公开(公告)号：US20140380224A1

公开(公告)日：2014-12-25

申请号：US14482667

申请日：2014-09-10

Applicant: Google Inc.

Inventor： Xincheng Zhang ,  Yefei Peng

IPC: G06F3/0489 ,  G06F3/0484 ,  G06F3/0488 ,  G06F3/0481

CPC classification number: G06F3/0489 ,  G06F3/017 ,  G06F3/0418 ,  G06F3/0481 ,  G06F3/04847 ,  G06F3/0488 ,  G06F3/04886

Abstract: A computing device automatically customizes attributes of a graphical keyboard based on user inputs to the graphical keyboard. For example, the computing device can display a first graphical keyboard arrangement that includes a first representation of a key associated with a target region of an input-sensitive display. The computing device receives a plurality of user inputs, each associated with a respective touch region of the input-sensitive display. Subsequent to determining that one or more of the touch regions is not substantially aligned with the target region, the computing device displays a second graphical keyboard arrangement that includes a second representation of the key, wherein at least one attribute of the second representation of the key is graphically modified relative to the first representation of the key so as to substantially align one or more of the touch regions with a target region associated with the second representation of the key.

Abstract translation: 计算设备根据图形键盘的用户输入自动定制图形键盘的属性。 例如，计算设备可以显示包括与输入敏感显示器的目标区域相关联的键的第一表示的第一图形键盘布置。 计算设备接收多个用户输入，每个用户输入与输入敏感显示器的相应触摸区域相关联。 在确定一个或多个触摸区域基本上不与目标区域对准之后，计算设备显示包括密钥的第二表示的第二图形键盘布置，其中密钥的第二表示的至少一个属性 相对于键的第一表示被图形地修改，以便使一个或多个触摸区域与与键的第二表示相关联的目标区域基本对齐。

公开(公告)号：US10417286B1

公开(公告)日：2019-09-17

申请号：US15704980

申请日：2017-09-14

Applicant: Google Inc.

Inventor： Yefei Peng ,  Christopher Kenneth Harris

IPC: G06F16/95

Abstract: Systems and methods of the present disclosure are directed generally to facilitating content selection by identifying low impact criteria. In some implementations, a data processing system accesses a data structure storing, in a memory element, a plurality of impression records. Each impression record can include one or more features and an indication of user interest corresponding to a content impression. The data processing system can identify a combination feature based on at least two of the features. The data processing system can execute a statistical model (e.g., logistic regression model) using the impression records and the combination feature. The data processing system can determine a weight for the combination feature. Responsive to the weight being less than a threshold, the data processing system can transmit an indication to disable the combination feature for selecting content associated with the plurality of impression records.

公开(公告)号：US20180143946A1

公开(公告)日：2018-05-24

申请号：US15360365

申请日：2016-11-23

Applicant: Google Inc.

Inventor： Yefei Peng

IPC: G06F17/21 ,  H04L29/08 ,  G06F17/22 ,  G06Q30/02

CPC classification number: G06Q30/0277 ,  H04L67/20

Abstract: The present disclosure discusses the adjustment of a rate of display between different types of content item categories. The system of the present disclosure can determine a content item's rate of display with a first category of content and with a second category of content. The system can determine a relationship between the display rates. If the display rates are outside of a predetermined range, the system can update the display parameters of the content categories.

公开(公告)号：US09767196B1

公开(公告)日：2017-09-19

申请号：US14085153

申请日：2013-11-20

Applicant: Google Inc.

Inventor： Yefei Peng ,  Christopher Kenneth Harris

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30861 ,  G06F17/30867

Abstract: Systems and methods of the present disclosure are directed generally to facilitating content selection by identifying low impact criteria. In some implementations, a data processing system accesses a data structure storing, in a memory element, a plurality of impression records. Each impression record can include one or more features and an indication of user interest corresponding to a content impression. The data processing system can identify a combination feature based on at least two of the features. The data processing system can execute a statistical model (e.g., logistic regression model) using the impression records and the combination feature. The data processing system can determine a weight for the combination feature. Responsive to the weight being less than a threshold, the data processing system can transmit an indication to disable the combination feature for selecting content associated with the plurality of impression records.