公开(公告)号：US20140122507A1

公开(公告)日：2014-05-01

申请号：US14114277

申请日：2011-04-29

申请人： Cheng Zeng ,  Jian Wang ,  Liang Hong ,  Jilei Tian ,  Xiaogang Yang ,  Huanhuan Cao

发明人： Cheng Zeng ,  Jian Wang ,  Liang Hong ,  Jilei Tian ,  Xiaogang Yang ,  Huanhuan Cao

IPC分类号： G06F17/30

CPC分类号： G06F17/30867 ,  G06F17/30528 ,  G06Q30/0282

摘要： An approach is provided for providing recommendations to a user based on user's role derived from the context information and an advanced user profile. A recommendation platform processes context information to determine one or more roles associated with a user. Next, the recommendation platform calculates at least one level of similarity between the one or more roles and one or more other roles associated with one or more other users. Then, the recommendation platform determines recommendation information associated with the one or more other users based, at least in part, on the at least one level of similarity. Next, the recommendation platform processes the recommendation information to generate one or more recommendations for the user.

摘要翻译： 提供了一种基于从上下文信息和高级用户简档导出的用户角色向用户提供建议的方法。 推荐平台处理上下文信息以确定与用户相关联的一个或多个角色。 接下来，推荐平台计算一个或多个角色与与一个或多个其他用户相关联的一个或多个其他角色之间的至少一个相似度水平。 然后，所述推荐平台至少部分地基于所述至少一个相似度来确定与所述一个或多个其他用户相关联的推荐信息。 接下来，推荐平台处理推荐信息以为用户生成一个或多个推荐。

公开(公告)号：US20130273976A1

公开(公告)日：2013-10-17

申请号：US13881517

申请日：2010-10-27

申请人： Jinghai Rao ,  Jilei Tian ,  Ye Tian ,  Guan Wang

发明人： Jinghai Rao ,  Jilei Tian ,  Ye Tian ,  Guan Wang

IPC分类号： G06F17/27

CPC分类号： G06F17/2785 ,  H04L12/1822 ,  H04W4/12

摘要： Techniques for identifying conversations in multiple short strings include determining from a first plurality of strings associated with a first contact of a user, based on time separations between successive strings, a first conversation portion and a different second conversation portion. The first conversation portion (snippet) comprises a plurality of strings of the first plurality; and the second snippet comprises a different pluralty of strings of the first plurality. A first semantic content for the first snippet and a second semantic content for the second snippet are determined. It is determined whether to merge the first snippet and the second snippet into a first conversation that includes the first snippet based, at least in part, on a similarity of the first semantic content to the second semantic content.

摘要翻译： 用于识别多个短串中的会话的技术包括基于与连续字符串之间的时间间隔，第一对话部分和不同的第二对话部分之间的与用户的第一接触相关联的第一多个字符串来确定。 第一会话部分（片段）包括多个第一组的串; 并且第二片段包括第一多个的不同的多个字符串。 确定第一片段的第一语义内容和第二片段的第二语义内容。 至少部分地基于第一语义内容与第二语义内容的相似性来确定是否将第一代码段和第二代码段合并到包括第一代码片段的第一对话中。

公开(公告)号：US20130268485A1

公开(公告)日：2013-10-10

申请号：US13994832

申请日：2010-12-23

申请人： Huanhuan Cao ,  Jilei Tian

发明人： Huanhuan Cao ,  Jilei Tian

IPC分类号： G06F17/30

CPC分类号： G06F16/21 ,  G06F8/60 ,  G06F16/23 ,  G06F16/9535

摘要： An apparatus for automatically recognizing the semantics of one or more mobile applications may include a processor and a memory storing executable computer program code that cause the apparatus to at least perform operations including receiving an indication of a selection of at least one mobile application. The computer program code may further cause the apparatus to enable provision of a request, to a device, requesting the device to search indicia associated with the selected mobile application in an instance in which a determination indicates that the selected mobile application is not identified in an application mapping list. The computer program code may further cause the apparatus to assign a semantic tag to the selected mobile application based in part on data associated with a description generated based in part by extracting content from one or more results of the search. Corresponding methods and computer program products are also provided,

摘要翻译： 用于自动识别一个或多个移动应用的语义的装置可以包括处理器和存储可执行计算机程序代码的存储器，该存储器使得该装置至少执行操作，包括接收对至少一个移动应用的选择的指示。 计算机程序代码还可以使设备能够向设备提供请求设备在与所选择的移动应用相关联的标记中提供请求，其中确定指示所选择的移动应用未被标识在所选择的移动应用中 应用程序映射列表。 计算机程序代码还可以使得设备部分地基于与基于部分地通过从搜索的一个或多个结果提取内容而生成的描述相关联的数据来为所选择的移动应用分配语义标签。 还提供了相应的方法和计算机程序产品，

