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. 发明授权

US08301438B2 Method for processing natural language questions and apparatus thereof 有权
标题翻译：用于处理自然语言问题的方法及其装置
公开(公告)号：US08301438B2
公开(公告)日：2012-10-30
申请号：US12765990
申请日：2010-04-23
申请人： David Angelo Ferrucci , Li Ma , Yue Pan , Zhao Ming Qiu , Chen Wang , Christopher Welty , Lei Zhang
发明人： David Angelo Ferrucci , Li Ma , Yue Pan , Zhao Ming Qiu , Chen Wang , Christopher Welty , Lei Zhang
IPC分类号： G06F17/27
CPC分类号： G06F17/30654
摘要： A method and an apparatus for selecting an answer to a natural language question. The method includes: detecting a named entity in the natural language question; extracting information related to an answer from the natural language question; searching in linked data according to the detected named entity; generating a candidate answer according to a search result; parsing the candidate answer according to the information related to the answer; and obtaining a value of a feature of the candidate answer; and evaluating each candidate answer by synthesizing the value of the feature of the candidate answer.
摘要翻译：一种用于选择自然语言问题的答案的方法和装置。该方法包括：在自然语言问题中检测命名实体; 从自然语言问题中提取与答案有关的信息; 根据检测到的命名实体搜索链接数据; 根据搜索结果生成候选答案; 根据与答案相关的信息解析候选答案; 并获得候选答案的特征值; 并且通过合成候选答案的特征值来评估每个候选答案。

2. 发明授权

US08099382B2 Method and system for mapping multi-dimensional model to data warehouse schema 失效
标题翻译：将多维模型映射到数据仓库模式的方法和系统
公开(公告)号：US08099382B2
公开(公告)日：2012-01-17
申请号：US12100749
申请日：2008-04-10
申请人： Sheng Ping Liu , Zhao Ming Qiu , Guo Tong Xie , Yang Yang
发明人： Sheng Ping Liu , Zhao Ming Qiu , Guo Tong Xie , Yang Yang
IPC分类号： G06F7/00 , G06F17/00
CPC分类号： G06F17/30592
摘要： A system maps a multidimensional model to data warehouse schema. The system includes a multidimensional model editor for defining a multidimensional model based on a conceptual model; a mapping reasoner for generating more simple mappings from basic mappings by reasoning on the conceptual model so as to provide mappings for concerning elements in an ontology path in the multidimensional model; a data warehouse schema analyzer for generating a data structure capable of indicating information of the data warehouse schema by making an analysis on the information of the data warehouse schema; and a mapping composition engine for generating result mappings according to mappings for the concerning elements of the ontology path in the multidimensional model and by searching in the data structure paths corresponding to the concerning elements of the ontology path in the multidimensional model. A method and computer program product are also disclosed.
摘要翻译：系统将多维模型映射到数据仓库模式。该系统包括用于基于概念模型定义多维模型的多维模型编辑器; 一种映射推理器，用于通过推理概念模型从基本映射生成更简单的映射，以便为多维模型中的本体路径中的元素提供映射; 数据仓库模式分析器，用于通过对数据仓库模式的信息进行分析来生成能够指示数据仓库模式信息的数据结构; 以及映射构图引擎，用于根据多维模型中的本体路径的相关元素的映射生成结果映射，并且通过在与多维模型中的本体路径的有关元素相对应的数据结构路径中进行搜索来生成结果映射。还公开了一种方法和计算机程序产品。

3. 发明授权

US07725504B2 Method and apparatus for helping user form structured diagram from unstructured information source 有权
标题翻译：帮助用户从非结构化信息源形成结构图的方法和装置
公开(公告)号：US07725504B2
公开(公告)日：2010-05-25
申请号：US11390924
申请日：2006-03-28
申请人： Zhao Ming Qiu , Guo Tong Xie , Dong Liu , Gang Hu
发明人： Zhao Ming Qiu , Guo Tong Xie , Dong Liu , Gang Hu
IPC分类号： G06F7/00 , G06F9/45 , G06F17/00
CPC分类号： G06F17/30731 , G06F17/3002 , G06F2217/74
摘要： The present invention provides a method and apparatus for helping a user form a structured diagram from an unstructured information source. Starting with one or more key information elements such as some special words, the requests of a customer contained in the information source can be obtained by performing interactive and iterative searching in the unstructured information source such as text, audio, video and etc., the artifacts representing them are drawn in the diagram, and linkages are established between the artifacts and the corresponding contents in the information source. The present invention also proposes that the distribution of established linkages can be used to check whether all the requests in the information source have been extracted in the diagram. Further, various levels of warnings can be shown according to the density of linkage distribution. Therefore the user can draw a structured diagram more conveniently and quickly, and can perform checking and reusing more easily.
摘要翻译：本发明提供了一种帮助用户从非结构化信息源形成结构化图的方法和装置。从一个或多个关键信息元素（例如一些特殊字）开始，可以通过在非结构化信息源（例如文本，音频，视频等）中执行交互式和迭代搜索来获得信息源中包含的客户的请求，在图中绘制代表它们的工件，并且在工件和信息源中的相应内容之间建立联系。本发明还提出，所建立的链接的分布可以用于检查信息源中的所有请求是否已经在图中被提取。此外，可以根据联动分配的密度显示各种警告级别。因此，用户可以更方便快捷地绘制结构化图表，并可以更轻松地执行检查和重用。

