公开(公告)号：WO2017145153A2

公开(公告)日：2017-08-31

申请号：PCT/IL2017/050222

申请日：2017-02-22

Applicant: ROTA, Arie

Inventor： ROTA, Arie

IPC: G06F17/30

CPC classification number: G06F17/30707 ,  G06F17/30625 ,  G06F17/30705 ,  G06F17/30734

Abstract: An accumulated information data store may include topic nodes, each having a text description of limited length and (in some cases) one or more attributes. A particular topic node may be associated as a parent topic node other child topic nodes such that the topic nodes form at least one data tree. An information processing engine may access information in the accumulated information data store and determine that a plurality of topic node text descriptions are similar and classify them as similar topic nodes. At least a part of the text description associated with one of the similar topic nodes may be selected as a favorable text description for the similar topic nodes. The system may also unify the similar topic nodes as identical topic nodes when they are currently grouped together as having the same upper tree hierarchy.

公开(公告)号：WO2017085548A1

公开(公告)日：2017-05-26

申请号：PCT/IB2016/001742

申请日：2016-11-15

Applicant: UCB BIOPHARMA SPRL

Inventor： HADDAD, Nassim ,  LIEUTENANT, Amaud ,  FILAIRE, Thomas

IPC: G06F17/30

CPC classification number: G16H40/63 ,  G06F3/04817 ,  G06F3/0482 ,  G06F3/04847 ,  G06F17/30392 ,  G06F17/30713 ,  G06F17/30734 ,  G06F19/00

Abstract: A computerized method for searching and organizing a healthcare textual data set is provided. The method includes receiving, by a server including a processor and a memory, an input of a user of a selected healthcare treatment product delimiting a subject data set; displaying, in response to the input subject data set received by the server, an intertopic distance map on a topic modeler graphical user interface displaying topics of the input subject data set as raw uncategorized data, the topic modeler graphical user interface displaying icons each representing a corresponding topic within the data set, the icons illustrating a prevalence of the topics in the data set by sizes of the icons and an interrelatedness of the topics by spacing and/or overlap of the icons; modifying, in response to a selection of one of the icons, a terms graph of the topic modeler graphical user interface to display representative keywords of the topic represented by the selected icon; receiving an input of a pattern in a taxonomy modifier graphical user interface generated by the server; displaying, in response to the input pattern, text of the data set corresponding to the input pattern on the taxonomy modifier graphical user interface; and adding, in response to a request of the user, the input pattern to one or more existing levels of a taxonomy of the data set to alter the structure of the taxonomy and provide a modified healthcare treatment taxonomy on the memory of the server.

Abstract translation: 提供了用于搜索和组织医疗文本数据集的计算机化方法。 该方法包括由包括处理器和存储器的服务器接收界定主题数据集的选定保健治疗产品的用户的输入; 响应于由服务器接收的输入对象数据集，在显示输入对象数据集的主题作为原始未分类数据的主题建模器图形用户界面上显示隐喻视距图，主题建模器图形用户界面显示各自代表 所述图标通过所述图标的大小以及所述主题之间的相互关系通过所述图标的间隔和/或重叠来示出所述数据集中的所述主题的普遍性; 响应于对所述图标之一的选择，修改所述主题建模器图形用户界面的术语图形以显示由所选图标表示的所述主题的代表性关键词; 接收由服务器生成的分类修饰符图形用户界面中的模式的输入; 响应于输入模式显示与分类修饰符图形用户界面上的输入模式对应的数据集的文本; 以及响应于用户的请求，将输入模式添加到数据集的分类法的一个或多个现有等级以改变分类法的结构并且在服务器的存储器上提供修改的医疗保健治疗分类法。 / p>

公开(公告)号：WO2016203230A1

公开(公告)日：2016-12-22

申请号：PCT/GB2016/051783

申请日：2016-06-15

Applicant: EREVALUE LIMITED

Inventor： LECOURT, Jean-Philippe ,  LECOURT-ALMA, Jeltje ,  BASDEVANT, Jerome

IPC: G06F17/30 ,  G06Q50/18 ,  G06Q50/26

CPC classification number: G06Q10/0637 ,  G06F17/3061 ,  G06F17/30613 ,  G06F17/30734 ,  G06Q10/06315 ,  G06Q10/0639 ,  G06Q50/18 ,  G06Q50/26 ,  H04L67/306

Abstract: The present invention relates to a computer-implemented method for locating regulatory information. The method including the steps of constructing a corporate profile; identifying regulatory information from a plurality of sources; and mapping the corporate profile to the identified regulatory information to locate relevant regulatory information. A system is also disclosed.

