公开(公告)号：US09785703B1

公开(公告)日：2017-10-10

申请号：US15182342

申请日：2016-06-14

申请人： EHARMONY, INC.

发明人： Steve Carter

IPC分类号： G06F17/30

CPC分类号： G06F17/30702 ,  G06F17/30675 ,  G06F17/30696 ,  G06F17/30705 ,  G06F17/30766 ,  G06F17/30861 ,  G06F17/30867

摘要： A computer-based system for presenting interpersonal relationship recommendation that utilizes peer based opinions about a potential match to influence the recommendation, and that presents the peer based opinions along with the recommendation.

公开(公告)号：US09525746B2

公开(公告)日：2016-12-20

申请号：US14486525

申请日：2014-09-15

申请人： ACTIVISION PUBLISHING, INC.

发明人： Cary Lee Bates ,  Jim Chun-Ta Chen ,  Zachary Adam Garbow ,  Gregory Edward Young

IPC分类号： H04L29/08 ,  G06F17/30

CPC分类号： H04L67/22 ,  G06F17/30749 ,  G06F17/30764 ,  G06F17/30766 ,  G06F17/30772

摘要： Embodiments of the invention provide techniques for generating song playlists for use in an immersive virtual environment. Generally, playlists may be generated based on stored music preference data. The music preference data may be generated by storing user interactions with specific songs. The user interactions may be associated with characteristics of the user's situational context within the virtual world. The music preference data may be indexed by song name, and/or by musical properties. Subsequently, the music preference data may be used to generate a playlist adapted to the user's current situation within the virtual world.

摘要翻译： 本发明的实施例提供了用于生成用于沉浸式虚拟环境中的歌曲播放列表的技术。 通常，可以基于存储的音乐偏好数据生成播放列表。 可以通过存储与特定歌曲的用户交互来生成音乐偏好数据。 用户交互可能与虚拟世界中用户的情境环境的特征相关联。 音乐偏好数据可以由歌曲名称和/或音乐属性索引。 随后，音乐偏好数据可以用于生成适合于虚拟世界内的用户当前情况的播放列表。

公开(公告)号：US09524338B2

公开(公告)日：2016-12-20

申请号：US14263750

申请日：2014-04-28

申请人： Sonos, Inc.

发明人： Maarten van der Heide

IPC分类号： G06F17/00 ,  G06F17/30

CPC分类号： G06F17/30766 ,  G06F3/16 ,  G06F17/3074 ,  G06F17/30772

摘要： Methods and systems described herein relate to management of media playback based on media preferences. A computing device may receive data indicating that a media item is available to be played by a media playback system. A media preference associated with the media item may then be identified based on the received data. The media preference may be identified in a preference database. Based on the media preference, the computing device determines whether the media item is or is not to be played by the media playback system. If a determination is made that the media item is not to be played, the computing device sends to the media playback system, an indication that the media item is not to be played. If a determination is made that the media item is to be played, the computing device causes the media item to be played by the media playback system.

摘要翻译： 本文描述的方法和系统涉及基于媒体偏好的媒体回放的管理。 计算设备可以接收指示媒体项目可用于媒体播放系统播放的数据。 然后可以基于接收到的数据来识别与媒体项目相关联的媒体偏好。 可以在偏好数据库中识别媒体偏好。 基于媒体偏好，计算设备确定媒体项目是否被媒体播放系统播放。 如果确定媒体项目不被播放，则计算设备向媒体播放系统发送媒体项目不被播放的指示。 如果确定媒体项目要被播放，则计算设备使媒体项由媒体播放系统播放。

公开(公告)号：US09496003B2

公开(公告)日：2016-11-15

申请号：US12242728

申请日：2008-09-30

申请人： Patrick Gates ,  Richard Frederick Wagner ,  Jeremy Werner ,  Andrew Wadycki ,  Josh Flowers

发明人： Patrick Gates ,  Richard Frederick Wagner ,  Jeremy Werner ,  Andrew Wadycki ,  Josh Flowers

IPC分类号： G06F17/00 ,  G11B27/10 ,  G06F17/30

CPC分类号： G11B27/105 ,  G06F17/30026 ,  G06F17/30053 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30758 ,  G06F17/30766 ,  G06F17/30772 ,  G06F17/30867

摘要： Methods and arrangements for facilitating media playlist generation for a program participant based at least in part on media library inventory information provided by a number of program participants. The system or program in which the individuals are participating is an on-line media store. Those individuals that decide to be program participants are interested in organizing, maintaining and playing their music, based at least in part, on data derived from a population of other participants in the program that have similar or the same music in their libraries. To be a program participant, the individual music holder must send, and the on-line music store receive, data representative of that program participant's media inventory. This data typically contains identification data of the individual media items presently contained in that participant's media library regardless of the individual media item's source. The system or program determines an incidence of co-occurrence of pairs of individual media items in different program participants' media libraries. Based on this determination, a similarity rating is assigned between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants' media libraries.