4. 发明申请

US20080301083A1 System and method for generating new concepts based on existing ontologies 有权
标题翻译：基于现有本体生成新概念的系统和方法
公开(公告)号：US20080301083A1
公开(公告)日：2008-12-04
申请号：US11447546
申请日：2006-06-05
申请人： Zhuo Zhang , Zhao Ming Qiu , Shixia Liu , Yue Pan , Guo Tong Xie
发明人： Zhuo Zhang , Zhao Ming Qiu , Shixia Liu , Yue Pan , Guo Tong Xie
IPC分类号： G06N5/02
CPC分类号： G06F17/2785
摘要： A system and a method for automatically generating new concepts based on existing ontologies are provided. The system creates new concepts in existing ontologies based on new concept descriptions expressed in a natural language format, and comprises: a normalizer for receiving and parsing the new concept descriptions so as to transform them into normalized one and output them, wherein said normalized concept description includes one or more description part(s) having kernel concepts, said description parts can only contain the terms which can be identified in said existing ontologies, and each of said kernel concept contains a headword and zero or more property(s); and a new concept factory for, based on the normalized description of the new concept, identifying the kernel concepts in each normalized concept description part, and extracting the identified kernel concepts, related properties, and the relations among the kernel concepts for a user to create new concepts according to existing ontologies. Therefore, ontologies will be easier to be managed, reused and expanded, while keeping smaller size and less complexity of the ontologies.
摘要翻译：提供了一种基于现有本体自动生成新概念的系统和方法。该系统基于以自然语言格式表示的新概念描述在现有本体中创建新概念，并且包括：规范化器，用于接收和解析新概念描述，以便将它们变换为归一化的，并将其输出，其中所述归一化概念描述包括具有核心概念的一个或多个描述部分，所述描述部分只能包含可在所述现有本体中识别的术语，并且所述核心概念中的每一个包含头条和零个或多个属性; 和一个新的概念工厂，基于对新概念的归一化描述，识别每个归一化概念描述部分中的内核概念，并提取所识别的内核概念，相关属性以及用户创建的内核概念之间的关系根据现有本体的新概念。因此，本体将更容易被管理，重用和扩展，同时保持较小的尺寸和较少的本体的复杂性。

5. 发明申请

US20080256121A1 METHOD AND SYSTEM FOR MAPPING MULTI-DIMENSIONAL MODEL TO DATA WAREHOUSE SCHEMA 失效
标题翻译：用于将多维模型映射到数据仓库示意图的方法和系统
公开(公告)号：US20080256121A1
公开(公告)日：2008-10-16
申请号：US12100749
申请日：2008-04-10
申请人： Sheng Ping Liu , Zhao Ming Qiu , Guo Tong Xie , Yang Yang
发明人： Sheng Ping Liu , Zhao Ming Qiu , Guo Tong Xie , Yang Yang
IPC分类号： G06F17/30
CPC分类号： G06F17/30592
摘要： A system maps a multidimensional model to data warehouse schema. The system includes a multidimensional model editor for defining a multidimensional model based on a conceptual model; a mapping reasoner for generating more simple mappings from basic mappings by reasoning on the conceptual model so as to provide mappings for concerning elements in an ontology path in the multidimensional model; a data warehouse schema analyzer for generating a data structure capable of indicating information of the data warehouse schema by making an analysis on the information of the data warehouse schema; and a mapping composition engine for generating result mappings according to mappings for the concerning elements of the ontology path in the multidimensional model and by searching in the data structure paths corresponding to the concerning elements of the ontology path in the multidimensional model. A method and computer program product are also disclosed.
摘要翻译：系统将多维模型映射到数据仓库模式。该系统包括用于基于概念模型定义多维模型的多维模型编辑器; 一种映射推理器，用于通过推理概念模型从基本映射生成更简单的映射，以便为多维模型中的本体路径中的元素提供映射; 数据仓库模式分析器，用于通过对数据仓库模式的信息进行分析来生成能够指示数据仓库模式的信息的数据结构; 以及映射构图引擎，用于根据多维模型中的本体路径的相关元素的映射生成结果映射，并且通过在与多维模型中的本体路径的有关元素相对应的数据结构路径中进行搜索来生成结果映射。还公开了一种方法和计算机程序产品。

