公开(公告)号：US09858275B1

公开(公告)日：2018-01-02

申请号：US14842554

申请日：2015-09-01

Applicant: Google Inc.

Inventor： Andrew Tomkins ,  Dandapani Sivakumar ,  Sangsoo Sung ,  Justin Kosslyn ,  Todd Jackson ,  Andre Rohe ,  Ya Luo ,  Andrew Bunner ,  Alexander Sobol ,  Luca de Alfaro

IPC: G06F17/30

CPC classification number: H04L67/10 ,  G06F12/06 ,  G06F17/30 ,  G06F17/30029 ,  G06F17/30041 ,  G06F17/30044 ,  G06F17/3005 ,  G06F17/30864 ,  G06F17/30867 ,  G06N5/00 ,  G06Q30/02 ,  H04L65/60 ,  H04L65/602 ,  H04L67/32

Abstract: A system and method for generating a real-time stream of content from heterogeneous data sources and a real-time index. The heterogeneous data sources include search, entertainment, social activity and activity on third-party sites. A fetching unit retrieves recent content that is indexed in the real-time index according to keywords. A model generation engine generates a model based on user activities. The mixer compares candidate content items from the heterogeneous data sources and the real-time index to the model to generate scores for each item and generates a stream of content based on the scores.

公开(公告)号：US20170206550A1

公开(公告)日：2017-07-20

申请号：US14313432

申请日：2014-06-24

Applicant: Google Inc.

Inventor： Fergus Gerard Hurley ,  Michael Schwarz ,  Robin Dua ,  Sangsoo Sung ,  Andrew Tomkins

IPC: G06Q30/02

CPC classification number: G06Q30/0251 ,  G06Q30/0275

Abstract: Methods, systems, and apparatus for allocating an offer based, in part, on a user's utility. In one aspect, a method includes receiving, at a data processing apparatus, data describing a purchase intent for a set of items, the purchase intent being for a user; receiving, at the data processing apparatus, from each offeror in a set of offerors: a corresponding offer from the offeror, each offer applying to one or more items in the set of items, and a corresponding valuation of the offer by the offeror for presentation of the offer to the user; for each offer in the set of offers, determining, by the data processing apparatus, a corresponding utility to the user based on a user utility model, and adjusting the valuation for the offer based on the corresponding utility determined for the offer to generate an adjusted valuation for the offer.

公开(公告)号：US09600543B1

公开(公告)日：2017-03-21

申请号：US14040466

申请日：2013-09-27

Applicant: Google Inc.

Inventor： Lucian Florin Cionca ,  Andre Rohe ,  Yonatan Zunger ,  Sangsoo Sung ,  Mohit Oberoi ,  Daniel Belov ,  Harish Rajamani ,  Jinan Lou

IPC: G06F17/30 ,  G06Q50/10

CPC classification number: G06F17/30554 ,  G06F17/30867 ,  G06Q50/10

Abstract: In one aspect, a method includes receiving an indication of a request from a user to view a stream associated with the user, generating a request for one or more items visible to the user for display within the stream, the request including a search query identifying search criteria including one or more tokens, the one or more tokens including at least a user token identifying the user, receiving one or more items in response to the request, the one or more items including at least one of the one or more tokens and further being visible to the user and providing the one or more items for display to the user within the stream in response to the request. Other aspects can be embodied in corresponding systems and apparatus, including computer program products.

公开(公告)号：US20150371271A1

公开(公告)日：2015-12-24

申请号：US14313451

申请日：2014-06-24

Applicant: Google Inc.

Inventor： Fergus Gerard Hurley ,  Michael Schwarz ,  Robin Dua ,  Sangsoo Sung ,  Andrew Tomkins

IPC: G06Q30/02

CPC classification number: G06Q30/0261 ,  G06Q30/0241 ,  G06Q30/0259 ,  G06Q30/0267 ,  H04W4/02 ,  H04W4/21

Abstract: Methods, systems, and apparatus, for detour based content selection. In one aspect, a method includes receiving, at a data processing apparatus, location data for a plurality of users, the location data describing, for each user, locations of a user device of the user; determining, from the location data, route data for the plurality of users, the route data describing, for each user, a route traveled by the user; determining, by the data processing apparatus, for at least one or more of the users, a detour from the route traveled by the user to a retail location of the offeror; determining, by the data processing apparatus, for each of the at least one or more of the users, whether the user is eligible for an offer of the offeror based on the detour; and for each user eligible for an offer, enabling the offeror to provide an offer to the user.

Abstract translation: 方法，系统和装置，用于基于绕行的内容选择。 一方面，一种方法包括在数据处理装置处接收多个用户的位置数据，所述位置数据针对每个用户描述用户的用户设备的位置; 从所述位置数据确定所述多个用户的路线数据，所述路线数据针对每个用户描述由所述用户行进的路线; 由所述数据处理装置为所述用户中的至少一个或多个确定从所述用户行进到所述提供者的零售位置的路线; 由所述数据处理装置为所述至少一个或多个所述用户中的每一个确定所述用户是否有资格基于所述绕行提供所述要约者的要约; 并且对于符合条件的每个用户，允许提供者向用户提供报价。

公开(公告)号：US20150370884A1

公开(公告)日：2015-12-24

申请号：US14313459

申请日：2014-06-24

Applicant: Google Inc.

