公开(公告)号：US20160217376A1

公开(公告)日：2016-07-28

申请号：US15025566

申请日：2013-12-06

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  FOUNDER APABI TECHNOLOGY LIMITED ,  PEKING UNIVERSITY

发明人： Mao YE ,  Lifeng JIN ,  Chao LEI ,  Yuanlong WANG ,  Zhi TANG ,  Jianbo XU

IPC分类号： G06N5/02 ,  G06F17/28

CPC分类号： G06N5/022 ,  G06F16/36 ,  G06F17/28

摘要： In the method and system for knowledge extraction of this invention, knowledge extraction is realized through acquiring an initial sentence group including one or more sentences, and then comparing the length of the initial sentence group with an expected length to determine the initial sentence group to be expanded according to the comparison result. Since the sentence groups are formed by consecutive sentences, it may be guaranteed that the sentence groups themselves have good coherence in logic, so that the final sentence groups obtained through expanding the initial sentence groups have good coherence in logic correspondingly. Thus, this invention may override the drawback of lacking logical coherence in extracted knowledge information in the prior art.

摘要翻译： 在本发明的知识提取方法和系统中，通过获取包括一个或多个句子的初始句子组，然后将初始句子组的长度与预期长度进行比较来确定初始句子组，从而实现知识抽取 根据比较结果扩大。 由于句子组是由连续句子形成的，可以保证句子组本身在逻辑上具有良好的一致性，从而通过扩展初始句子组获得的最终句子组在逻辑上具有良好的一致性。 因此，本发明可以覆盖现有技术中提取的知识信息中缺少逻辑一致性的缺点。

公开(公告)号：US20160217142A1

公开(公告)日：2016-07-28

申请号：US15025460

申请日：2013-12-06

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  FOUNDER APABI TECHNOLOGY LIMITED ,  PEKING UNIVERSITY

发明人： Mao YE ,  Zhi TANG ,  Jianbo XU ,  Lifeng JIN ,  Wei WAN

IPC分类号： G06F17/30 ,  G06F3/0484

CPC分类号： G06F17/3071 ,  G06F3/0484 ,  G06F17/30666 ,  G06F17/30672 ,  G06F17/30684

摘要： The present invention provides a semantic information acquisition method and system, and corresponding keyword expansion and search methods and systems, comprising: searching for, then classifying an article; then, performing word segmentation according to the classified article to obtain the words in said category, and setting said category and words to serve as the semantic information of the keyword; also, a method and system using the semantic information acquisition method to expand a keyword, and a method and system using keyword expansion to perform a search. The described semantic information acquisition method effectively avoids the technical problems in the prior art of only being able to obtain semantic information of English vocabulary; and it also being impossible to classify semantic information based on category information. The invention is particularly suitable for searching using a keyword, searching a large number of texts, and organizing large amounts of related data and information.

摘要翻译： 本发明提供了一种语义信息获取方法和系统，以及相应的关键词扩展和搜索方法和系统，包括：搜索，然后对文章进行分类; 然后，根据分类文章执行词分割以获得所述类别中的单词，并将所述类别和单词设置为关键词的语义信息; 还有，使用语义信息获取方法来扩展关键字的方法和系统，以及使用关键词扩展来执行搜索的方法和系统。 所描述的语义信息获取方法有效地避免了现有技术中仅能够获得英语词汇的语义信息的技术问题; 并且也不可能基于类别信息对语义信息进行分类。 本发明特别适用于使用关键字搜索，搜索大量文本以及组织大量相关数据和信息。

公开(公告)号：US20160224564A1

公开(公告)日：2016-08-04

申请号：US15025448

申请日：2013-12-06

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  FOUNDER APABI TECHNOLOGY LIMITED ,  PEKING UNIVERSITY

发明人： Mao YE ,  Jianbo XU ,  Zhi TANG ,  Lifeng JIN ,  Yuanlong WANG

IPC分类号： G06F17/30

CPC分类号： G06F17/3053 ,  G06N5/00

摘要： A method and system for key knowledge point recommendation are provided, the method comprising calculating knowledge point relationship strengths of knowledge points in a set of knowledge points; calculating weights for knowledge points according to the knowledge point relationship strengths of knowledge points in the set of knowledge points, and storing the knowledge points and weights correspondingly; determining key knowledge points according to the weights of the knowledge points and recommending the key knowledge points to a user. With this solution, knowledge point relationship strengths are obtained through calculating knowledge point relationship strengths of knowledge points in a set of knowledge points; and recommendation is given to the user for learning knowledge according to knowledge point relationship strengths, so as to help the user to learn key knowledge points selectively in a more objective and effective manner, and avoid problems of information recommendation based on fuzzy logical information recommendation technology.

