-
公开(公告)号：US20060136472A1
公开(公告)日：2006-06-22
申请号：US11017595
申请日：2004-12-20
IPC分类号： G06F17/00
CPC分类号： G06F17/30067 , Y10S707/99938 , Y10S707/99952
摘要： A method and system for supporting a concurrent recordation of a change in a data file by a server while allowing an application to continue writing changes to a data file. In response to a change in a data file, a near-instantaneous version of the file is created. Metadata reflecting the change to the data file are synchronized with a version of the file in cache and recorded in persistent storage. During the process of recording metadata changes to the file, subsequent changes to the data file may continue, and metadata reflecting the changes may be recorded in a subsequent near-instantaneous version of the file which may also be synchronized with a version of the metadata in persistent storage.
-
公开(公告)号：US08644611B2
公开(公告)日：2014-02-04
申请号：US12477582
申请日：2009-06-03
CPC分类号： G06K9/6842 , G06K9/00865 , G06K9/6292 , G06K2209/01
摘要： A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.
摘要翻译： 用于文本识别的方法包括为图像生成多个文本假设，例如，使用基于HMM的方法使用固定宽度分析特征。 对于每个文本假设，生成一个或多个分段，并在分段级别进行评分，例如，根据文本假设的字符或字符组段。 在一些实施例中，针对每个文本假设考虑多个替代分割。 在一些示例中，组合生成文本假设和分段得分时确定的分数，以选择图像的整体文本识别。
-
3.发明申请METHOD AND SYSTEM FACILITATING AN END-TO-END SOLUTION FOR ONE OR MORE SERVICE OFFERINGS 审中-公开方法和系统促进一个或多个服务提供的端到端解决方案公开(公告)号：US20110313903A1
公开(公告)日：2011-12-22
申请号：US12855026
申请日：2010-08-12
申请人： Gnanapriya C. , Arup Goswami , Nishi Mathur , Munish Kashyap , Jamsheed Kormath , Rohit Prasad , Yuvraj Sakharam Magdum , Sreekumar Gopalakrishnan , Anand Subramanian , Soumen Saha
发明人： Gnanapriya C. , Arup Goswami , Nishi Mathur , Munish Kashyap , Jamsheed Kormath , Rohit Prasad , Yuvraj Sakharam Magdum , Sreekumar Gopalakrishnan , Anand Subramanian , Soumen Saha
CPC分类号： G06Q20/367 , G06Q30/04 , H04M15/43 , H04M15/61 , H04M15/765 , H04M15/772 , H04M15/80 , H04M15/8022
摘要： A system and method facilitating an end-to-end solution for one or more service offerings. The end-to-end solution includes the modeling, provisioning, and rating of a single subscription as at least one of prepaid and postpaid. The system includes a CRM layer, an integration layer, a rating and billing management layer, and a service activation platform layer.
摘要翻译： 一种促进一个或多个服务产品的端到端解决方案的系统和方法。 端到端解决方案包括单个订阅的建模，配置和评级，至少是预付费和后付费之一。 该系统包括CRM层，集成层，评级和计费管理层以及服务激活平台层。
-
公开(公告)号：US20200045130A1
公开(公告)日：2020-02-06
申请号：US16455604
申请日：2019-06-27
申请人： Ariya Rastrow , Tony Hardie , Rohit Prasad
发明人： Ariya Rastrow , Tony Hardie , Rohit Prasad
摘要： Systems, methods, and devices for computer-generating responses and sending responses to communications when the recipient of the communication is unavailable are disclosed. An individual may send a message (either audio or text) to a recipient. The recipient may be unavailable to contemporaneously respond to the message (e.g., the recipient may be performing an action that makes is difficult or impractical for the recipient to contemporaneously respond to the audio message). When the recipient is unavailable, a response to the message is generated and sent without receiving an instruction from the recipient to do so. The response may be sent to the message originating individual, and content of the response may thereafter be sent to the recipient to receive feedback regarding the correctness of the response. Alternatively, the response content may first be sent to the recipient to receive the feedback, and thereafter the response may be sent to the message originating individual.
