-
1.发明授权公开(公告)号：US08160362B2
公开(公告)日：2012-04-17
申请号：US13090242
申请日：2011-04-19
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
Abstract translation: 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。
-
2.发明授权公开(公告)号：US08501762B2
公开(公告)日：2013-08-06
申请号：US11988441
申请日：2006-07-07
Applicant: Jianfeng Li , Aixiang Liu , Xinjian Chen , Guozhang Jin , Tiema Yan , Rongxia Zhang , Yi Zhu , Yanjun Pan , Jingshan Shen , Jingkang Shen
Inventor： Jianfeng Li , Aixiang Liu , Xinjian Chen , Guozhang Jin , Tiema Yan , Rongxia Zhang , Yi Zhu , Yanjun Pan , Jingshan Shen , Jingkang Shen
IPC: A61K31/4353 , C07D221/18
CPC classification number: C07D455/03
Abstract: The present invention relates to tetrahydroprotoberberines of the formula (I) and the physiologically acceptable salts thereof. The invention also relates to the use of the compounds of the formula (I) or pharmaceutically acceptable salts thereof for preparing a pharmaceutical composition for the treatment of a medical disorder susceptible to treatment with dopamine receptor ligand, such as schizophrenia.
Abstract translation: 本发明涉及式（I）的四氢异丙基丁腈及其生理上可接受的盐。 本发明还涉及式（I）化合物或其药学上可接受的盐在制备用于治疗易受多巴胺受体配体如精神分裂症治疗的医学疾病的药物组合物中的用途。
-
3.发明授权公开(公告)号：US07953279B2
公开(公告)日：2011-05-31
申请号：US11823644
申请日：2007-06-28
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
Abstract translation: 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。
-
4.发明申请公开(公告)号：US20100163316A1
公开(公告)日：2010-07-01
申请号：US12345668
申请日：2008-12-30
Applicant: Ming Chang , Shi Han , Dongmei Zhang , Yu Zou , Xinjian Chen
Inventor： Ming Chang , Shi Han , Dongmei Zhang , Yu Zou , Xinjian Chen
IPC: G08C21/00
CPC classification number: G06K9/00416 , G06K9/00429 , G16C20/70
Abstract: Described is a multi-path handwriting recognition framework based upon stroke segmentation, symbol recognition, two-dimensional structure analysis and semantic structure analysis. Electronic pen input corresponding to handwritten input (e.g., a chemical expression) is recognized and output via a data structure, which may include multiple recognition candidates. A recognition framework performs stroke segmentation and symbol recognition on the input, and analyzes the structure of the input to output the data structure corresponding to recognition results. For chemical expressions, the structural analysis may perform a conditional sub-expression analysis for inorganic expressions, or organic bond detection, connection relationship analysis, organic atom determination and/or conditional sub-expression analysis for organic expressions. The structural analysis also performs subscript, superscript analysis and character determination. Further analysis may be performed, e.g., chemical valence analysis and/or semantic structure analysis.
Abstract translation: 描述了基于笔划分割，符号识别，二维结构分析和语义结构分析的多路径手写识别框架。 对应于手写输入（例如，化学表达）的电子笔输入通过可包括多个识别候选的数据结构被识别和输出。 识别框架对输入进行笔划分割和符号识别，并分析输入结构以输出与识别结果相对应的数据结构。 对于化学表达式，结构分析可以对有机表达进行无机表征或有机键检测，连接关系分析，有机原子测定和/或条件子表达分析的条件子表达分析。 结构分析还执行下标，上标分析和字符测定。 可以进行进一步分析，例如化学价态分析和/或语义结构分析。
-
5.发明申请公开(公告)号：US20090149488A1
公开(公告)日：2009-06-11
申请号：US11988441
申请日：2006-07-07
Applicant: Jianfeng Li , Aixiang Liu , Xinjian Chen , Guozhang Jin , Tiema Yan , Rongxia Zhang , Yi Zhu , Yanjun Pan , Jingshan Shen , Jingkang Shen
Inventor： Jianfeng Li , Aixiang Liu , Xinjian Chen , Guozhang Jin , Tiema Yan , Rongxia Zhang , Yi Zhu , Yanjun Pan , Jingshan Shen , Jingkang Shen
IPC: A61K31/4375 , C07D221/18 , A61P25/00 , A61P25/18
CPC classification number: C07D455/03
Abstract: The present invention relates to tetrahydroprotoberberines of the formula (I) and the physiologically acceptable salts thereof. The invention also relates to the use of the compounds of the formula (I) or pharmaceutically acceptable salts thereof for preparing a pharmaceutical composition for the treatment of a medical disorder susceptible to treatment with dopamine receptor ligand, such as schizophrenia.