摘要翻译： 提供了一种用于关键知识点推荐的方法和系统，该方法包括计算一组知识点中知识点的知识点关系强度; 根据知识点知识点的知识点关系强度计算知识点的权重，并相应地存储知识点和权重; 根据知识点的权重确定关键知识点，并向用户推荐关键知识点。 利用这个解决方案，通过计算一组知识点中知识点的知识点关系强度来获得知识点关系强度; 并根据知识点关系强度向用户提供学习知识的建议，帮助用户以更客观有效的方式有选择地学习关键知识点，避免基于模糊逻辑信息推荐技术的信息推荐问题 。

公开(公告)号：US20160210372A1

公开(公告)日：2016-07-21

申请号：US15025478

申请日：2013-12-06

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  FOUNDER APABI TECHNOLOGY LIMITED ,  PEKING UNIVERSITY

发明人： Mao YE ,  Wei WAN ,  Jianbo XU ,  Zhi TANG ,  Lifeng JIN

IPC分类号： G06F17/30

CPC分类号： G06F17/30958 ,  G06F17/30994 ,  G06N5/00

摘要： A method and system for obtaining a knowledge point implicit relationship are provided; first, establishing a knowledge point explicit relationship map according to knowledge point explicit relationship strengths; second, computing according to said knowledge point explicit relationship map a simple path set of two knowledge points; then, computing the implicit relationship strength values corresponding to each simple path in said simple path set; further, comparing the relationship strength values of the simple paths and setting as the significant implicit relationship strength value the simple path relationship strength having the largest value also greater than a preset threshold value. The described solution effectively avoids the problems of only using the relationship strengths between knowledge points and the ratio of relationship strengths to obtain the implicit relationship of knowledge points, the manner of searching for an implicit relationship being insufficiently accurate, and not performing normalization processing on the relationship strengths.

摘要翻译： 提供了一种获取知识点隐式关系的方法和系统; 首先，根据知识点明确的关系强度建立知识点显性关系图; 第二，根据所述知识点计算显性关系映射两个知识点的简单路径集; 然后，计算与所述简单路径集中的每个简单路径相对应的隐含关系强度值; 此外，比较简单路径的关系强度值和设置为有效隐含关系强度值，具有最大值的简单路径关系强度也大于预设阈值。 所描述的解决方案有效地避免了仅使用知识点之间的关系强度和关系强度比率来获得知识点的隐含关系，隐含关系搜索方式不够准确以及不执行归一化处理的问题 关系优势。

公开(公告)号：US20140337717A1

公开(公告)日：2014-11-13

申请号：US14104245

申请日：2013-12-12

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  PEKING UNIVERSITY ,  FOUNDER APABI TECHNOLOGY LIMITED

发明人： Canhui XU ,  Zhi TANG ,  Xin TAO ,  Cao SHI

IPC分类号： G06F17/21

CPC分类号： G06F17/212 ,  G06F3/0483 ,  G06F3/0484 ,  G06F17/2705 ,  G06K9/00463

摘要： A logic process apparatus for composite graphs in a fixed layout document is provided in this invention, comprising: a composite graph block extraction unit, for extracting composite graph blocks from the fixed layout document; a document parsing unit, for parsing the fixed layout document to obtain text primitives contained therein; a legend primitive extraction unit, for extracting legend primitives from the text primitives; a correlation detection unit, for detecting correlations between the composite graph blocks and the legend primitives; a correlation storage unit, for storing the detected correlations. A logic process method for composite graphs in a fixed layout document is also provided.