-
公开(公告)号：US20100246961A1
公开(公告)日：2010-09-30
申请号：US12413048
申请日：2009-03-27
IPC分类号： G06K9/00
CPC分类号： G06K9/3258 , G06K9/6297 , G06K9/723 , G06K2209/01
摘要： Multi-frame persistence of videotext is exploited to mitigate challenges posed by varying characteristics of videotext across frame instances to improve OCR techniques. In some examples, each frame of video is processed to form multiple binary images, and one or more text hypotheses is formed from each binary image. In some examples, one or more combined images are formed from multiple frames processed to form a binary image and a corresponding text hypothesis. The text hypotheses are combined to yield an overall text recognition output.
摘要翻译： 利用视频文本的多帧持续性来减轻视频文本跨框架实例的不同特征所带来的挑战，从而改善OCR技术。 在一些示例中，视频的每个帧被处理以形成多个二进制图像，并且从每个二进制图像形成一个或多个文本假设。 在一些示例中，一个或多个组合图像由处理以形成二进制图像和相应文本假设的多个帧形成。 文本假设被组合以产生整体文本识别输出。
-
6.发明授权Method and apparatus for training an automated speech recognition-based system 有权用于训练基于自动语音识别的系统的方法和装置公开(公告)号：US07346507B1
公开(公告)日：2008-03-18
申请号：US10454213
申请日：2003-06-04
申请人： Premkumar Natarajan , Rohit Prasad
发明人： Premkumar Natarajan , Rohit Prasad
CPC分类号： G10L15/063
摘要： A method and apparatus for building a training set for an automated speech recognition-based system, which determines the statistically optimal number of frequently requested responses to automate in order to achieve a desired automation rate. The invention may be used to select the appropriate tokens and responses to train the system and to achieve a desired “phrase coverage” for all of the many different ways human beings may phrase a request that calls for one of a plurality of frequently-requested responses. The invention also determines the statistically optimal number of tokens (spoken requests) required to train a speech recognition-based system to achieve the desired phrase coverage and optimal allocation of tokens over the set of responses that are to be automated.
摘要翻译： 一种用于构建用于基于自动语音识别的系统的训练集的方法和装置，其基于自动化来确定经常请求的响应的统计最佳数量以实现期望的自动化速率。 本发明可以用于选择适当的标记和响应来训练系统并且为人类可以短时呼叫多个频繁请求的响应之一的请求的所有许多不同方式实现期望的“短语覆盖” 。 本发明还确定训练基于语音识别的系统以实现期望的短语覆盖所需的令牌（口头请求）的统计最佳数量，并且对要自动化的响应集合进行令牌的最佳分配。
-
公开(公告)号：US08290273B2
公开(公告)日：2012-10-16
申请号：US12413048
申请日：2009-03-27
CPC分类号： G06K9/3258 , G06K9/6297 , G06K9/723 , G06K2209/01
摘要： Multi-frame persistence of videotext is exploited to mitigate challenges posed by varying characteristics of videotext across frame instances to improve OCR techniques. In some examples, each frame of video is processed to form multiple binary images, and one or more text hypotheses is formed from each binary image. In some examples, one or more combined images are formed from multiple frames processed to form a binary image and a corresponding text hypothesis. The text hypotheses are combined to yield an overall text recognition output.
摘要翻译： 利用视频文本的多帧持续性来减轻视频文本跨框架实例的不同特征所带来的挑战，从而改善OCR技术。 在一些示例中，视频的每个帧被处理以形成多个二进制图像，并且从每个二进制图像形成一个或多个文本假设。 在一些示例中，一个或多个组合图像由处理以形成二进制图像和相应文本假设的多个帧形成。 文本假设被组合以产生整体文本识别输出。
-
公开(公告)号：US20100310172A1
公开(公告)日：2010-12-09
申请号：US12477582
申请日：2009-06-03
IPC分类号： G06K9/00
CPC分类号： G06K9/6842 , G06K9/00865 , G06K9/6292 , G06K2209/01
摘要： A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.
摘要翻译： 用于文本识别的方法包括为图像生成多个文本假设，例如，使用基于HMM的方法使用固定宽度分析特征。 对于每个文本假设，生成一个或多个分段，并在分段级别进行评分，例如，根据文本假设的字符或字符组段。 在一些实施例中，针对每个文本假设考虑多个替代分割。 在一些示例中，组合生成文本假设和分段得分时确定的分数，以选择图像的整体文本识别。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.027 秒)