摘要翻译： 至少部分地基于由多个节目参与者提供的媒体库库存信息来促进节目参与者的媒体播放列表生成的方法和装置。 个人参与的系统或程序是在线媒体商店。 决定参加计划的人员有兴趣至少部分地组织，维护和演奏他们的音乐，这些数据来源于程序中其他图书馆中具有相似或相同音乐的其他参与者的人群。 作为节目参与者，个人音乐持有者必须发送和在线音乐商店接收代表该节目参与者的媒体库存的数据。 该数据通常包含目前包含在该参与者的媒体库中的各个媒体项的标识数据，而不管各个媒体项的来源。 该系统或程序确定不同节目参与者的媒体库中各个媒体项目的共同发生率。 基于该确定，基于所确定的不同节目参与者的媒体库中的共现发生率，在各个媒体项目对之间分配相似性评级。

公开(公告)号：US09495448B2

公开(公告)日：2016-11-15

申请号：US12853630

申请日：2010-08-10

申请人： Paul Barom Jeon

发明人： Paul Barom Jeon

IPC分类号： G06F13/00 ,  G06F17/30

CPC分类号： G06F17/30766 ,  G06F17/30828 ,  G06F17/30867

摘要： A method of generating a combined profile of a terminal, and an apparatus to perform the method, the method including collecting a profile of one or more content playback devices connected to the terminal, and generating a combined profile of the terminal according to a profile of the terminal and the collected profile of the one or more content playback devices.

摘要翻译： 一种生成终端的组合简档的方法以及执行该方法的装置，所述方法包括收集连接到所述终端的一个或多个内容回放设备的简档，以及根据所述终端的简档生成所述终端的组合简档 终端和所收集的一个或多个内容回放设备的配置文件。

公开(公告)号：US20160267116A1

公开(公告)日：2016-09-15

申请号：US14697855

申请日：2015-04-28

申请人： Eyal Nathan

发明人： Eyal Nathan

IPC分类号： G06F17/30

CPC分类号： G06F17/30321 ,  G06F17/30286 ,  G06F17/30684 ,  G06F17/30766 ,  G06F2221/2113

摘要： The present disclosure involves systems, software, and computer implemented methods for generating NER dictionaries from structured business data. In one example, a method may include identifying a set of structured data for use in generating a NER dictionary, identifying a particular collection within the identified structured data to use in the dictionary generation, the particular identified collection including a plurality of values, identifying at least one variant of the value for each value in the particular identified collection, each of the at least one variants of the value including at least a portion of the underlying value, determining a set of unique variants from the identified at least one variants across each of the values in the particular identified subset, adding the determined set of unique variants to the generated dictionary, each unique variant added to the generated dictionary being associated with the value from which the unique variant was derived.

摘要翻译： 本公开涉及用于从结构化业务数据生成NER字典的系统，软件和计算机实现的方法。 在一个示例中，方法可以包括识别用于生成NER字典的一组结构化数据，识别所识别的结构化数据中的特定集合以在字典生成中使用，特定标识的集合包括多个值， 所述特定识别集合中的每个值的值的至少一个变体，所述值的至少一个变体中的每一个包括所述基础值的至少一部分，从每个所述的所识别的至少一个变体确定一组唯一变体 在特定识别的子集中的值的添加中，将确定的唯一变体集合添加到所生成的词典中，添加到生成的词典中的每个唯一变体与从其导出唯一变体的值相关联。

公开(公告)号：US09384734B1

公开(公告)日：2016-07-05

申请号：US13404971

申请日：2012-02-24

申请人： Matthew Wiseman ,  Gheorghe M. Postelnicu ,  Dominik Roblek ,  Yaniv Bernstein ,  Matthew Sharifi ,  Annie Chen

发明人： Matthew Wiseman ,  Gheorghe M. Postelnicu ,  Dominik Roblek ,  Yaniv Bernstein ,  Matthew Sharifi ,  Annie Chen

IPC分类号： G10L15/26

CPC分类号： G10L15/26 ,  G06F17/3074 ,  G06F17/30743 ,  G06F17/30766 ,  G06F17/30769 ,  G10H1/0008 ,  G10H1/0033 ,  G10H2240/141 ,  G10L15/00 ,  G10L15/265 ,  G10L17/00 ,  G10L25/51

摘要： An audio recognition service recognizes an audio sample across multiple content types. At least a partial set of results generated by the service are returned to a client while the audio sample is still being recorded and/or transmitted. The client additionally displays the results in real-time or near real-time to the user. The audio sample can be sent over a first HTTP connection and the results can be returned over a second HTTP connection. The audio recognition service further processes check-in selections received from the client for content items indicated by the results. Responsive to receiving the check-in selections, the service determines whether a user is eligible for a reward. If the user is eligible, the service provides the reward.

摘要翻译： 音频识别服务识别多种内容类型的音频样本。 当音频样本仍然被记录和/或发送时，由服务产生的至少一部分结果返回给客户机。 客户端另外向用户实时或接近实时显示结果。 音频样本可以通过第一个HTTP连接发送，并且可以通过第二个HTTP连接返回结果。 音频识别服务进一步处理从客户端接收的用于由结果指示的内容项的登记选择。 响应于接收签入选择，该服务确定用户是否有资格获得奖励。 如果用户符合条件，则该服务将提供奖励。

公开(公告)号：US09338514B2

公开(公告)日：2016-05-10

申请号：US14229333

申请日：2014-03-28

申请人： SONOS, INC.

