知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

294 条记录 (耗时 0.033 秒)

    SEARCH SYSTEM, SEARCH METHOD AND PROGRAM RECORDING MEDIUM
    3.
    发明申请
    SEARCH SYSTEM, SEARCH METHOD AND PROGRAM RECORDING MEDIUM 审中-公开
    搜索系统，搜索方法和程序记录介质

    公开(公告)号：US20160350416A1

    公开(公告)日：2016-12-01

    申请号：US15114930

    申请日：2015-02-09

    申请人： NEC CORPORATION

    发明人： Masato ISHII

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30743 ,  G06F17/30247 ,  G06F17/30766 ,  G06K9/6223

    摘要： Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

    摘要翻译： 提供了一种搜索系统，其被配置为基于输入向量和注册向量之间的相似度来搜索与多个注册向量中的输入向量相似的注册向量。 搜索系统包括部分相似度计算单元，其计算作为与输入向量和登记向量的一个或多个维度中的一些相关的相似度的部分相似度的程度;限制计算单元，基于 计算部分相似度的程度，计算相似度时期望的相似程度的上限;以及拒绝判定单元，根据相似度的上限判定是否拒绝 来自搜索结果候选者的注册向量。

    Method and system of iteratively autotuning prediction parameters in a media content recommender
    4.
    发明授权
    Method and system of iteratively autotuning prediction parameters in a media content recommender 有权
    在媒体内容推荐器中迭代自动调整预测参数的方法和系统

    公开(公告)号：US09495645B2

    公开(公告)日：2016-11-15

    申请号：US13954942

    申请日：2013-07-30

    申请人： concept.io, Inc.

    发明人： Dominic Hughes ,  Gurumurthy D. Ramkumar ,  Georgios Sofianatos

    IPC分类号： G06F15/18 ,  G06N99/00 ,  G06F17/30

    CPC分类号： G06N99/005 ,  G06F17/30766

    摘要： In one exemplary embodiment, a method of a computerized media-content recommender includes receiving a user-judgment score based on an historical user-listening data with respect to a media content. A first prediction score for a user with respect to the media content is calculated with a media-content recommender. The media-content recommender includes a first set of prediction parameters. A first prediction error including a difference between the user-judgment score and the first prediction score is determined. At least one parameter value of the first set of prediction parameters is modified with a machine-learning optimization technique to generate a second set of prediction parameters. A second prediction score for the user with respect to the media content is calculated with a media-content recommender. A second prediction error including a difference between the user-judgment score and the second prediction score is calculated.

    摘要翻译： 在一个示例性实施例中，计算机化媒体内容推荐器的方法包括基于关于媒体内容的历史用户收听数据来接收用户判断得分。 使用媒体内容推荐器计算用户相对于媒体内容的第一预测分数。 媒体内容推荐器包括第一组预测参数。 确定包括用户判断分数与第一预测分数之间的差的第一预测误差。 通过机器学习优化技术修改第一组预测参数的至少一个参数值，以生成第二组预测参数。 使用媒体内容推荐器计算用户相对于媒体内容的第二预测分数。 计算包括用户判断分数和第二预测分数之间的差的第二预测误差。

    Distributed user profile
    7.
    发明授权
    Distributed user profile 有权
    分布式用户配置文件

    公开(公告)号：US09338249B2

    公开(公告)日：2016-05-10

    申请号：US12066783

    申请日：2006-08-25

    申请人： Makram Bouzid ,  David Bonnefoy ,  Jerome Picault

    发明人： Makram Bouzid ,  David Bonnefoy ,  Jerome Picault

    IPC分类号： G06F17/30 ,  H04L29/08

    CPC分类号： H04L67/303 ,  G06F17/30766 ,  H04L67/10 ,  H04L67/306

    摘要： A reasoning apparatus (101) is arranged to determine device locations for user profile elements of a distributed user profile. A user profile processor (201) receives a user profile which comprises a plurality of user profile elements. Each user profile element furthermore comprises associated metadata. The apparatus (101) also comprises a device profile receiver (203) that receives device profiles for a plurality of devices. A device location processor (205) proceeds to determine device locations for the user profile elements in response to the associated metadata and the device profiles. Specifically, a user profile element may be assigned to a specific device if the device profile for that device matches the metadata for the user profile element. The reasoning apparatus (101) may furthermore comprise a user profile element synchronizer (207) which synchronizes the user profile elements with the appropriate devices.

