公开(公告)号：EP0597630A1

公开(公告)日：1994-05-18

申请号：EP93308829.6

申请日：1993-11-04

申请人： CONQUEST SOFTWARE INC.

发明人： Addison,Edwin R. Conquest Software Inc. ,  Blair,Arden S. Conquest Software Inc. ,  Nelson,Paul E. Conquest Software Inc. ,  Schwartz,Thomas Conquest Software Inc.

IPC分类号： G06F15/403 ,  G06F15/20

CPC分类号： G06F17/30663 ,  G06F17/274 ,  G06F17/30684 ,  G06F17/30719 ,  G06F17/30737

摘要： The method of the present invention combines concept searching, document ranking, high speed and efficiency, browsing capabilities, "intelligent" hypertext, document routing, and summarization (machine abstracting) in an easy-to-use implementation. The method of the present invention also offers Boolean and statistical query options. The method of the present invention is based upon "concept indexing" (an index of "word senses" rather than just words.) It builds its concept index from a "semantic network" of word relationships with word definitions drawn from one or more standard human-language dictionaries. During query, users may select the meaning of a word from the dictionary during query construction, or may allow the method to disambiguate words based on semantic and statistical evidence of meaning. This results in a measurable improvement in precision and recall. Results of searching are retrieved and displayed in ranked order. The ranking process is more sophisticated than prior art systems providing ranking because it takes linguistics and concepts, as well as statistics into account.

摘要翻译： 本发明的方法将易于使用的实现中的概念搜索，文档排序，高速度，高效率，浏览功能，“智能”超文本，文档路由和摘要（机器抽象）相结合。 本发明的方法还提供布尔和统计查询选项。 本发明的方法是基于“概念索引”（“词义”而不是单词的指标）。它从与一个或多个标准所绘出的词定义的词关系的“语义网络”构建其概念索引 人类语言字典。 在查询期间，用户可以在查询构造期间从字典中选择一个单词的含义，也可以允许该方法根据意义上的语义和统计证据来消除歧义。 这导致精确度和召回的可测量的改善。 搜索结果按照排序顺序进行检索和显示。 排序过程比提供排名的现有技术系统更复杂，因为它需要语言学和概念以及统计数据。

公开(公告)号：EP0361464A3

公开(公告)日：1992-09-02

申请号：EP89117915.2

申请日：1989-09-28

申请人： KABUSHIKI KAISHA TOSHIBA

发明人： Doi, Miwako

IPC分类号： G06F15/401

CPC分类号： G06F17/30719 ,  G06F17/243

摘要： A method and an apparatus for producing an abstract of a document capable of producing concise abstract with correct meaning precisely indicative of the content of the document automatically. The method includes the steps of: listing hint words which are preselected words indicative of presence of significant phrases that can reflect content of the document; searching all the hint words in the document; extracting sentences of the document in which any one of the listed hint words is found by the search; and producing an abstract for the document by juxtaposing the extracted sentences. An apparatus for performing this method is also disclosed.

公开(公告)号：EP0361464A2

公开(公告)日：1990-04-04

申请号：EP89117915.2

申请日：1989-09-28

申请人： KABUSHIKI KAISHA TOSHIBA

发明人： Doi, Miwako

IPC分类号： G06F15/401

CPC分类号： G06F17/30719 ,  G06F17/243

摘要： A method and an apparatus for producing an abstract of a document capable of producing concise abstract with correct meaning precisely indicative of the content of the document automatically. The method includes the steps of: listing hint words which are preselected words indicative of presence of significant phrases that can reflect content of the document; searching all the hint words in the document; extracting sentences of the document in which any one of the listed hint words is found by the search; and producing an abstract for the document by juxtaposing the extracted sentences. An apparatus for performing this method is also disclosed.

