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

US20160313868A1 System and Method for Dialog-Enabled Context-Dependent and User-Centric Content Presentation 审中-公开
标题翻译：具有对话框的上下文相关性和以用户为中心的内容呈现的系统和方法
公开(公告)号：US20160313868A1
公开(公告)日：2016-10-27
申请号：US15104695
申请日：2014-12-11
申请人： Fuliang Weng , Kui Xu , Fel Liu , Lin Zhao , Zhe Feng , Zhongnan Shen , ROBERT BOSCH GMBH
发明人： Fuliang Weng , Kui Xu , Fel Liu , Lin Zhao , Zhe Feng , Zhongnan Shen
IPC分类号： G06F3/0481 , B60K35/00 , H04L29/06 , H04L29/08 , G10L15/22 , G06F3/01
CPC分类号： G06F3/0481 , B60K35/00 , B60K2350/1028 , B60K2350/1044 , B60K2350/1052 , B60K2350/2052 , B60K2350/901 , B60K2350/962 , G06F3/017 , G06F3/04883 , G06F9/451 , G06F2203/0381 , G06Q30/02 , G10L15/22 , H04L65/4069 , H04L67/12
摘要： An in-vehicle infotainment system, smart home information access and device control unit, or mobile system presents summarized information to a user based on a user preference model that is associated with the user. The system modifies the presentation of information to the user based on environmental context data about the vehicle and user context data about the activity of the user. During presentation of the information, the system modifies the content and presentation of the summarized information in response to multi-modal input requests from the user.
摘要翻译：车载信息娱乐系统，智能家居信息访问和设备控制单元或移动系统基于与用户相关联的用户偏好模型向用户呈现总结信息。系统基于关于车辆的环境上下文数据和关于用户的活动的用户上下文数据来向用户修改信息呈现。在呈现信息期间，系统响应于来自用户的多模式输入请求来修改总结信息的内容和呈现。

2. 发明授权

US10209853B2 System and method for dialog-enabled context-dependent and user-centric content presentation 有权
公开(公告)号：US10209853B2
公开(公告)日：2019-02-19
申请号：US15104695
申请日：2014-12-11
申请人： Robert Bosch GmbH , Fuliang Weng , Kui Xu , Fei Liu , Lin Zhao , Zhe Feng , Zhongnan Shen
发明人： Fuliang Weng , Kui Xu , Fei Liu , Lin Zhao , Zhe Feng , Zhongnan Shen
IPC分类号： G06F3/0481 , G06F9/451 , G06F3/01 , G06Q30/02 , G10L15/22 , G06F3/0488 , B60K35/00 , H04L29/06 , H04L29/08
摘要： An in-vehicle infotainment system, smart home information access and device control unit, or mobile system presents summarized information to a user based on a user preference model that is associated with the user. The system modifies the presentation of information to the user based on environmental context data about the vehicle and user context data about the activity of the user. During presentation of the information, the system modifies the content and presentation of the summarized information in response to multi-modal input requests from the user.

3. 发明授权

US08972260B2 Speech recognition using multiple language models 有权
标题翻译：多语言模型的语音识别
公开(公告)号：US08972260B2
公开(公告)日：2015-03-03
申请号：US13450861
申请日：2012-04-19
申请人： Fuliang Weng , Zhe Feng , Kui Xu , Lin Zhao
发明人： Fuliang Weng , Zhe Feng , Kui Xu , Lin Zhao
IPC分类号： G10L15/00 , G10L15/32 , G10L15/06 , G10L15/18 , G10L15/193 , G10L15/197 , G10L15/30
CPC分类号： G10L15/32 , G10L15/063 , G10L15/18 , G10L15/193 , G10L15/197 , G10L15/30
摘要： In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.
摘要翻译：根据一个实施例，一种生成用于语音识别的语言模型的方法包括：识别与语音相对应的训练数据中的多个话语，产生多个话语中的每个发声的频率计数，从多个话语中产生高频多个话语所述多个话音具有超过预定频率阈值的频率，从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语，使用所述高频率生成基于语法的语言模型多个话语作为训练数据，并且使用低频多个话语生成统计语言模型作为训练数据。

4. 发明申请

US20120271631A1 SPEECH RECOGNITION USING MULTIPLE LANGUAGE MODELS 有权
标题翻译：使用多种语言模型进行语音识别
公开(公告)号：US20120271631A1
公开(公告)日：2012-10-25
申请号：US13450861
申请日：2012-04-19
申请人： Fuliang Weng , Zhe Feng , Kui Xu , Lin Zhao
发明人： Fuliang Weng , Zhe Feng , Kui Xu , Lin Zhao
IPC分类号： G10L15/06
CPC分类号： G10L15/32 , G10L15/063 , G10L15/18 , G10L15/193 , G10L15/197 , G10L15/30
摘要： In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.
摘要翻译：根据一个实施例，一种生成用于语音识别的语言模型的方法包括：识别与语音相对应的训练数据中的多个话语，产生多个话语中的每个发声的频率计数，从多个话语中产生高频多个话语所述多个话音具有超过预定频率阈值的频率，从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语，使用所述高频率生成基于语法的语言模型多个话语作为训练数据，并且使用低频多个话语生成统计语言模型作为训练数据。