Abstract translation: 本发明涉及一种用于定位监管信息的计算机实现的方法。 该方法包括构建公司简档的步骤; 从多个来源识别管制信息; 并将公司简介映射到所识别的监管信息，以查找相关的监管信息。 还公开了一种系统。

公开(公告)号：WO2016185227A1

公开(公告)日：2016-11-24

申请号：PCT/GB2016/051473

申请日：2016-05-20

Applicant: KNOGNO LTD

Inventor： JONES, Simon ,  HAMPSON, John ,  COWARD, Martin ,  SKARDON, Christopher David

IPC: G06F17/30

CPC classification number: G06F17/30734 ,  G06F17/30312 ,  G06F17/30958 ,  G06F17/30961 ,  G06F17/30991

Abstract: The present invention relates to a computer-implemented method of defining an entity for a graph-based information system. The method includes the steps of receiving user input at one or more processors to create or select one of a plurality of options for a node in a graph; receiving user input at one or more processors to create or select one of a plurality of options for one or more child nodes in the graph; defining a value for the created/selected option for one of the child nodes at one or more processors in response to user input; and storing the value in at least one memory. The node and one or more child nodes are displayed within a user interface at a user device. A system for defining an entity for a graph-based information system is also disclosed.

Abstract translation: 本发明涉及一种定义用于基于图表的信息系统的实体的计算机实现的方法。 该方法包括以下步骤：在一个或多个处理器处接收用户输入以创建或选择图中的节点的多个选项之一; 在一个或多个处理器处接收用户输入以创建或选择所述图中的一个或多个子节点的多个选项之一; 响应于用户输入，为一个或多个处理器的子节点之一定义创建/选择的选项的值; 并将该值存储在至少一个存储器中。 节点和一个或多个子节点显示在用户设备的用户界面内。 还公开了一种用于定义基于图表的信息系统的实体的系统。

公开(公告)号：WO2016077016A1

公开(公告)日：2016-05-19

申请号：PCT/US2015/055490

申请日：2015-10-14

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： NAUZE, Fabrice ,  KISSIG, Christian ,  ZARAFIN, Madalina ,  VILLADA-MOIRON, Maria Begona ,  GENET, Roos

IPC: G06F17/30 ,  G06F17/27

CPC classification number: G06F17/277 ,  G06F17/27 ,  G06F17/2735 ,  G06F17/2755 ,  G06F17/2775 ,  G06F17/28 ,  G06F17/30731 ,  G06F17/30734

Abstract: A method of automatically generating a lemma dictionary from a web resource may include extracting a plurality of tokens from text-based documents within the web resource, and generating a plurality of N-grams from the plurality of tokens. The method may additionally include receiving one or more filter definitions that identify valid N-grams, and filtering the plurality of N-grams using the one or more filter definitions to generate a lemma dictionary. The method may further include generating an ontology that comprises the lemma dictionary.

Abstract translation: 从网页资源自动生成引文词典的方法可以包括从web资源内的基于文本的文档中提取多个令牌，以及从多个令牌生成多个N克。 该方法可以另外包括接收一个或多个识别有效N-gram的过滤器定义，以及使用一个或多个过滤器定义对多个N-gram进行过滤以生成词法辞典。 该方法还可以包括生成包含引文词典的本体。

公开(公告)号：WO2016045735A1

公开(公告)日：2016-03-31

申请号：PCT/EP2014/070522

申请日：2014-09-25

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： HUBAUER, Thomas ,  LAMPARTER, Steffen ,  ROSHCHIN, Mikhail ,  WALTINGER, Ulli

IPC: G05B19/042 ,  G06F17/30

CPC classification number: G05B19/042 ,  G05B2219/13023 ,  G06F17/3043 ,  G06F17/30734

Abstract: A configuration system and method adapted to perform a configuration or reconfiguration of applications run by an automation system, said configuration system comprising; a processing unit adapted to process at least one natural language statement of a user requirement input by a user concerning a control and/or monitoring functionality of the automation system based on a user ontology of the user and/or an automation system ontology of the automation system to generate a formal requirements specification; and a matching unit adapted to match the generated formal requirements specification and formal component specifications read from a component library to derive a configuration deployment comprising one or several suitable components with configurations fulfilling the input user requirement.

Abstract translation: 一种适于执行由自动化系统运行的应用的配置或重新配置的配置系统和方法，所述配置系统包括： 处理单元，其适于基于用户的用户本体和/或自动化的自动化系统本体来处理用户输入的关于自动化系统的控制和/或监视功能的用户需求的至少一个自然语言语句 系统生成正式的要求规范; 以及匹配单元，其适于匹配从组件库读取的所生成的形式要求规范和形式组件规范，从而导出包括具有满足输入用户需求的配置的一个或多个合适组件的配置部署。

公开(公告)号：WO2015175936A1

公开(公告)日：2015-11-19

申请号：PCT/US2015/031075

申请日：2015-05-15

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： AKBACAK, Murat ,  HAKKANI-TUR, Dilek Z. ,  TUR, Gokhan ,  HECK, Larry P. ,  DUMOULIN, Benoit

IPC: G06F17/30 ,  G10L15/06

CPC classification number: G10L15/18 ,  G06F17/30654 ,  G06F17/30734 ,  G06F17/30766 ,  G10L15/07

Abstract: Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.