6. 发明授权

US07149681B2 Method, system and program product for resolving word ambiguity in text language translation 有权
标题翻译：用于解决文本语言翻译中词义模糊的方法，系统和程序产品
公开(公告)号：US07149681B2
公开(公告)日：2006-12-12
申请号：US09740780
申请日：2000-12-19
申请人： Gang Hu , Jian Min Jiang , Zhao Ming Qiu , Donald T. Tang , Li Ping Yang
发明人： Gang Hu , Jian Min Jiang , Zhao Ming Qiu , Donald T. Tang , Li Ping Yang
IPC分类号： G06F17/27
CPC分类号： G06F17/2785 , G06F17/2845 , G06F17/2872
摘要： This invention discloses a computer translation method and system for resoving word ambiguity. During translating a text in a first language, checking whether or not the word to be translated or the sentence containing the word has additional related text that is associated by a linkage. When the meaning of the word can not be uniquely determined in a second language by analyzing the context than the related text is obtained according to the linkage and the word is translated using both the immediate text and the related text. The linkage mechanism is described as a hyperlink in a HTML document.
摘要翻译：本发明公开了一种用于解决词义模糊的计算机翻译方法和系统。在翻译第一语言的文本时，检查要翻译的单词是否包含该单词的句子具有由链接相关联的附加相关文本。当通过分析上下文而不能以第二语言唯一确定单词的含义时，根据链接获得相关文本，并且使用立即文本和相关文本翻译该单词。链接机制被描述为HTML文档中的超链接。

7. 发明申请

US20100299139A1 METHOD FOR PROCESSING NATURAL LANGUAGE QUESTIONS AND APPARATUS THEREOF 有权
标题翻译：用于处理自然语言问题的方法及其设备
公开(公告)号：US20100299139A1
公开(公告)日：2010-11-25
申请号：US12765990
申请日：2010-04-23
申请人： David Angelo Ferrucci , Li MA , Yue Pan , Zhao Ming Qiu , Chen Wang , Christopher Welty , Lei Zhang
发明人： David Angelo Ferrucci , Li MA , Yue Pan , Zhao Ming Qiu , Chen Wang , Christopher Welty , Lei Zhang
IPC分类号： G06F17/27
CPC分类号： G06F17/30654
摘要： A method and an apparatus for selecting an answer to a natural language question. The method includes: detecting a named entity in the natural language question; extracting information related to an answer from the natural language question; searching in linked data according to the detected named entity; generating a candidate answer according to a search result; parsing the candidate answer according to the information related to the answer; and obtaining a value of a feature of the candidate answer; and evaluating each candidate answer by synthesizing the value of the feature of the candidate answer.
摘要翻译：一种用于选择自然语言问题的答案的方法和装置。该方法包括：在自然语言问题中检测命名实体; 从自然语言问题中提取与答案有关的信息; 根据检测到的命名实体搜索链接数据; 根据搜索结果生成候选答案; 根据与答案相关的信息解析候选答案; 并获得候选答案的特征值; 并且通过合成候选答案的特征值来评估每个候选答案。

