-
公开(公告)号：US08352414B2
公开(公告)日：2013-01-08
申请号：US12575294
申请日：2009-10-07
申请人： Anuradha Bhamidipaty , Krishna Kummamuru , Shailabh Nagar , Ramendra Sahoo , Virendra K. Varshneya , Karthik Visweswariah
发明人： Anuradha Bhamidipaty , Krishna Kummamuru , Shailabh Nagar , Ramendra Sahoo , Virendra K. Varshneya , Karthik Visweswariah
CPC分类号： G06Q10/06 , G06Q10/063
摘要： A system for discovering business processes from noisy activities logs from various activities performed during the execution of the process. Activities are observed from the noisy activity logs that may include text from manually entered activity logs, chat scripts, emails, voice transcripts, desktop captures, and tool logs, wherein the noisy activity logs are received from multiple person/tool actors with each of the actors performing one or more activities related to one/more business tasks. Extracting information from the noisy activity logs to capture activity based information, and then analyzing similar activities and finding possible paths in the similar activities. The results are used to build a process graph based on the similar activities and the possible paths in the similar activities.
摘要翻译： 从执行过程中执行的各种活动中发现来自嘈杂活动日志的业务流程的系统。 从嘈杂的活动日志观察到活动，其中可能包括手动输入的活动日志，聊天脚本，电子邮件，语音记录，桌面捕获和工具日志的文本，其中从多个人/工具演员接收嘈杂活动日志，其中每个 执行与一个/多个业务任务相关的一个或多个活动的演员。 从嘈杂的活动日志中提取信息以捕获基于活动的信息，然后分析类似活动并在类似活动中查找可能的路径。 结果用于根据类似活动和类似活动中可能的路径构建流程图。
-
公开(公告)号：US20110082716A1
公开(公告)日：2011-04-07
申请号：US12575294
申请日：2009-10-07
申请人： Anuradha Bhamidipaty , Krishna Kummamuru , Shailabh Nagar , Ramendra Kumar Sahoo , Virendra K. Varshneya , Karthik Visweswariah
发明人： Anuradha Bhamidipaty , Krishna Kummamuru , Shailabh Nagar , Ramendra Kumar Sahoo , Virendra K. Varshneya , Karthik Visweswariah
CPC分类号： G06Q10/06 , G06Q10/063
摘要： A system for discovering business processes from noisy activities logs from various activities performed during the execution of the process. Activities are observed from the noisy activity logs that may include text from manually entered activity logs, chat scripts, emails, voice transcripts, desktop captures, and tool logs, wherein the noisy activity logs are received from multiple person/tool actors with each of the actors performing one or more activities related to one/more business tasks. Extracting information from the noisy activity logs to capture activity based information, and then analyzing similar activities and finding possible paths in the similar activities. The results are used to build a process graph based on the similar activities and the possible paths in the similar activities.
摘要翻译： 从执行过程中执行的各种活动中发现来自嘈杂活动日志的业务流程的系统。 从嘈杂的活动日志观察到活动，其中可能包括手动输入的活动日志，聊天脚本，电子邮件，语音记录，桌面捕获和工具日志的文本，其中从多个人/工具演员接收嘈杂活动日志，其中每个 执行与一个/多个业务任务相关的一个或多个活动的演员。 从嘈杂的活动日志中提取信息以捕获基于活动的信息，然后分析类似活动并在类似活动中查找可能的路径。 结果用于根据类似活动和类似活动中可能的路径构建流程图。
-
公开(公告)号：US20120109664A1
公开(公告)日：2012-05-03
申请号：US12916665
申请日：2010-11-01
IPC分类号： G06Q30/00
CPC分类号： G06Q30/02
摘要： A Customer Relationship Management (CRM) offer template is established in data storage and includes at least one variable field and having at least one offer attribute. For each of a plurality of customer groups, a data processing system calculates an expected benefit to be obtained by sending an instantiated CRM offer to a customer based upon historical responses, offer cost, and legal values of the at least one variable field. The data processing system outputs a CRM offer instance and target list of customers that maximizes the expected benefit.
摘要翻译： 在数据存储中建立客户关系管理（CRM）提供模板，并且包括至少一个变量字段并具有至少一个报价属性。 对于多个客户组中的每一个，数据处理系统基于历史响应，提供成本和至少一个可变字段的合法值，向客户发送实例化的CRM提供来计算要获得的预期收益。 数据处理系统输出一个客户关系管理提供实例和最大化预期收益的客户目标列表。
-
4.发明授权Methods and apparatus for generating dialog state conditioned language models 有权用于生成对话状态条件语言模型的方法和装置公开(公告)号：US07542901B2
公开(公告)日：2009-06-02
申请号：US11509390
申请日：2006-08-24
申请人： Satyanarayana Dharanipragada , Michael Daniel Monkowski , Harry W. Printz , Karthik Visweswariah
发明人： Satyanarayana Dharanipragada , Michael Daniel Monkowski , Harry W. Printz , Karthik Visweswariah
CPC分类号： G10L15/197 , G10L15/183 , G10L2015/228
摘要： Techniques are provided for generating improved language modeling. Such improved modeling is achieved by conditioning a language model on a state of a dialog for which the language model is employed. For example, the techniques of the invention may improve modeling of language for use in a speech recognizer of an automatic natural language based dialog system. Improved usability of the dialog system arises from better recognition of a user's utterances by a speech recognizer, associated with the dialog system, using the dialog state-conditioned language models. By way of example, the state of the dialog may be quantified as: (i) the internal state of the natural language understanding part of the dialog system; or (ii) words in the prompt that the dialog system played to the user.