公开(公告)号：US20130013308A1

公开(公告)日：2013-01-10

申请号：US13634811

申请日：2010-03-23

申请人： Yang Cao ,  Feng Ding ,  Jilei Tian

发明人： Yang Cao ,  Feng Ding ,  Jilei Tian

IPC分类号： G10L15/00

CPC分类号： G06Q30/0271 ,  G06Q30/0267

摘要： An approach is provided for determining a user age range. An age estimator causes, at least in part, acquisition of voice data. Next, the age estimator calculates a first set of probability values, wherein each of the probability values represents a probability that the voice data is in a respective one of a plurality of predefined age ranges, and the predefined age ranges are segments of a lifespan. Then, the age estimator derives a second set of probability values by applying a correlation matrix to the first set of probability values, wherein the correlation matrix associates the first set of probability values with probabilities of the voice data matching individual ages over the lifespan. Then, the age estimator, for each of the predefined age ranges, calculates a sum of the probabilities in the second set of probability values corresponding to the individual ages within the respective predefined age ranges. Further, the age estimator determines the predefined age range to associate with the voice data based, at least in part, on the calculated sums of the probabilities.

摘要翻译： 提供了一种用于确定用户年龄范围的方法。 年龄估计器至少部分地导致获取语音数据。 接下来，年龄估计器计算第一组概率值，其中每个概率值表示语音数据在多个预定义年龄范围中的相应一个中的概率，并且预定义的年龄段是寿命段。 然后，年龄估计器通过将相关矩阵应用于第一组概率值来导出第二组概率值，其中相关矩阵将第一组概率值与在寿命期间匹配个体年龄的语音数据的概率相关联。 然后，对于每个预定义的年龄范围，年龄估计器计算对应于各个预定年龄范围内的各个年龄的第二组概率值中的概率之和。 此外，年龄估计器至少部分地基于计算出的概率的和来确定与语音数据相关联的预定年龄范围。

公开(公告)号：US07716049B2

公开(公告)日：2010-05-11

申请号：US11427954

申请日：2006-06-30

申请人： Jilei Tian

发明人： Jilei Tian

IPC分类号： G10L15/04 ,  G10L15/06 ,  G10L15/18

CPC分类号： G10L15/197

摘要： An apparatus for providing adaptive language model scaling includes an adaptive scaling element and an interface element. The adaptive scaling element is configured to receive input speech comprising a sequence of spoken words and to determine a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words. Each corresponding sentence score is calculated using an adaptive scaling factor. The interface element is configured to receive a user input selecting one of the candidate sequences. The adaptive scaling element is further configured to estimate an objective function based on the user input and to modify the adaptive scaling factor based on the estimated objective function.

摘要翻译： 用于提供自适应语言模型缩放的装置包括自适应缩放元素和接口元素。 自适应缩放元件被配置为接收包括一系列口语单词的输入语音，并且确定多个候选序列的文本单词，其中候选序列中的每一个具有相应的句子分数，表示候选序列与 口语 使用自适应缩放因子计算每个相应的句子得分。 接口元件被配置为接收选择候选序列之一的用户输入。 自适应缩放元件还被配置为基于用户输入来估计目标函数，并且基于估计的目标函数修改自适应缩放因子。

公开(公告)号：US20070256189A1

公开(公告)日：2007-11-01

申请号：US11380289

申请日：2006-04-26

申请人： Jilei Tian ,  Jani Nurminen ,  Victor Popa

发明人： Jilei Tian ,  Jani Nurminen ,  Victor Popa

IPC分类号： C12N15/82 ,  C12N15/87

CPC分类号： G10L13/033 ,  G10L2021/0135

摘要： Systems and methods are provided for performing soft alignment in Gaussian mixture model (GMM) based and other vector transformations. Soft alignment may assign alignment probabilities to source and target feature vector pairs. The vector pairs and associated probabilities may then be used calculate a conversion function, for example, by computing GMM training parameters from the joint vectors and alignment probabilities to create a voice conversion function for converting speech sounds from a source speaker to a target speaker.