    摘要翻译： 推理装置（101）被布置成确定分布式用户简档的用户简档元素的设备位置。 用户简档处理器（201）接收包括多个用户简档元素的用户简档。 每个用户简档元素还包括相关联的元数据。 设备（101）还包括接收多个设备的设备简档的设备简档接收器（203）。 设备位置处理器（205）继续响应于相关联的元数据和设备简档来确定用户简档元素的设备位置。 具体地说，如果该设备的设备配置文件与用户配置文件元素的元数据匹配，那么可以将用户配置文件元素分配给特定设备。 推理装置（101）还可以包括用户简档元素同步器（207），其使用户简档元素与适当的设备同步。

    Systems and methods for interactively displaying user images
    8.
    发明授权
    Systems and methods for interactively displaying user images 有权
    用于交互显示用户图像的系统和方法

    公开(公告)号：US09335895B2

    公开(公告)日：2016-05-10

    申请号：US13300403

    申请日：2011-11-18

    申请人： Daniel Kaufman

    发明人： Daniel Kaufman

    IPC分类号： G06F3/048 ,  G06F3/0482 ,  G06F3/0484 ,  G06F3/0481 ,  G06F17/30 ,  G06Q10/10

    CPC分类号： G06F3/0482 ,  G06F3/0481 ,  G06F3/0484 ,  G06F17/30265 ,  G06F17/30766 ,  G06F17/30772 ,  G06F17/30775 ,  G06Q10/10

    摘要： In accordance with the present invention, an interactive user display application is provided. The application displays and refreshes images that are intended to represent users or members of a social network or other web-based service. Using these images, the interactive user display application allows a user of the application to interact with other users or their profiles while viewing their images or while interacting with or consuming media.

    摘要翻译： 根据本发明，提供了交互式用户显示应用。 应用程序显示和刷新旨在表示用户或社交网络或其他基于Web的服务的成员的图像。 使用这些图像，交互式用户显示应用程序允许应用程序的用户在查看图像或与媒体进行交互或消费时与其他用户或其配置文件进行交互。

    System and method for generating dynamically filtered content results, including for audio and/or video channels
    9.
    发明授权
    System and method for generating dynamically filtered content results, including for audio and/or video channels 有权
    用于生成动态过滤的内容结果的系统和方法，包括用于音频和/或视频通道

    公开(公告)号：US09311364B2

    公开(公告)日：2016-04-12

    申请号：US14690686

    申请日：2015-04-20

    申请人： PORTO TECHNOLOGY, LLC

    发明人： Scott Curtis

    IPC分类号： G06F17/30 ,  G06F7/00

    CPC分类号： G06F17/3005 ,  G06F3/04817 ,  G06F3/0483 ,  G06F3/04842 ,  G06F3/04855 ,  G06F17/30038 ,  G06F17/3053 ,  G06F17/30554 ,  G06F17/30598 ,  G06F17/30749 ,  G06F17/30766 ,  G06F17/30775 ,  G06F17/30817 ,  G06F17/30828 ,  G06F17/30849 ,  G06F17/30867

    摘要： A system and method for allowing a user to more effectively generate focused content results, including audio and/or video content is described. Content is dynamically filtered to generate content results in response to initial filtering settings or characteristics. The content results are provided to a user. Once the user finds and selects a content result of interest, additional filtering characteristics associated with the selected result are provided to the user as a suggestion for additional filtering. In this manner, the user is made aware of additional filtering settings or characteristics that can be used to focus the search results. Subsequent filter settings and filtering operations can be based on characteristics of previous relevant results in an iterative and dynamic manner. Focused results are more likely produced, because additional filtering settings are provided and adjusted according to characteristics of results deemed relevant by the user.

    摘要翻译： 描述了允许用户更有效地产生包括音频和/或视频内容的聚焦内容结果的系统和方法。 动态过滤内容以响应初始过滤设置或特征生成内容结果。 内容结果被提供给用户。 一旦用户发现并选择了感兴趣的内容结果，则将与所选结果相关联的附加过滤特征作为附加过滤的建议提供给用户。 以这种方式，使用户知道可以用于集中搜索结果的附加过滤设置或特征。 随后的过滤器设置和过滤操作可以以迭代和动态的方式基于先前相关结果的特征。 更可能产生重点关注的结果，因为根据用户认为相关的结果的特征提供和调整了附加的过滤设置。

    Knowledge Source Personalization To Improve Language Models
    10.
    发明申请
    Knowledge Source Personalization To Improve Language Models 有权
    知识源个性化来改善语言模型

    公开(公告)号：US20150332672A1

    公开(公告)日：2015-11-19

    申请号：US14280070

    申请日：2014-05-16

    申请人： Microsoft Corporation

    发明人： Murat Akbacak ,  Dilek Z. Hakkani-Tur ,  Gokhan Tur ,  Larry P. Heck ,  Benoit Dumoulin

    IPC分类号： G10L15/18

    CPC分类号： G10L15/18 ,  G06F17/30654 ,  G06F17/30734 ,  G06F17/30766 ,  G10L15/07

    摘要： Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.

    摘要翻译： 提供了系统和方法，用于通过将语言模型所使用的知识源个性化为特定用户或用户群体特征来改进用于语音识别的语言模型。 通过将实体或用户操作与用户的使用历史（例如查询日志）映射到知识源，为特定用户个性化知识源。 个性化知识源可以用于通过训练具有与出现在使用历史中的实体或实体对相对应的查询的语言模型来构建个人语言模型。 在一些实施例中，可以基于类似用户的个性化知识源来扩展用于特定用户的个性化知识源。