Inventor： Fergus Gerard Hurley ,  Robin Dua ,  Sangsoo Sung ,  Andrew Tomkins

IPC: G06F17/30

CPC classification number: G06F16/285 ,  G06Q10/109

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for list accumulation and reminder triggering. In one aspect, a method includes receiving, at a data processing apparatus, a first input comprising a plurality of terms; determining, by the data processing apparatus, that one or more of the terms in the first input specify an item that belongs to a reminder category, the reminder category being associated with a collection of items that belong to the category and for which reminders may be generated; and in response to the determination, storing data that associates a reminder type with the item specified by the one or more terms.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于列表累积和提醒触发。 一方面，一种方法包括在数据处理装置处接收包括多个项的第一输入; 由数据处理装置确定第一输入中的一个或多个术语指定属于提醒类别的项目，提醒类别与属于该类别的项目的集合相关联，并且提醒可以是 生成的 并且响应于所述确定，存储将提醒类型与由所述一个或多个术语指定的项目相关联的数据。

公开(公告)号：US10083697B2

公开(公告)日：2018-09-25

申请号：US14723279

申请日：2015-05-27

Applicant: Google Inc.

Inventor： Sangsoo Sung ,  Yuli Gao ,  Prathab Murugesan

IPC: G10L15/22 ,  G10L15/02 ,  G10L15/30 ,  G10L15/16 ,  G10L15/187 ,  H04M3/533 ,  G10L17/22 ,  H04L29/06

CPC classification number: H04L67/42 ,  G10L15/22 ,  G10L15/30

Abstract: Data associated with a selectively offline capable voice action is locally persisted in a voice-enabled electronic device whenever such an action cannot be competed locally due to the device being offline to enable the action to later be completed after online connectivity has been restored. Synchronization with an online service and/or another electronic device, and/or retrieval of context sensitive data from an online service may be performed after online connectivity has been restored to enable the voice action to thereafter be completed.

公开(公告)号：US20170242914A1

公开(公告)日：2017-08-24

申请号：US15051778

申请日：2016-02-24

Applicant: Google Inc.

Inventor： Yuli Gao ,  Sangsoo Sung ,  Pedro Jose Moreno Mengibar

IPC: G06F17/30 ,  G06F17/27 ,  G10L15/26

CPC classification number: G06F17/30654 ,  G06F17/271 ,  G06F17/30684 ,  G10L15/265 ,  G10L2015/223 ,  G10L2015/225

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements to parse voice-based queries. In various implementations, a query issued at a resource-constrained device may be semantically processed to identify candidate responsive actions that are performable by the resource-constrained device. Candidate responsive action performance statistics may be analyzed to select, from the one or more candidate responsive actions, a qualifying responsive action. In various implementations, the candidate responsive action performance statistics may relate to performance of the one or more candidate responsive actions by the resource-constrained device following issuance of the query. An offline grammar model stored in the resource-constrained device may be updated to include a mapping between the issued query and the qualifying responsive action, wherein the offline grammar model maps queries to actions that are performable by the resource-constrained device while offline.

公开(公告)号：US20160350320A1

公开(公告)日：2016-12-01

申请号：US14723305

申请日：2015-05-27

Applicant: Google Inc.

Inventor： Sangsoo Sung ,  Yuli Gao ,  Prathab Murugesan

IPC: G06F17/30 ,  G10L17/22

CPC classification number: G06F17/3097 ,  G06F17/271 ,  G06F17/274 ,  G06F17/30321 ,  G06F17/30395 ,  G06F17/30401 ,  G06F17/30684 ,  G10L15/19 ,  G10L15/30 ,  G10L17/22

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements to parse voice-based queries received by the device. The offline grammar model may be generated from a larger and more comprehensive grammar model used by an online voice-based query processor, and the generation of the offline grammar model may be based upon query usage data collected from one or more users to enable a subset of more popular voice-based queries from the online grammar model to be incorporated into the offline grammar model. In addition, such a device may collect query usage data and upload such data to an online service to enable an updated offline grammar model to be generated and downloaded back to the device and thereby enable a dynamic update of the offline grammar model to be performed.

Abstract translation: 诸如移动设备的资源受限制的语音设备的离线语义处理器利用具有减少的资源需求的离线语法模型来解析由设备接收的基于语音的查询。 离线语法模型可以由在线基于语音的查询处理器使用的较大且更全面的语法模型生成，并且离线语法模型的生成可以基于从一个或多个用户收集的查询使用数据，以使得子集 来自在线语法模型的更流行的基于语音的查询将被并入到离线语法模型中。 此外，这样的设备可以收集查询使用数据并且将这样的数据上传到在线服务以使得更新的离线语法模型被生成并被下载回设备，从而能够执行离线语法模型的动态更新。

公开(公告)号：US09286357B1

公开(公告)日：2016-03-15

申请号：US14589140

申请日：2015-01-05

Applicant: Google Inc.

Inventor： Alexander Sobol ,  Andre Rohe ,  Sangsoo Sung ,  Lucian F. Cionca

IPC: G06F17/30

CPC classification number: G06F17/3053 ,  G06F17/30716 ,  G06F17/30864

Abstract: Techniques include obtaining ranges of content relevance scores for different collections of content; generating a normalized range based on the ranges of content relevance scores; and normalizing a particular range of a particular collection of content including: generating a distribution of content relevance scores for the collection of content; identifying portions in the distribution; and generating a mapping of portions from the distribution to portions in the normalized range.

公开(公告)号：US10783166B2

公开(公告)日：2020-09-22

申请号：US14313459

申请日：2014-06-24

Applicant: Google Inc.

Inventor： Fergus Gerard Hurley ,  Robin Dua ,  Sangsoo Sung ,  Andrew Tomkins

IPC: G06F16/00 ,  G06F16/28 ,  G06Q10/10

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for list accumulation and reminder triggering. In one aspect, a method includes receiving, at a data processing apparatus, a first input comprising a plurality of terms; determining, by the data processing apparatus, that one or more of the terms in the first input specify an item that belongs to a reminder category, the reminder category being associated with a collection of items that belong to the category and for which reminders may be generated; and in response to the determination, storing data that associates a reminder type with the item specified by the one or more terms.