摘要翻译： 提供了系统和方法，用于在基于高斯混合模型（GMM）和其他矢量变换中执行软对齐。 软对齐可以将对齐概率分配给源和目标特征向量对。 然后可以使用矢量对和相关联的概率来计算转换函数，例如通过从联合向量计算GMM训练参数和对齐概率来创建用于将语音从源扬声器转换为目标扬声器的语音转换功能。

公开(公告)号：US20070233625A1

公开(公告)日：2007-10-04

申请号：US11396831

申请日：2006-04-03

申请人： Jilei Tian ,  Jani Nurminen ,  Victor Popa

发明人： Jilei Tian ,  Jani Nurminen ,  Victor Popa

IPC分类号： G06F15/18

CPC分类号： G06K9/628 ,  G06N99/005 ,  G10L21/007

摘要： An apparatus for providing data clustering and mode selection includes a training element and a transformation element. The training element is configured to receive a first training data set, a second training data set and auxiliary data extracted from the same material as the first training data set. The training element is also configured to train a classifier to group the first training data set into M clusters based on the auxiliary data and the first training data set and train M processing schemes corresponding to the M clusters for transforming the first training data set into the second training data set. The transformation element is in communication with the training element and is configured to cluster the second training data set into M clusters based on features associated with the second training data set.

摘要翻译： 一种用于提供数据聚类和模式选择的装置包括训练元素和变换元素。 训练元件被配置为接收从与第一训练数据集相同的材料提取的第一训练数据集，第二训练数据集和辅助数据。 训练元素还被配置为训练分类器，以基于辅助数据和第一训练数据集以及对应于M个簇的训练M个处理方案将第一训练数据集合分组成M个群集，以将第一训练数据集变换为 第二训练数据集。 转换元件与训练元素通信，并且被配置为基于与第二训练数据集相关联的特征将第二训练数据集聚集成M个群集。

公开(公告)号：US20060167680A1

公开(公告)日：2006-07-27

申请号：US11042445

申请日：2005-01-25

申请人： Jilei Tian ,  Jani Nurminen

发明人： Jilei Tian ,  Jani Nurminen

IPC分类号： G06F17/21

CPC分类号： G06F17/2735 ,  G06F9/454 ,  G06F17/2223

摘要： A system and method of extracting information from a lexicon and using the information with a computer software program. Lexicon data is arranged for a particular language using Unicode values or other uniquely defined code values for each character of word of the language. A location array is then created for the lexicon data arranged by Unicode value or other uniquely defined code value. Upon a request to search for a word, words that have the same initial character as the searched-for word are identified using the location array. The identified words are then searched for an identified word that matches the searched-for word. Therefore, the amount of data loaded into run-time memory is minimized, and searches for a given word are completely more quickly than in conventional systems.

摘要翻译： 从词汇提取信息并使用计算机软件程序使用信息的系统和方法。 针对特定语言的Lexicon数据使用Unicode值或其他唯一定义的代码值针对该语言的每个字符。 然后为由Unicode值或其他唯一定义的代码值排列的词典数据创建位置数组。 在搜索单词的请求时，使用位置数组来识别具有与搜索词相同的初始字符的单词。 然后搜索所识别的单词与搜索词匹配的识别词。 因此，加载到运行时存储器中的数据量最小化，并且搜索给定单词比在常规系统中更快。

公开(公告)号：US09916363B2

公开(公告)日：2018-03-13

申请号：US14112090

申请日：2011-04-19

申请人： Jilei Tian ,  Shaowei Jiang ,  Xinxing Yang ,  Dong Liu ,  Hao Yang

发明人： Jilei Tian ,  Shaowei Jiang ,  Xinxing Yang ,  Dong Liu ,  Hao Yang

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/3053 ,  G06F17/30522 ,  G06F17/3064 ,  G06F17/30648 ,  G06F17/30867

摘要： An approach is provided for diversifying recommendation results. A diversification manager determines one or more recommendation scores associated with one or more items. The one or more recommendation scores are for determining a sort order of the one or more items. The diversification manager then determines similarity information associated with the one or more items, and processes and/or facilitates a processing of the similarity information to cause, at least in part, an adjustment of the one or more recommendation scores, the sort order, or a combination thereof.

公开(公告)号：US09881092B2

公开(公告)日：2018-01-30

申请号：US14114277

申请日：2011-04-29

申请人： Cheng Zeng ,  Jian Wang ,  Liang Hong ,  Jilei Tian ,  Xiaogang Yang ,  Huanhuan Cao

发明人： Cheng Zeng ,  Jian Wang ,  Liang Hong ,  Jilei Tian ,  Xiaogang Yang ,  Huanhuan Cao

IPC分类号： G06F17/30 ,  G06Q30/02

CPC分类号： G06F17/30867 ,  G06F17/30528 ,  G06Q30/0282

摘要： An example approach is provided for providing recommendations to a user based on user's role derived from the context information and an advanced user profile. A recommendation platform processes context information to determine one or more roles associated with a user. Next, the recommendation platform calculates at least one level of similarity between the one or more roles and one or more other roles associated with one or more other users. Then, the recommendation platform determines recommendation information associated with the one or more other users based, at least in part, on the at least one level of similarity. Next, the recommendation platform processes the recommendation information to generate one or more recommendations for the user.