011 ,  G06F17/30719 ,  G06F17/30864

摘要： Systems and methods for generating concept-based search summaries from a plurality of documents are provided. In one embodiment, a system may include interfaces to receive information identifying a meaning taxonomy including a normalized term and a search query including search terms. The system may be configured to identify documents relating to the search terms and normalized terms and display a concept-based summary of the documents, the summary including a syntactic structure associated with the normalized terms and search terms. In another embodiment, a method includes receiving a meaning taxonomy including normalized terms and search terms, identifying at least one document including the search terms and syntactic structures associated with the normalized terms, and display a search summary including the search terms and syntactic structures.

摘要翻译： 提供了用于从多个文档生成基于概念的搜索摘要的系统和方法。 在一个实施例中，系统可以包括用于接收标识包括归一化术语和包括搜索项的搜索查询的含义分类的信息的接口。 系统可以被配置为识别与搜索项和归一化术语相关的文档，并且显示文档的基于概念的概要，该概括包括与归一化术语和搜索项相关联的句法结构。 在另一个实施例中，一种方法包括接收包括归一化术语和搜索项的含义分类，识别包括与归一化术语相关联的搜索项和句法结构的至少一个文档，并且显示包括搜索项和句法结构的搜索摘要。

公开(公告)号：EP0952533B1

公开(公告)日：2016-09-14

申请号：EP99105851.2

申请日：1999-03-23

申请人： Xerox Corporation

发明人： Grefenstette, Gregory T.

IPC分类号： G06F17/30

CPC分类号： G06F17/30719 ,  G10L13/00

公开(公告)号：EP3036923A2

公开(公告)日：2016-06-29

申请号：EP14837154.5

申请日：2014-08-22

申请人： Sensoriant, Inc.

发明人： Sensoriant, Inc.

IPC分类号： H04W4/02 ,  G01S19/01

CPC分类号： G06F17/30631 ,  G06F17/30241 ,  G06F17/30684 ,  G06F17/30719 ,  G06F17/30864 ,  G06F17/3087 ,  G06Q10/1093

摘要： A system and method is presented that extracts snippets form web pages according to specially designed logic. The extracted snippets might be made relevant to, i.e., indexed by, a location and time/day applicability. Such snippets may be thought of as apps or services that are defined only when a mobile terminal is in a pre-defined geographical area at a certain time and day (e.g., as defined by a calendar of events). Extracted snippets are stored and made searchable. Methods and a system are described to control the display of snippet search results. Snippets may be selected by user or by programmed logic and executed on the mobile terminal or in remote servers without the need to download the app or source code associated with the snippet.

摘要翻译： 提出的系统和方法做了提取物片段形成网页gemäß到专门设计的逻辑。 所提取的片段可能作出相关的，即通过，位置和时间/日期适用性索引。 网络片段可以被认为是应用程序或服务没有被定义，只有当移动终端在预先定义的地理区域在一定的时间和日期的（例如，通过事件的日历定义）。 提取的片段存储和可搜索。 方法和系统的描述，以控制搜索结果代码段的显示。 代码段可以通过用户或者由编程的逻辑来选择并且不需要下载与所述片段相关联的应用或源代码在移动终端上或在远程服务器上执行。

公开(公告)号：EP2315129A4

公开(公告)日：2016-06-15

申请号：EP09817577

申请日：2009-07-30

申请人： IBM

发明人： IKAWA YOHEI ,  TAKEUCHI HIRONORI ,  NEGISHI SHIHO

IPC分类号： G06F17/28 ,  G06F17/21 ,  G06F17/27 ,  G06F17/30

CPC分类号： G06F17/28 ,  G06F17/277 ,  G06F17/30719

公开(公告)号：EP3021239A2

公开(公告)日：2016-05-18

申请号：EP15194788.4

申请日：2015-11-16

申请人： Samsung Electronics Co., Ltd.

发明人： PARK, Kyung-su ,  JO, Eun-kyoung ,  RYU, Hee-seob ,  LEE, Dong-jin

IPC分类号： G06F17/30

CPC分类号： G06F17/30719 ,  G06F17/27 ,  G06F17/30657

摘要： A display apparatus including a communicator configured to perform data communication with a content server and to receive at least one of a main document and a sub document related to the main document; a document analyzer configured to extract a keyword having a high frequency of occurrence from the main document and to determine a head keyword for generating a summarized document from the extracted keyword with reference to the received sub document; and a processor configured to determine a reliability of each sentence of the main document based on the head keyword, extract a sentence that matches a predetermined condition with reference to the determined reliability, and analyze a structural format of the extracted sentence so as to re-configure a word that forms the sentence and generate a summarized sentence, thereby generating a summarized document where information and logical cohesion have been obtained.