摘要翻译： 一种用于生成能够产生具有正确意义的精简抽象的文档的摘要的方法和装置，其自动精确地指示文档的内容。 该方法包括以下步骤：列出作为预示单词的提示词，该单词指示能够反映文档内容的重要短语的存在; 搜索文档中的所有提示词; 提取通过搜索找到列出的提示词中的任何一个的文档的句子; 并通过并列提取的句子来生成文档的摘要。 还公开了一种用于执行该方法的装置。

公开(公告)号：EP0032194A1

公开(公告)日：1981-07-22

申请号：EP80107625.8

申请日：1980-12-04

申请人： International Business Machines Corporation

发明人： Glickman, David ,  Repass, James Terry ,  Rosenbaum, Walter Steven ,  Russel, Janet Goodson

IPC分类号： G06F15/40

CPC分类号： G06F17/2785 ,  G06F17/2765 ,  G06F17/279 ,  G06F17/30678 ,  G06F17/30719 ,  Y10S707/99935

摘要： Method for automatically abstracting a document in machine readable form consisting in storing in a dictionary memory (8) language terms commonly used in document preparation, comparing language terms from an input document received from an input register (16) with the stored language terms, selecting language terms from input document which do not compare, selecting language terms from input document which compare, coding the selecting language terms with the identity of the input document and storing the language terms in memory (12). When retrieving a document from storage, the processor (10) under the control of instruction memory (14) compares the words in an input query against the word index file in memory (12) and provides in register (18) the selected documents whose identification code corresponds to the highest retrieval value calculated using each identification code of each language term that compares.

摘要翻译： 用于自动提取机器可读形式在一字典存储器存放由文档方法在文件的准备（8）语言术语常用，从在输入文档比较语言术语从在输入寄存器（16）与所存储的语言术语接收，选择 从输入文件，它不比较，选择从输入文档的语言哪个方面比较，与输入文档的身份编码选择语言术语和储存在内存中（12）语言方面的语言条件。 从存储设备检索一个文档时，指令存储器的控制（14）下的处理器（10）比较在以对在存储器（12）中的词索引文件输入查询的所述词和在寄存器提供（18）所选择的文件的其标识 码对应使用的每种语言期内的各个识别码计算的最高值检索做比较。

公开(公告)号：EP3283984A1

公开(公告)日：2018-02-21

申请号：EP16862610.9

申请日：2016-03-10

申请人： Hewlett Packard Enterprise Development LP

发明人： BHATTACHARYA, Suparna ,  VOIGT, Doug ,  MANNARSWAMY, Sandya

IPC分类号： G06F17/30

CPC分类号： G06F17/30598 ,  G06F17/30719

摘要： Relevance optimized representative content associated with a data storage system is disclosed. One example is a system including a data summarization module, a clustering module, and a representative content selection module. The data summarization module associates, via a processor, each data object in a storage system with a derived data object. The clustering module determines clusters of similar data objects based on a similarity between associated derived data objects, and selects a representative data object for each determined cluster. The representative content selection module selects representative content associated with the storage system, where the representative content is based on the data objects, the derived data objects, and the representative data objects, and relevance optimizes of the selected representative content to an analytics application.

公开(公告)号：EP2517156A4

公开(公告)日：2018-02-14

申请号：EP10840199

申请日：2010-12-23

申请人： MOODWIRE INC

发明人： DUONG-VAN MINH

IPC分类号： G06K9/72 ,  G06F17/30

CPC分类号： G06F17/2785 ,  G06F17/30719 ,  G06F17/30867

摘要： A system, computer readable storage medium storing instructions, and computer-implemented method for determining sentiment expressed in documents is disclosed. A document is received from a plurality of documents. A sentence in the document that includes at least one sentiment signature within a predetermined distance of at least one keyword from a list of keywords is identified, wherein the list of keywords is extracted from the plurality of documents and is filtered using a phase transition formula, and wherein the at least one sentiment signature corresponds to an expression of at least one sentiment in the sentence. At least one category corresponding to the at least one keyword of the sentence is determined, wherein the at least one category is included in a list of categories that is generated using the list of keywords. At least one sentiment corresponding to the at least one category is determined based on the at least one sentiment signature.

公开(公告)号：EP2668592A4

公开(公告)日：2018-01-24

申请号：EP11856929

申请日：2011-12-21

申请人： INTEL CORP

发明人： LYONS KENTON M ,  ROSARIO BARBARA ,  PERING TREVOR ,  WANT ROY

IPC分类号： G06F17/30 ,  G06F9/44 ,  G06F17/20

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.