发明人： Abhishek Kumar ,  Ron Kuper

IPC分类号： G06F17/00 ,  H04N21/475 ,  G06F3/16 ,  H04L29/08 ,  G06F17/30

CPC分类号： G06F3/165 ,  G06F17/30766 ,  H04L67/306 ,  H04N21/25891 ,  H04N21/4325 ,  H04N21/43615 ,  H04N21/4755 ,  H04N21/4756 ,  H04N21/6582 ,  H04N21/8113 ,  H04R27/00 ,  H04R2227/003 ,  H04R2227/005

摘要： Embodiments described herein involve providing media item preferences according to a user account of a user providing the preference, rather than a user account providing the media item. When a user indicates a preference for a media item, the preference are associated with that particular user, rather than with another user whose account the media item may have been accessed and played through when the particular user indicated the preference. As a result, a media preference history associated with the account providing the media item will not be disrupted by other users indicating preferences for the media item. Further, users may build on their respective media preference histories even when listening to music provided by someone else.

摘要翻译： 本文描述的实施例涉及根据提供偏好的用户的用户帐户提供媒体项目偏好，而不是提供媒体项目的用户帐户。 当用户指示对媒体项目的偏好时，偏好与该特定用户相关联，而不是与特定用户指示该偏好的媒体项目可能被访问和播放的帐户的另一用户相关联。 结果，与提供媒体项目的帐户相关联的媒体偏好历史将不会被指示媒体项目的偏好的其他用户中断。 此外，即使在听别人提供的音乐时，用户也可以建立在它们各自的媒体偏好历史上。

公开(公告)号：US09280270B1

公开(公告)日：2016-03-08

申请号：US14205124

申请日：2014-03-11

申请人： Amazon Technologies, Inc.

发明人： Erich Lawrence Ringewald ,  Sam Heyworth

IPC分类号： G10H1/00 ,  G10H1/36 ,  G06F3/0484

CPC分类号： G06F3/0484 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30758 ,  G06F17/30766 ,  G06F17/30772 ,  G06F17/30817 ,  G06F17/30828 ,  G06F17/3084 ,  G11B27/034

摘要： A system can receive and/or otherwise access information about items of content (e.g., audio tracks, video tracks, images and/or other items), information about a playlist to be generated, information about the past behavior of the target entity for the playlist and/or information about the past behavior of other entities. Examples of information about the items of content include genre, artist, album, time period, etc. Examples of information about a playlist include tempo curve, event type, playlist duration, etc. Based on all or a subset of the above-described information, the system automatically generates a playlist that identifies items of content. The playlist is presented to the target entity so that the target entity can acquire the playlist and/or the items of content identified in the playlist. In some embodiments, the target entity is also provided with an opportunity to edit the playlist.

摘要翻译： 系统可以接收和/或以其它方式访问有关内容（例如音频轨道，视频轨道，图像和/或其他项目）的信息，关于要生成的播放列表的信息，关于目标实体的过去行为的信息， 播放列表和/或关于其他实体的过去行为的信息。 关于内容项的信息的示例包括类型，艺术家，专辑，时间段等。关于播放列表的信息的示例包括节奏曲线，事件类型，播放列表持续时间等。基于上述信息的全部或一个子集 ，系统自动生成识别内容项目的播放列表。 将播放列表呈现给目标实体，使得目标实体可以获取播放列表和/或播放列表中标识的内容项。 在一些实施例中，目标实体还具有编辑播放列表的机会。

公开(公告)号：US20150332670A1

公开(公告)日：2015-11-19

申请号：US14278659

申请日：2014-05-15

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： G10L15/06 ,  G10L15/18 ,  G06F17/28

CPC分类号： G10L15/063 ,  G06F17/28 ,  G06F17/30654 ,  G06F17/30766 ,  G10L15/18 ,  G10L15/183

摘要： Systems and methods are provided for training language models using in-domain-like data collected automatically from one or more data sources. The data sources (such as text data or user-interactional data) are mined for specific types of data, including data related to style, content, and probability of relevance, which are then used for language model training. In one embodiment, a language model is trained from features extracted from a knowledge graph modified into a probabilistic graph, where entity popularities are represented and the popularity information is obtained from data sources related to the knowledge. Embodiments of language models trained from this data are particularly suitable for domain-specific conversational understanding tasks where natural language is used, such as user interaction with a game console or a personal assistant application on personal device.

摘要翻译： 提供了系统和方法，用于使用从一个或多个数据源自动收集的类似域的数据来训练语言模型。 为特定类型的数据挖掘数据源（如文本数据或用户交互数据），包括与风格，内容和相关概率相关的数据，然后将其用于语言模型培训。 在一个实施例中，从从修改为概率图的知识图中提取的特征来训练语言模型，其中表示实体流行度，并且从与知识相关的数据源获得流行度信息。 从该数据训练的语言模型的实施例特别适用于使用自然语言的领域特定对话理解任务，例如用户与个人设备上的游戏控制台或个人助理应用程序的交互。