5. 发明授权

US11783179B2 System and method for domain- and language-independent definition extraction using deep neural networks 有权
公开(公告)号：US11783179B2
公开(公告)日：2023-10-10
申请号：US16958892
申请日：2018-12-27
申请人： Robert Bosch GmbH , Lin Zhao , Kui Xu , Zhe Feng
发明人： Yifan He , Lin Zhao , Kui Xu , Zhe Feng
IPC分类号： G06F17/00 , G06N3/08 , G06F40/237 , G06N3/042 , G06N3/044 , G06N3/045 , G06F16/36 , G06F40/247 , G06F40/279
CPC分类号： G06N3/08 , G06F16/367 , G06F40/237 , G06N3/042 , G06N3/044 , G06N3/045 , G06F40/247 , G06F40/279
摘要： A method of automatically generating a terminology definition knowledge base (KB) includes mapping each word in a word sequence to a real value dense vector using dense vector representations. The word sequence is then processed using a Convolutional Neural Network (CNN) model to identify whether the word sequence includes a terminology definition and to label the word sequence with a label indicating whether a terminology definition exists within the word sequence. The word sequence is then processed using a Conditional Random Field (CRF) model to identify boundaries of the terminology definition in the word sequence. The terminology definition is then extracted and added to the terminology definition KB.

6. 发明授权

US08700403B2 Unified treatment of data-sparseness and data-overfitting in maximum entropy modeling 有权
标题翻译：在最大熵建模中统一处理数据稀疏和数据过拟合
公开(公告)号：US08700403B2
公开(公告)日：2014-04-15
申请号：US11266867
申请日：2005-11-03
申请人： Fuliang Weng , Lin Zhao
发明人： Fuliang Weng , Lin Zhao
IPC分类号： G10L15/14 , G06F17/28 , G06F17/27 , G06F17/21 , G10L15/26 , G10L19/14 , G10L21/06
CPC分类号： G10L15/197 , G06F17/2715 , G06F17/278 , G10L15/183
摘要： A method of statistical modeling is provided which includes constructing a statistical model and incorporating Gaussian priors during feature selection and during parameter optimization for the construction of the statistical model.
摘要翻译：提供了一种统计建模方法，包括构建统计模型，并在特征选择期间和参数优化期间并入高斯先验，以构建统计模型。

7. 发明申请

US20070100624A1 Unified treatment of data-sparseness and data-overfitting in maximum entropy modeling 有权
标题翻译：在最大熵建模中统一处理数据稀疏和数据过拟合
公开(公告)号：US20070100624A1
公开(公告)日：2007-05-03
申请号：US11266867
申请日：2005-11-03
申请人： Fuliang Weng , Lin Zhao
发明人： Fuliang Weng , Lin Zhao
IPC分类号： G10L15/18
CPC分类号： G10L15/197 , G06F17/2715 , G06F17/278 , G10L15/183
摘要： A method of statistical modeling is provided which includes constructing a statistical model and incorporating Gaussian priors during feature selection and during parameter optimization for the construction of the statistical model.
摘要翻译：提供了一种统计建模方法，包括构建统计模型，并在特征选择期间和参数优化过程中并入高斯先验，以构建统计模型。

8. 发明申请

US20060015484A1 Method and apparatus for providing proper or partial proper name recognition 有权
标题翻译：提供正确或部分正确名称识别的方法和装置
公开(公告)号：US20060015484A1
公开(公告)日：2006-01-19
申请号：US10892724
申请日：2004-07-15
申请人： Fuliang Weng , Lin Zhao
发明人： Fuliang Weng , Lin Zhao
IPC分类号： G06F17/30 , G06F17/27 , G06F7/00
CPC分类号： G06F17/278
摘要： A method of proper name recognition includes classifying each word of a word string with a tag indicating a proper name entity category or a non-named entity category, and correcting the tag of a boundary word of the word string.
摘要翻译：正确名称识别的方法包括用指示正确名称实体类别或非命名实体类别的标签对单词串的每个单词进行分类，以及校正字串的边界字的标签。

9. 发明授权

US07865356B2 Method and apparatus for providing proper or partial proper name recognition 有权
标题翻译：提供正确或部分正确名称识别的方法和装置
公开(公告)号：US07865356B2
公开(公告)日：2011-01-04
申请号：US10892724
申请日：2004-07-15
申请人： Fuliang Weng , Lin Zhao
发明人： Fuliang Weng , Lin Zhao
IPC分类号： G06F17/27
CPC分类号： G06F17/278
摘要： A method of proper name recognition includes classifying each word of a word string with a tag indicating a proper name entity category or a non-named entity category, and correcting the tag of a boundary word of the word string.
摘要翻译：正确名称识别的方法包括用指示正确名称实体类别或非命名实体类别的标签对单词串的每个单词进行分类，以及校正字串的边界字的标签。

10. 发明授权

US11036774B2 Knowledge-based question answering system for the DIY domain 有权
公开(公告)号：US11036774B2
公开(公告)日：2021-06-15
申请号：US16151835
申请日：2018-10-04
申请人： Robert Bosch GmbH
发明人： Lin Zhao , Zhe Feng , Doo Soon Kim
IPC分类号： G06F16/00 , G06N5/00 , G06F16/332 , G06F16/33 , G06F16/9535 , G06N5/02 , G06F16/242 , G06F16/36 , G06F16/9032 , G06F40/56
摘要： DIY (Do-It-Yourself) is challenging for many novices, requiring extensive knowledge such as the usage of particular tools and the properties of the required materials. Many DIYers use web searches to find relevant information and instructions, but web search is time-consuming and the results often do not fit the DIYers' specific needs. To address these problems, we present a Question Answering (QA) system that can assist DIYers through the whole cycle of a DIY project. Given a natural language question about a DIY project, the QA system described herein provides an answer along with the explanations that are tailored to the DIYers' specific needs.

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