Abstract translation: 本发明涉及式（I）的四氢异丙基丁腈及其生理上可接受的盐。 本发明还涉及式（I）化合物或其药学上可接受的盐在制备用于治疗易受多巴胺受体配体如精神分裂症治疗的医学疾病的药物组合物中的用途。
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20120183223A1
公开(公告)日：2012-07-19
申请号：US13426427
申请日：2012-03-21
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
IPC: G06K9/62
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
Abstract translation: 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。
-
7.发明申请公开(公告)号：US20110194771A1
公开(公告)日：2011-08-11
申请号：US13090242
申请日：2011-04-19
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
IPC: G06K9/00
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
Abstract translation: 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。
-
8.发明申请公开(公告)号：US20090003706A1
公开(公告)日：2009-01-01
申请号：US11823644
申请日：2007-06-28
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
IPC: G06K9/00
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
Abstract translation: 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。
-
公开(公告)号：US20080318949A1
公开(公告)日：2008-12-25
申请号：US12094071
申请日：2006-11-16
Applicant: Guanghui Tian , Shunan Lai , Zhen Wang , Yi Zhu , Xinjian Chen , Yurong Ji , Jinfeng Zhang , Weixi Jin , Heping Lv , Jinping Liu , Wei Wang , Ruyun Ji , Jingshan Shen
Inventor： Guanghui Tian , Shunan Lai , Zhen Wang , Yi Zhu , Xinjian Chen , Yurong Ji , Jinfeng Zhang , Weixi Jin , Heping Lv , Jinping Liu , Wei Wang , Ruyun Ji , Jingshan Shen
IPC: A61K31/5377 , C07D487/04 , A61K31/506 , A61K31/519
CPC classification number: C07D487/04
Abstract: The invention discloses a series of pyrazolopyrimidinone derivatives, which have the following chemical structure, their preparation methods and use, It has been proved by pharmacological experiment that the said pyrazolopyrimidinone derivatives have high inhibitory activity against PDE5, and parts of them have a much stronger potency against PDE5 than against PDE6. Most of the compounds show low toxicity. The pyrazolopyrimidinone derivatives can be used in clinics for the palliative or curative treatment of symptoms or diseases relating to cardiovascular system, urinary system, especially for the palliative or curative treatment of erectile dysfunction.
Abstract translation: 本发明公开了一系列具有以下化学结构的吡唑并嘧啶酮衍生物及其制备方法和应用，已经通过药理实验证明，所述吡唑并嘧啶酮衍生物对PDE5具有高抑制活性，部分药效较强 对PDE5而不是PDE6。 大多数化合物显示低毒性。 吡唑并嘧啶酮衍生物可用于临床上用于缓解或治疗与心血管系统，泌尿系统有关的症状或疾病，特别是对勃起功能障碍的姑息治疗或治疗性治疗。
-
公开(公告)号：US08363950B2
公开(公告)日：2013-01-29
申请号：US13426427
申请日：2012-03-21
Applicant: Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
Inventor： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
CPC classification number: G06K9/00973 , G06K9/6292 , G06K9/6296
Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.016 seconds)