摘要翻译： 本发明提供了一种用于固定布局文档中的复合图形的逻辑处理装置，包括：组合图块提取单元，用于从固定布局文档中提取合成图块; 文档解析单元，用于解析固定布局文档以获得其中包含的文本图元; 用于从文本原语中提取图例原语的图例原始提取单元; 相关检测单元，用于检测合成图形块和图例基元之间的相关性; 相关存储单元，用于存储检测到的相关性。 还提供了一种用于固定布局文档中的复合图的逻辑处理方法。

公开(公告)号：US20160217373A1

公开(公告)日：2016-07-28

申请号：US15025492

申请日：2013-12-05

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  FOUNDER APABI TECHNOLOGY LIMITED ,  PEKING UNIVERSITY

发明人： Mao YE ,  Zhi TANG ,  Jianbo XU

IPC分类号： G06N5/02

CPC分类号： G06N5/02 ,  G06N5/00

摘要： The present invention provides a method and system of measuring knowledge point relationship strength, the method comprising calculating explicit relationship strength for all knowledge points and generating a knowledge point relationship strength matrix M; constructing a weighted and directed graph G according to the knowledge point relationship strength matrix of all knowledge points; calculating knowledge point implicit relationship strength values according to the weighted and directed graph and generating a knowledge point implicit relationship strength matrix I; traversing the knowledge point implicit relationship strength matrix I and updating the knowledge point relationship strength matrix M. The above technical solution may effectively avoid the problem of lack of an absolute measurable value for the determination of relationship strength, incorrect measurement of relationship strength, or unable to discover some stronger relationship strength in the prior art.

摘要翻译： 本发明提供了一种测量知识点关系强度的方法和系统，该方法包括计算所有知识点的显式关系强度，并生成知识点关系强度矩阵M; 根据所有知识点的知识点关系强度矩阵构建加权和有向图G; 根据加权和有向图计算知识点隐式关系强度值，生成知识点隐式关系强度矩阵I; 遍历知识点隐性关系强度矩阵I并更新知识点关系强度矩阵M.上述技术方案可以有效地避免关系强度确定，关系强度测量不正确或无法确定的绝对可测量值的问题 在现有技术中发现一些更强的关系强度。

公开(公告)号：US20150093021A1

公开(公告)日：2015-04-02

申请号：US14096532

申请日：2013-12-04

申请人： Founder Apabi Technology Limited ,  Peking University Founder Group Co., Ltd.

发明人： Canhui XU ,  Zhi TANG ,  Jianbo XU ,  Xin TAO

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06T7/00

CPC分类号： G06K9/00449 ,  G06K9/00463

摘要： Provided is a table recognizing method, comprising: parsing and analyzing metadata information in an original fixed-layout document, and extracting basic elements on a page of the document; segmenting the basic elements, extracting segmented text lines on the page, and acquiring fragments; constructing an undirected graph with respect to each of the fragments; extracting an image on the page, detecting intersection points of horizontal lines and vertical lines, detecting an external bounding box of the intersection points, and taking whether the segmented text lines fall within the external bounding box as local relationship features; training a learning model according to the local relationship features, local features of the fragments, and neighborhood relationship features among the fragments, acquiring model parameters, and establishing a table recognizing model; and invoking the table recognizing model to perform table recognizing for the document, and acquiring a recognizing result.

摘要翻译： 提供了一种表识别方法，包括：解析和分析原始固定布局文档中的元数据信息，以及提取文档页面上的基本元素; 分割基本元素，在页面上提取分割的文本行，并获取片段; 构建关于每个片段的无向图; 提取页面上的图像，检测水平线和垂直线的交点，检测交点的外部边界框，以及分割的文本行是否落在外部边框内作为局部关系特征; 根据局部关系特征，片段的局部特征，片段间的邻域关系特征，获取模型参数，建立表识别模型，训练学习模型; 并调用表识别模型来执行文档的表识别，并获取识别结果。

公开(公告)号：US20150095022A1

公开(公告)日：2015-04-02

申请号：US14096431

申请日：2013-12-04

申请人： Founder Apabi Technology Limited ,  Peking University Founder Group Co., Ltd.

发明人： Canhui XU ,  Zhi TANG ,  Jianbo XU ,  Xin TAO

IPC分类号： G06F17/27

CPC分类号： G06K9/00456 ,  G06K9/00469

摘要： A list recognizing method and system, which comprises: parsing and analyzing metadata information within an original fixed-layout document, and extracting basic elements within a page; segmenting the basic elements, extracting segmented text lines within the page to obtain fragments; building an undirected graph with respect to the fragments; detecting indent features of a bullet according to features of the basic elements; training a learning model according to the indent features, local features of the fragments and neighborhood relation features among the fragments, obtaining model parameters, and establishing a list recognizing model; and invoking the list recognizing model to perform list recognizing on the required document, so as to get recognition result. This machine learning method may recognize not only a list, but also the contextual relationship between the first line and its subsequent lines of a list, and realize analyzing and understanding a layout of the list of the fixed-layout document ultimately. The accuracy of list recognizing on a fixed-layout document can be improved even if the bullets of the first line of the list are various.