Abstract translation: 提供了系统和方法，用于通过将语言模型所使用的知识源个性化为特定用户或用户群体特征来改进用于语音识别的语言模型。 通过将实体或用户操作与用户的使用历史（例如查询日志）映射到知识源，为特定用户个性化知识源。 个性化知识源可以用于通过训练具有对应于出现在使用历史中的实体或实体对的查询的语言模型来构建个人语言模型。 在一些实施例中，可以基于类似用户的个性化知识源来扩展用于特定用户的个性化知识源。

公开(公告)号：WO2015026485A3

公开(公告)日：2015-06-18

申请号：PCT/US2014048356

申请日：2014-07-28

Applicant: INTELLIGENT MEDICAL OBJECTS INC

Inventor： CHARLOT REGIS ,  NAEYMI-RAD FRANK ,  BODAL AZIZ ,  CARDWELL MATTHEW ,  OGANESOVA ALINA ,  YOUNG ANDRE ,  MASARIE FRED ,  ALVIN DAVID ,  HAINES DAVID ,  MALDONADO JOSE ,  KOBASHI MASAYO

IPC: G06F17/30 ,  G16H10/60

CPC classification number: G06F17/30554 ,  G06F17/30684 ,  G06F17/30734

Abstract: A system and method for searching and presenting data may include receiving a search request, storing data in an in memory database, accessing that data by one or more 64 bit processors, determining exact or approximate matches among the data to the search request, building a machine-readable data file including the search results, and serving the data file to a user's machine, where it is visible through a portal interface, which may be local or remotely served to the user's machine. The system may employ 64 bit technology in order to access and serve significant amounts of information, including mappings between code set and other data that may include mappings to one or more code sets. The system also may employ raw TCP/IP sockets to reduce latency and increase search speed.

Abstract translation: 用于搜索和呈现数据的系统和方法可以包括接收搜索请求，将数据存储在存储器数据库中，通过一个或多个64位处理器访问该数据，确定数据之间对搜索请求的准确或近似匹配，构建一个 包括搜索结果的机器可读数据文件，以及将数据文件提供给用户的机器，其中可通过门户界面看到该文件，其可以是本地的或远程地提供给用户的机器。 该系统可以采用64位技术来访问和服务大量的信息，包括代码集与可以包括到一个或多个代码集的映射的其他数据之间的映射。 该系统还可以使用原始TCP / IP套接字来减少延迟并提高搜索速度。

公开(公告)号：WO2014163857A1

公开(公告)日：2014-10-09

申请号：PCT/US2014/018165

申请日：2014-02-25

Applicant: NUANCE COMMUNICATIONS, INC.

Inventor： DELANEY, Brian, William ,  YEGNANARAYANAN, Girija

IPC: G06F17/27

CPC classification number: G06F17/30734 ,  G06F17/278 ,  G06F17/2785 ,  G06F19/00 ,  G16H10/60

Abstract: Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. The first and second concepts may be included in a set of features of the token. Based at least in part on the set of features of the token, a measure related to a likelihood that the at least a portion of the text string corresponds to a particular entity type may be determined.

Abstract translation: 用于实体检测的技术包括将文本串的至少一部分的令牌与本体中的匹配概念进行匹配。 可以将第一概念识别为与本体内的匹配概念分层相关，并且第二概念可以被识别为与本体内的第一概念分层相关。 第一和第二概念可以被包括在令牌的一组特征中。 至少部分地基于令牌的特征集合，可以确定与文本串的至少一部分对应于特定实体类型的可能性有关的度量。

公开(公告)号：WO2014123158A1

公开(公告)日：2014-08-14

申请号：PCT/JP2014/052685

申请日：2014-02-05

Applicant: 株式会社 東芝

Inventor： 細川　晃 ,  村山　廣

IPC: G06F17/30 ,  G06F9/44

CPC classification number: G06F17/30705 ,  G06F9/448 ,  G06F17/30292 ,  G06F17/30554 ,  G06F17/30607 ,  G06F17/30734

Abstract: ［課題］アプリケーションやツールに依存しない方法で、表示、出力および登録等のデータ制御を柔軟に行う。 ［解決手段］本発明の一態様としての情報処理装置は、データベースと、制御実行部とを備える。前記データベースは、メタクラスとして表現される任意のカテゴリーを指定した対象カテゴリーアトリビュートと、前記対象カテゴリーアトリビュートで指定されたカテゴリーで定義されるアトリビュートに対して行う制御を定めた制御アトリビュートとを定義した制御メタクラスのインスタンスを少なくとも１つ記憶する。前記制御実行部は、前記制御メタクラスのインスタンスに従って、前記対象カテゴリーアトリビュートで指定されるカテゴリーのアトリビュートに対して、前記制御アトリビュートで定められた制御を実行する。

Abstract translation: [问题]使用不依赖于应用程序或工具的方法来灵活地执行数据控制，如显示，输出和注册。 [解决方案]本发明的一个实施例的信息处理装置具有数据库和控制执行单元。 数据库存储至少一个控制元类的实例，该控件元类定义了指定表示为元类的任何给定类别的目标类别属性，以及控制属性，其规定对由指定类别定义的属性执行的控件 按目标类别属性。 根据控制元类的实例，控制执行单元执行由目标类别属性指定的类别属性上的控制属性规定的控制。