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. 发明申请

US20110270771A1 System and method for a flexible management of the escalation of support for devices 审中-公开
标题翻译：系统和方法灵活地管理对设备的支持升级
公开(公告)号：US20110270771A1
公开(公告)日：2011-11-03
申请号：US12772692
申请日：2010-05-03
申请人： Jean-Marc Coursimault , Maria Antonietta Grasso , Frederic Roulland , Stefania Castellani
发明人： Jean-Marc Coursimault , Maria Antonietta Grasso , Frederic Roulland , Stefania Castellani
IPC分类号： G06Q10/00
CPC分类号： H04N1/00344 , G06Q10/06 , G06Q10/10 , G06Q30/016 , H04N2201/0082 , H04N2201/0098
摘要： A system and method are disclosed for determining when to escalate from one support level to a higher support level in assisting a user resolve a problem with a device. The method includes storing information on past users' interactions with a self help server during prior self help sessions, the self help server providing a first remote support level for troubleshooting a problem with a device. Information is stored on a current user's interactions with the self help server during a current self help session for troubleshooting the current user's problem with a device. A determination of when to provide for escalation to a higher remote support level for troubleshooting the current user's problem with the device is based on the stored information on the past users' interactions and the current user's interactions.
摘要翻译：公开了一种用于确定何时从一个支持级别升级到更高支持级别以帮助用户解决设备问题的系统和方法。该方法包括在先前的自助会话期间存储关于过去用户与自助服务器的交互的信息，自助服务器提供用于对设备的问题进行故障排除的第一远程支持级别。在当前的自助会话期间，信息存储在当前用户与自助服务器的交互中，以对当前用户的设备问题进行故障排除。确定什么时候提供升级到更高的远程支持级别，以排除当前用户的设备问题，这是基于存储的关于过去用户交互的信息和当前用户的交互。

2. 发明授权

US09552355B2 Dynamic bi-phrases for statistical machine translation 有权
标题翻译：用于统计机器翻译的动态双语短语
公开(公告)号：US09552355B2
公开(公告)日：2017-01-24
申请号：US12784040
申请日：2010-05-20
申请人： Marc Dymetman , Wilker Ferreira Aziz , Nicola Cancedda , Jean-Marc Coursimault , Vassilina Nikoulina , Lucia Specia
发明人： Marc Dymetman , Wilker Ferreira Aziz , Nicola Cancedda , Jean-Marc Coursimault , Vassilina Nikoulina , Lucia Specia
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2818
摘要： A system and a method for phrase-based translation are disclosed. The method includes receiving source language text to be translated into target language text. One or more dynamic bi-phrases are generated, based on the source text and the application of one or more rules, which may be based on user descriptions. A dynamic feature value is associated with each of the dynamic bi-phrases. For a sentence of the source text, static bi-phrases are retrieved from a bi-phrase table, each of the static bi-phrases being associated with one or more values of static features. Any of the dynamic bi-phrases which each cover at least one word of the source text are also retrieved, which together form a set of active bi-phrases. Translation hypotheses are generated using active bi-phrases from the set and scored with a translation scoring model which takes into account the static and dynamic feature values of the bi-phrases used in the respective hypothesis. A translation, based on the hypothesis scores, is then output.
摘要翻译：公开了一种用于基于短语的翻译的系统和方法。该方法包括接收要翻译成目标语言文本的源语言文本。基于可以基于用户描述的一个或多个规则的源文本和应用来生成一个或多个动态双词组。动态特征值与每个动态双词组相关联。对于源文本的句子，从双词表检索静态双词组，每个静态双词组与一个或多个静态特征值相关联。还检索了每个覆盖源文本的至少一个单词的动态双词组，其一起形成一组活动双词组。使用来自集合的活动双词组产生翻译假设，并用考虑到各自假设中使用的双词组的静态和动态特征值的翻译评分模型进行评分。然后输出基于假设分数的翻译。

3. 发明申请

US20110288852A1 DYNAMIC BI-PHRASES FOR STATISTICAL MACHINE TRANSLATION 有权
标题翻译：用于统计机器翻译的动态BI-PHRASES
公开(公告)号：US20110288852A1
公开(公告)日：2011-11-24
申请号：US12784040
申请日：2010-05-20
申请人： Marc Dymetman , Wilker Ferreira Aziz , Nicola Cancedda , Jean-Marc Coursimault , Vassilina Nikoulina , Lucia Specia
发明人： Marc Dymetman , Wilker Ferreira Aziz , Nicola Cancedda , Jean-Marc Coursimault , Vassilina Nikoulina , Lucia Specia
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2818
摘要： A system and a method for phrase-based translation are disclosed. The method includes receiving source language text to be translated into target language text. One or more dynamic bi-phrases are generated, based on the source text and the application of one or more rules, which may be based on user descriptions. A dynamic feature value is associated with each of the dynamic bi-phrases. For a sentence of the source text, static bi-phrases are retrieved from a bi-phrase table, each of the static bi-phrases being associated with one or more values of static features. Any of the dynamic bi-phrases which each cover at least one word of the source text are also retrieved, which together form a set of active bi-phrases. Translation hypotheses are generated using active bi-phrases from the set and scored with a translation scoring model which takes into account the static and dynamic feature values of the bi-phrases used in the respective hypothesis. A translation, based on the hypothesis scores, is then output.
摘要翻译：公开了一种用于基于短语的翻译的系统和方法。该方法包括接收要翻译成目标语言文本的源语言文本。基于可以基于用户描述的一个或多个规则的源文本和应用来生成一个或多个动态双词组。动态特征值与每个动态双语短语相关联。对于源文本的句子，从双词表检索静态双词组，每个静态双词组与一个或多个静态特征值相关联。还检索了每个覆盖源文本的至少一个单词的动态双词组，其一起形成一组活动双词组。使用来自集合的活动双词组产生翻译假设，并用考虑到各自假设中使用的双词组的静态和动态特征值的翻译评分模型进行评分。然后输出基于假设分数的翻译。

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