摘要翻译： 一种列表识别方法和系统，包括：解析和分析原始固定布局文档内的元数据信息，以及提取页面内的基本元素; 分割基本元素，提取页面内的分段文本行以获取片段; 构建与片段无关的图形; 根据基本要素的特征检测子弹的缩进特征; 根据缩进特征，片段的局部特征以及片段间的邻域关系特征，获取模型参数，建立列表识别模型，训练学习模型; 并调用列表识别模型，对所需文件执行列表识别，以获得识别结果。 该机器学习方法不仅可以识别列表，而且可以识别列表的第一行及其后续行之间的上下文关系，并且最终实现对固定布局文档的列表的布局的分析和理解。 即使列表的第一行的子弹是各种各样的，固定布局文档中的列表识别的精度也可以得到提高。

公开(公告)号：US20140348390A1

公开(公告)日：2014-11-27

申请号：US14092563

申请日：2013-11-27

申请人： PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  PEKING UNIVERSITY ,  BEIJING FOUNDER APABI TECHNOLOGY LTD.

发明人： Yan LIU ,  Xiaoqing LV ,  Jianbo XU ,  Zhi TANG

IPC分类号： G06K9/00

CPC分类号： G06K9/00785

摘要： The present invention provides a method and an apparatus for detecting a traffic monitoring video. The method comprises: determining a background reference model; determining a target area image in the traffic monitoring video according to the background reference model; updating the background reference model by using the target area image; summating all target points in detection area of each frame of image in the traffic monitoring video according to the updated background reference model to obtain a total area of all the target points; segmenting the frame with the biggest total area to obtain a target area at the best position; and extracting vehicle information from the target area at the best position. By using the present invention, the accuracy of a detection result in a complex environment may be improved.

摘要翻译： 本发明提供了一种用于检测交通监控视频的方法和装置。 该方法包括：确定背景参考模型; 根据背景参考模型确定交通监控视频中的目标区域图像; 通过使用目标区域图像来更新背景参考模型; 根据更新的背景参考模型，在交通监控视频中的每帧图像的检测区域中求和所有目标点，以获得所有目标点的总面积; 以最大的总面积分割框架，以获得最佳位置的目标区域; 并从最佳位置的目标区域提取车辆信息。 通过使用本发明，可以提高复杂环境中的检测结果的精度。

公开(公告)号：US20140348378A1

公开(公告)日：2014-11-27

申请号：US14092663

申请日：2013-11-27

申请人： Peking University Founder Group Co., Ltd. ,  Beijing Founder Apabi Technology Ltd. ,  Peking University

发明人： Yan LIU ,  Xiaoqing LV ,  Jianbo XU ,  Zhi TANG

IPC分类号： G06T7/20 ,  G06T7/00

CPC分类号： G06T7/2006 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30236

摘要： The present invention provides a method and an apparatus for detecting traffic video information. The method includes: acquiring a traffic video stream; determining color features of each frame of image in the traffic video stream; calculating the inter-frame distance between adjacent frames according to the color features; calculating the boundary of an image clustered frames' group according to the inter-frame distance by adopting an image clustering evaluation standard in RGB space and an image clustering evaluation standard in YUV space respectively; and determining a final boundary of the image clustered frames' group according to the boundaries of the image clustered frames' group in RGB space and YUV space. By using the present invention, the stability of detection results in different environments may be improved.

摘要翻译： 本发明提供一种用于检测业务视频信息的方法和装置。 该方法包括：获取业务视频流; 确定所述业务视频流中每帧图像的颜色特征; 根据颜色特征计算相邻帧之间的帧间距离; 通过采用RGB空间中的图像聚类评估标准和YUV空间中的图像聚类评估标准，根据帧间距离计算图像聚类帧组的边界; 并根据RGB空间和YUV空间中的图像聚类帧组的边界确定图像聚类帧组的最终边界。 通过使用本发明，可以提高不同环境下的检测稳定性。