8. 发明授权

US07685088B2 System and method for generating new concepts based on existing ontologies 有权
标题翻译：基于现有本体生成新概念的系统和方法
公开(公告)号：US07685088B2
公开(公告)日：2010-03-23
申请号：US11447546
申请日：2006-06-05
申请人： Zhuo Zhang , Zhao Ming Qiu , Shixia Liu , Yue Pan , Guo Tong Xie
发明人： Zhuo Zhang , Zhao Ming Qiu , Shixia Liu , Yue Pan , Guo Tong Xie
IPC分类号： G06N5/04 , G06F15/18
CPC分类号： G06F17/2785
摘要： A system and a method for automatically generating new concepts based on existing ontologies are provided. The system creates new concepts in existing ontologies based on new concept descriptions expressed in a natural language format, and comprises: a normalizer for receiving and parsing the new concept descriptions so as to transform them into normalized one and output them, wherein said normalized concept description includes one or more description part(s) having kernel concepts, said description parts can only contain the terms which can be identified in said existing ontologies, and each of said kernel concept contains a headword and zero or more property(s); and a new concept factory for, based on the normalized description of the new concept, identifying the kernel concepts in each normalized concept description part, and extracting the identified kernel concepts, related properties, and the relations among the kernel concepts for a user to create new concepts according to existing ontologies. Therefore, ontologies will be easier to be managed, reused and expanded, while keeping smaller size and less complexity of the ontologies.
摘要翻译：提供了一种基于现有本体自动生成新概念的系统和方法。该系统基于以自然语言格式表示的新概念描述在现有本体中创建新概念，并且包括：规范化器，用于接收和解析新概念描述，以便将它们变换为归一化的，并将其输出，其中所述归一化概念描述包括具有核心概念的一个或多个描述部分，所述描述部分只能包含可在所述现有本体中识别的术语，并且所述核心概念中的每一个包含头条和零个或多个属性; 和一个新的概念工厂，基于对新概念的归一化描述，识别每个归一化概念描述部分中的内核概念，并提取所识别的内核概念，相关属性以及用户创建的内核概念之间的关系根据现有本体的新概念。因此，本体将更容易被管理，重用和扩展，同时保持较小的尺寸和较少的本体的复杂性。

9. 发明申请

US20080250015A1 CORPUS EXPANSION SYSTEM AND METHOD THEREOF 有权
标题翻译：公司扩展系统及其方法
公开(公告)号：US20080250015A1
公开(公告)日：2008-10-09
申请号：US12138139
申请日：2008-06-12
申请人： Hong Lei Guo , Li Zhang , Zhao Ming Qiu , Li Qin Shen , Zhi Li Guo
发明人： Hong Lei Guo , Li Zhang , Zhao Ming Qiu , Li Qin Shen , Zhi Li Guo
IPC分类号： G06F17/30
CPC分类号： G06F17/2715 , G06F17/30731
摘要： A system and method for expanding new sample seeds to automatically expand corpora, in which sample seeds are used to collect corpus is provided. The new sample seeds are generated based on the already existed sample seeds and collected corpora; The corpus expansion strategy is determined based on all the sample seeds having been used and new sample seeds: The new sample seeds are refined based on the corpus expansion strategy, and the refined new sample seeds are used to further collect corpus. The above steps are repeatedly executed until predefined condition is satisfied. According to the invention, corpus may be automatically expanded from the web or other resources with low cost and in convenient way to improve the coverage of corpora.
摘要翻译：提供了用于扩展新样本种子以自动扩展语料库的系统和方法，其中使用样本种子收集语料库。新样本种子基于已经存在的样本种子和收集的语料库生成; 基于所使用的所有样本种子和新的样本种子确定语料库扩展策略：基于语料库扩展策略对新样本种子进行细化，并使用精制的新样本种子进一步收集语料库。重复执行上述步骤，直到满足预定条件。根据本发明，语料库可以以低成本和便利的方式从网络或其他资源自动地扩展以提高语料库的覆盖。

10. 发明授权

US09020862B2 Method and system for computer question-answering 有权
标题翻译：计算机问答方法和系统
公开(公告)号：US09020862B2
公开(公告)日：2015-04-28
申请号：US13552998
申请日：2012-07-19
申请人： Yuan Ni , Zhao Ming Qiu , Lei Zhang
发明人： Yuan Ni , Zhao Ming Qiu , Lei Zhang
IPC分类号： G06F15/18 , G06N99/00
CPC分类号： G06N99/005
摘要： A method and system for computer question-answering. The method includes: receiving a plurality of the questions to be trained, and obtaining a candidate answer set for each question; determining part of the questions to which the candidate answer sets include correct answers, and using first feature sets of the candidate; obtaining a first mathematical model, which is used to compute a first confidence degree that the candidate answer is a correct answer; computing first confidence degrees of the candidate answers of all the questions to be trained, and for each question, extracting a second feature set related to the first confidence degrees and the first feature set; and obtaining a second mathematic model, which is used to compute a second confidence degree that the candidate answer is a correct answer based on the second feature set.
摘要翻译：一种计算机问答方法和系统。该方法包括：接收要训练的多个问题，并获得每个问题的候选答案集; 确定候选答案集的问题的一部分包括正确的答案，以及使用候选人的第一特征集; 获得第一数学模型，其用于计算候选答案是正确答案的第一置信度; 计算要训练的所有问题的候选答案的第一置信度，并且对于每个问题，提取与第一置信度和第一特征集相关的第二特征集; 以及获得第二数学模型，所述第二数学模型用于基于所述第二特征集来计算所述候选答案为正确答案的第二置信度。

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