摘要翻译： 一种显示装置，包括通信器，被配置为执行与内容服务器的数据通信并且接收与所述主文档相关的主文档和子文档中的至少一个; 文档分析器，其被配置为从主文档中提取具有高频率出现的关键字，并且根据所接收的子文档从所提取的关键字中确定用于生成汇总文档的头关键字; 以及处理器，被配置为基于头部关键词确定主文档的每个句子的可靠性，参考所确定的可靠性提取与预定条件匹配的句子，并且分析所提取的句子的结构格式， 配置形成句子的单词并生成一个汇总句子，从而生成一个已经获得信息和逻辑内聚的总结文档。

公开(公告)号：EP2918047A4

公开(公告)日：2016-04-20

申请号：EP12887963

申请日：2012-11-06

申请人： HEWLETT PACKARD DEVELOPMENT CO

发明人： KELLY TERENCE P

IPC分类号： H04L12/24 ,  H04L12/28

CPC分类号： G06F17/30705 ,  G06F17/30719 ,  H04L41/12

公开(公告)号：EP2988231A1

公开(公告)日：2016-02-24

申请号：EP15181988.5

申请日：2015-08-21

申请人： Samsung Electronics Co., Ltd.

发明人： SATHISH, Sailesh ,  PATANKAR, Anish ,  NEEMA, Nirmesh

IPC分类号： G06F17/30

CPC分类号： G06F17/2241 ,  G06F17/24 ,  G06F17/2785 ,  G06F17/30719

摘要： A method of displaying summarized content by an electronic device includes: performing a text analysis on first content accessed by a user to acquire a plurality of subject words; displaying the acquired plurality of subject words; and displaying second content corresponding to at least one of the acquired plurality of subject words based on an external input, wherein the second content is summarized content of the first content.

摘要翻译： 通过在电子设备总结显示内容的方法，包括：执行由用户访问的第一内容的文本分析来获取的对象字的多个; 显示的主题单词的获取的多个; 和显示第二内容对应于外部输入基于对主题单词的获取的多个中的至少一个，worin第二内容概括第一内容的内容。

公开(公告)号：EP2836986A1

公开(公告)日：2015-02-18

申请号：EP12874222.8

申请日：2012-12-29

申请人： eBay Inc.

发明人： KAUSHAL, Govind ,  DANDEKAR, Jai ,  CHITTAR, Naren ,  KOPPAKA, Bhanu ,  SHEELEY, John ,  MACLAURIN, Matthew Bret

IPC分类号： G06T13/00

CPC分类号： H04N21/482 ,  G06F17/30023 ,  G06F17/30719 ,  G06F17/30864 ,  H04N21/472

摘要： Method and system to provide video-based search results are described. A search results video may be present to a user details from listings that match certain search criteria. When a select request associated with the search results video is detected, a listing rendering module presents the selected listing on the display device.

摘要翻译： 描述了提供基于视频的搜索结果的方法和系统。 搜索结果视频可以呈现给来自符合特定搜索标准的列表的用户细节。 当检测到与搜索结果视频相关联的选择请求时，列表呈现模块在显示设备上呈现所选列表。

公开(公告)号：EP2668592A2

公开(公告)日：2013-12-04

申请号：EP11856929.2

申请日：2011-12-21

申请人： Intel Corporation

发明人： LYONS, Kenton M. ,  ROSARIO, Barbara ,  PERING, Trevor ,  WANT, Roy

IPC分类号： G06F17/20 ,  G06F9/44

CPC分类号： G06F17/30719

摘要： Methods and systems to summarize a source text as a function of contextual information, including to fit a summary within a context-based allotted time. The context-based allotted time may be apportioned amongst multiple portions of the source text, such as by relevance. The context-based allotted time and/or relevance may be user-specified and/or determined, such as by look-up, rule, computation, inference, and/or machine learning. During summary presentation, one or more portions of the source text may be re-summarized, such as to adjust a level of detail. A presentation rate may be user-controllable. Where new and/or changed contextual information affects an available time to review a remaining portion of the summary, the summary presentation may be automatically adjusted, and/or one or more portions of the source text may be re-summarized based on a revised context-based allotted time.