摘要翻译： 提供了用于生成改进的语言建模的技术。 通过对使用语言模型的对话框的状态调节语言模型来实现这种改进的建模。 例如，本发明的技术可以改进用于基于自动语言的对话系统的语音识别器中使用的语言建模。 对话系统的可用性的提高是由使用对话状态条件语言模型更好地识别与对话系统相关联的语音识别器的用户话语。 作为示例，对话的状态可以量化为：（i）对话系统的自然语言理解部分的内部状态; 或（ii）对话系统向用户播放的提示中的单词。
-
5.发明申请Methods and Apparatus for Generating Dialog State Conditioned Language Models 有权用于生成对话状态条件语言模型的方法和装置公开(公告)号：US20080215329A1
公开(公告)日：2008-09-04
申请号：US12057646
申请日：2008-03-28
申请人： Satyanarayana Dharanipragada , Michael Daniel Monkowski , Harry W. Printz , Karthik Visweswariah
发明人： Satyanarayana Dharanipragada , Michael Daniel Monkowski , Harry W. Printz , Karthik Visweswariah
IPC分类号： G10L15/28
CPC分类号： G10L15/197 , G10L15/183 , G10L2015/228
摘要： Techniques are provided for generating improved language modeling. Such improved modeling is achieved by conditioning a language model on a state of a dialog for which the language model is employed. For example, the techniques of the invention may improve modeling of language for use in a speech recognizer of an automatic natural language based dialog system. Improved usability of the dialog system arises from better recognition of a user's utterances by a speech recognizer, associated with the dialog system, using the dialog state-conditioned language models. By way of example, the state of the dialog may be quantified as: (i) the internal state of the natural language understanding part of the dialog system; or (ii) words in the prompt that the dialog system played to the user.
摘要翻译： 提供了用于生成改进的语言建模的技术。 通过对使用语言模型的对话框的状态调节语言模型来实现这种改进的建模。 例如，本发明的技术可以改进用于基于自动语言的对话系统的语音识别器中使用的语言建模。 对话系统的可用性的提高源自使用对话状态条件语言模型更好地识别与对话系统相关联的语音识别器的用户话语。 作为示例，对话的状态可以量化为：（i）对话系统的自然语言理解部分的内部状态; 或（ii）对话系统向用户播放的提示中的单词。
-
6.发明授权User interface for managing questions and answers across multiple social media data sources 有权用于管理多个社交媒体数据源的问题和答案的用户界面公开(公告)号：US09026916B2
公开(公告)日：2015-05-05
申请号：US13167452
申请日：2011-06-23
CPC分类号： G06Q50/01 , G06F17/21 , G06F17/2785 , G06Q10/10
摘要： A method for managing user-generated questions and answers across multiple social media data sources can begin with the receiving of query parameters, including a user-entered question, via the user interface of a social media Q&A manage. Social media data sources can be queried for knowledge related to the user-entered question. When knowledge related to the user-entered question exists, the existing related knowledge can be organized and presented in the user interface according to a determined answer quality. When knowledge related to the user-entered question does not exist or is deemed unsatisfactory by a user, the user-entered question can be automatically submitted to applicable social media data sources by the social media Q&A manager on behalf of the user. A status of the submitted user-entered question can be monitored. When the status of the submitted user-entered question changes, the method can be re-executed at the querying step.
摘要翻译： 用于管理多个社交媒体数据源的用户生成的问题和答案的方法可以从通过社交媒体问答管理的用户界面接收查询参数（包括用户输入的问题）开始。 社会媒体资料来源可以查询与用户输入的问题有关的知识。 当存在与用户输入问题相关的知识时，可以根据确定的答案质量在用户界面中组织和呈现现有的相关知识。 当与用户输入的问题相关的知识不存在或被用户认为不令人满意时，用户输入的问题可以由社交媒体问答经理代表用户自动提交给适用的社交媒体数据源。 可以监视提交的用户输入的问题的状态。 当提交的用户输入的问题的状态改变时，该方法可以在查询步骤重新执行。
-
公开(公告)号：US08903844B2
公开(公告)日：2014-12-02
申请号：US13598262
申请日：2012-08-29
IPC分类号： G06F17/30
CPC分类号： G06F17/30389
摘要： Methods and arrangements for providing interactive query suggestions. A partial user query phrase is received, the partial query phrase comprising a final word element. A vocabulary is accessed and, from the vocabulary, at least one possible completion of the final word element is ascertained. A phrase index is accessed and, from the phrase index, at least two phrases corresponding to completions of the partial user query phrase with the at least one possible completion of the final word element are ascertained. A probability score is assigned to each of the at least two phrases, and the at least two phrases are ranked based on probability.