公开(公告)号：EP3264350A1

公开(公告)日：2018-01-03

申请号：EP16177306.4

申请日：2016-06-30

申请人： Verint Systems UK Limited

发明人： Adams, Conor

IPC分类号： G06Q30/00

CPC分类号： H04M3/5191 ,  G06F17/30657 ,  G06F17/30719 ,  G06Q30/016 ,  G06Q50/26 ,  H04L67/02

摘要： In the field of government engagement management, for users of an employee desktop web client, it is now possible, within the web client application, to search and read articles and/or knowledge content that has been authored to external locations. Due to this integration to external, third-party applications, content and/or articles can be displayed to an agent on the employee desktop web client graphical user interface. Agents can enter free text into a specific search field and review the results in summary form, and then select an article in HTML format to progress the current interaction with the client. This functionality adds value to the agent experience and enables the agent to provide an improved service to the end client. Results may be filtered by the search engine as well. Moreover, this system and method improves the operation of the computer in that the computer running such a system in the past was not able to integrate in such a fashion in a web client format. This system and method also enables an agent to handle calls with the web client more efficiently, and allows agents on the web client to automatically classify.

摘要翻译： 在政府参与管理领域，对于员工桌面Web客户端的用户，现在可以在Web客户端应用程序内搜索并阅读已编写到外部位置的文章和/或知识内容。 由于与外部第三方应用程序的集成，内容和/或文章可以显示给员工桌面Web客户端图形用户界面上的代理。 代理可以将自由文本输入到特定的搜索字段中，并以摘要形式查看结果，然后选择HTML格式的文章以推进与客户端的当前交互。 此功能为代理体验增添了价值，并使代理能够为最终客户提供改进的服务。 结果也可能被搜索引擎过滤。 而且，该系统和方法改进了计算机的操作，因为在过去运行这种系统的计算机不能以这种方式以网络客户机格式集成。 该系统和方法还使代理能够更有效地处理与Web客户端的呼叫，并允许Web客户端上的代理自动分类。

公开(公告)号：EP3084713A4

公开(公告)日：2017-08-16

申请号：EP14872043

申请日：2014-11-19

申请人： GOOGLE INC

发明人： NAVRIDES CHRIS ,  TOKSOZ TUNA

IPC分类号： G06F17/30 ,  G06Q50/10

CPC分类号： G06F17/30719 ,  G06F17/278

摘要： An entity-based summary of an electronic book (e-book) is presented to a user of a client device. The e-book to be summarized is identified and multiple entities, e.g., characters, events and dates, referenced in the identified e-book are also identified. A computer server is adapted to determine a type of the e-book to be summarized and to identify one or more external data sources based on the determined type of the e-book, where an external data source provides information about entities in the identified e-book. Upon receiving a request for an entity-based summary of the e-book from the client device, the computer server is adapted to generate an entity-based summary of the e-book, which describes identified entities referenced in a range of the e-book specified in the request. The generated entity-based summary is presented to the client device responsive to the request.

摘要翻译： 将电子书（电子书）的基于实体的摘要呈现给客户端设备的用户。 识别待总结的电子书，并识别在所识别的电子书中引用的多个实体，例如字符，事件和日期。 计算机服务器适用于确定要汇总的电子书的类型，并且基于所确定的电子书的类型来识别一个或多个外部数据源，其中外部数据源提供关于所识别的电子书中的实体的信息 -书。 在从客户端设备接收到对基于实体的电子书摘要的请求时，计算机服务器适于生成电子书的基于实体的摘要，其描述了在电子书的范围内引用的被识别的实体， 在请求中指定的书。 生成的基于实体的摘要响应于请求被呈现给客户端设备。

公开(公告)号：EP3069265A4

公开(公告)日：2017-05-24

申请号：EP14805752

申请日：2014-11-12

申请人： GETGO INC

发明人： THAPLIYAL ASHISH V

IPC分类号： G06Q10/10 ,  G06F17/00 ,  G06F17/30

CPC分类号： G06F17/30598 ,  G06F17/30719 ,  G06Q10/10