摘要翻译： 提供交互式查询建议的方法和安排。 接收到部分用户查询短语，该部分查询短语包括最后的单词元素。 访问词汇表，并从词汇中确定最终单词元素的至少一个可能的完成。 访问短语索引，并且从短语索引中确定与部分用户查询短语的完成相对应的至少两个短语与所述最终单词的至少一个可能的完成。 向所述至少两个短语中的每一个分配概率分数，并且基于概率对所述至少两个短语进行排名。
-
8.发明授权Methods and arrangements for providing effective interactive query suggestions without query logs 有权提供无需查询日志的有效交互式查询建议的方法和安排公开(公告)号：US08898182B2
公开(公告)日：2014-11-25
申请号：US13094995
申请日：2011-04-27
IPC分类号： G06F17/30
CPC分类号： G06F17/30389
摘要： Methods and arrangements for providing interactive query suggestions. A partial user query phrase is received, the partial query phrase comprising a final word element. A vocabulary is accessed and, from the vocabulary, at least one possible completion of the final word element is ascertained. A phrase index is accessed and, from the phrase index, at least two phrases corresponding to completions of the partial user query phrase with the at least one possible completion of the final word element are ascertained. A probability score is assigned to each of the at least two phrases, and the at least two phrases are ranked based on probability.
摘要翻译： 提供交互式查询建议的方法和安排。 接收到部分用户查询短语，该部分查询短语包括最后的单词元素。 访问词汇表，并从词汇中确定最终单词元素的至少一个可能的完成。 访问短语索引，并且从短语索引中确定与部分用户查询短语的完成相对应的至少两个短语与所述最终单词的至少一个可能的完成。 向所述至少两个短语中的每一个分配概率分数，并且基于概率对所述至少两个短语进行排名。
-
公开(公告)号：US08768921B2
公开(公告)日：2014-07-01
申请号：US13277307
申请日：2011-10-20
申请人： Sugata Ghosal , Anup K. Ghosh , Nandakishore Kambhatla , Rose C. Kanjirathinkal , Asidhara Lahiri , Debapriyo Majumdar , Shajith I. Mohamed , Karthik Visweswariah
发明人： Sugata Ghosal , Anup K. Ghosh , Nandakishore Kambhatla , Rose C. Kanjirathinkal , Asidhara Lahiri , Debapriyo Majumdar , Shajith I. Mohamed , Karthik Visweswariah
CPC分类号： G06F17/30693 , G06F11/0781 , G06F17/30303 , G06F17/3053
摘要： Embodiments of the present invention relate to an approach for reusing information/knowledge. Specifically, embodiments of the present invention provide an approach for retrieving previously stored data to satisfy queries (e.g., jobs/tickets) for solutions to problems while maintaining privacy/security of the data as well as ensuring the quality of the results. In a typical embodiment, a query for a solution to a problem is received and details are extracted therefrom. Using the details, a search is performed on a set of data stored in at least one computer storage device. Based on the search, a set of results will be generated and classified into a set of categories. In any event, the quality of each of the set of results will be assessed based on the usefulness of the set of results.
摘要翻译： 本发明的实施例涉及一种重用信息/知识的方法。 具体地，本发明的实施例提供了一种用于检索先前存储的数据以满足针对问题的解决方案的查询（例如，作业/票证）的方法，同时保持数据的隐私/安全性以及确保结果的质量。 在典型的实施例中，接收到对问题的解决方案的查询，并从中提取细节。 使用细节，对存储在至少一个计算机存储设备中的一组数据执行搜索。 基于搜索，将生成一组结果并将其分类为一组类别。 无论如何，将根据一组结果的有用性来评估每组结果的质量。
-
10.发明申请公开(公告)号：US20120323952A1
公开(公告)日：2012-12-20
申请号：US13598262
申请日：2012-08-29
IPC分类号： G06F17/30
CPC分类号： G06F17/30389
摘要： Methods and arrangements for providing interactive query suggestions. A partial user query phrase is received, the partial query phrase comprising a final word element. A vocabulary is accessed and, from the vocabulary, at least one possible completion of the final word element is ascertained. A phrase index is accessed and, from the phrase index, at least two phrases corresponding to completions of the partial user query phrase with the at least one possible completion of the final word element are ascertained. A probability score is assigned to each of the at least two phrases, and the at least two phrases are ranked based on probability.
摘要翻译： 提供交互式查询建议的方法和安排。 接收到部分用户查询短语，该部分查询短语包括最后的单词元素。 访问词汇表，并从词汇中确定最终单词元素的至少一个可能的完成。 访问短语索引，并且从短语索引中确定与部分用户查询短语的完成相对应的至少两个短语与所述最终单词的至少一个可能的完成。 向所述至少两个短语中的每一个分配概率分数，并且基于概率对所述至少两个短语进行排名。
-
-
-
-
-
-
-
-
-
搜索结果
43 条记录 (耗时 0.026 秒)
