公开(公告)号：US20180137400A1

公开(公告)日：2018-05-17

申请号：US15349037

申请日：2016-11-11

Applicant: Google Inc.

Inventor： Thomas Deselaers ,  Victor Carbune ,  Pedro Gonnet Anders ,  Daniel Martin Keysers

IPC: G06N3/00 ,  G06N3/08 ,  G06N3/04

CPC classification number: G06N3/0445

Abstract: The present disclosure provides systems and methods that leverage machine-learned models (e.g., neural networks) to provide enhanced communication assistance. In particular, the systems and methods of the present disclosure can include or otherwise leverage a machine-learned communication assistance model to detect problematic statements included in a communication and/or provide suggested replacement statements to respectively replace the problematic statements. In one particular example, the communication assistance model can include a long short-term memory recurrent neural network that detects an inappropriate tone or unintended meaning within a user-composed communication and provides one or more suggested replacement statements to replace the problematic statements.

公开(公告)号：US20170061291A1

公开(公告)日：2017-03-02

申请号：US14836113

申请日：2015-08-26

Applicant: Google Inc.

Inventor： Thomas Deselaers ,  Daniel Martin Keysers ,  Abraham Murray ,  Shumin Zhai

IPC: G06N5/04 ,  G06F3/0488 ,  G06K9/00

CPC classification number: G06N5/04 ,  G06F3/0237 ,  G06F3/04883 ,  G06F3/04886 ,  G06K9/00402

Abstract: A computing device is described that receives first input, at an initial time, of a first textual character and a second input, at a subsequent time, of a second textual character. The computing device determines, based on the first and second textual characters, a first character sequence that does not include a space character between the first and second textual characters and a second character sequence that includes the space character between the first and second textual characters. The computing device determines a first score associated with the first character sequence and a second score associated with the second character sequence. The computing device adjusts, based on a duration of time between the initial and subsequent times, the second score to determine a third score, and responsive to determining that the third score exceeds the first score, the computing device outputs the second character sequence.

Abstract translation: 描述了在初始时间接收第二文本字符的第一文本字符和第二输入的第二输入的计算设备。 计算设备基于第一和第二文本字符确定不包括第一和第二文本字符之间的空格字符的第一字符序列和包括第一和第二文本字符之间的空格字符的第二字符序列。 计算设备确定与第一字符序列相关联的第一得分和与第二字符序列相关联的第二分数。 计算设备基于初始和随后时间之间的持续时间来调整第二分数以确定第三分数，并且响应于确定第三分数超过第一分数，计算设备输出第二字符序列。

公开(公告)号：US09536180B2

公开(公告)日：2017-01-03

申请号：US14142967

申请日：2013-12-30

Applicant: Google Inc.

Inventor： Thomas Deselaers ,  Daniel Martin Keysers ,  Dmitriy Genzel ,  Ashok Chhabedia Popat

IPC: G06K9/62 ,  G06K9/72 ,  G06F17/22

CPC classification number: G06K9/723 ,  G06F17/22 ,  G06K2209/013

Abstract: Methods and systems for grapheme splitting of text input for recognition are provided. A method may include receiving a text input in a script and segmenting the text input into one or more graphemes. Each of the one or more graphemes may be split into one or more recognition units based on one or more recognition unit identification criteria associated with the script. Next, a text recognition system may be trained using the recognition units. Text input may be handwritten text input received from a user or a scanned image of text.

Abstract translation: 提供了用于识别文本输入的图形分割的方法和系统。 方法可以包括在脚本中接收文本输入并将文本输入分割成一个或多个字形。 基于与脚本相关联的一个或多个识别单元识别标准，一个或多个字形中的每一个可以被分割成一个或多个识别单元。 接下来，可以使用识别单元来训练文本识别系统。 文本输入可以是从用户接收的手写文本输入或文本的扫描图像。

公开(公告)号：US20160300573A1

公开(公告)日：2016-10-13

申请号：US14681408

申请日：2015-04-08

Applicant: Google Inc.

Inventor： Victor Carbune ,  Daniel M. Keysers ,  Thomas Deselaers

IPC: G10L15/26 ,  G10L17/22

CPC classification number: G10L15/26 ,  G06F17/243 ,  G10L15/193 ,  G10L17/22 ,  G10L25/48

Abstract: In some implementations, user input is received while a form that includes text entry fields is being accessed. In one aspect, a process may include mapping user input to fields of a form and populating the fields of the form with the appropriate information. This process may allow a user to fill out a form using speech input, by generating a transcription of input speech, determining a field that best corresponds to each portion of the speech, and populating each field with the appropriate information.

Abstract translation: 在一些实现中，接收用户输入，而正在访问包括文本输入字段的表单。 在一个方面，过程可以包括将用户输入映射到表单的字段并且用适当的信息填充表单的字段。 该过程可以允许用户使用语音输入来填写表单，通过生成输入语音的转录，确定与语音的每个部分最佳对应的字段，以及用适当的信息填充每个字段。

公开(公告)号：US20160098595A1

公开(公告)日：2016-04-07

申请号：US14967901

申请日：2015-12-14

Applicant: Google Inc.

Inventor： Daniel M. Keysers ,  Thomas Deselaers ,  Henry Allan Rowley

IPC: G06K9/00 ,  G06K9/52

CPC classification number: G06K9/00422 ,  G06K9/00 ,  G06K9/00402 ,  G06K9/00865 ,  G06K9/52 ,  G06K2209/01

Abstract: An optimal recognition for handwritten input based on receiving a touch input from a user may be selected by applying both a delayed stroke recognizer as well as an overlapping recognizer to the handwritten input. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition.

Abstract translation: 可以通过将延迟的笔画识别器以及重叠识别器同时应用于手写输入来选择基于从用户接收触摸输入的手写输入的最佳识别。 可以为延迟的卒中识别以及重叠识别生成分数，并且对应于最高分数的识别可以被呈现为整体识别。

公开(公告)号：US20150235097A1

公开(公告)日：2015-08-20

申请号：US14184997

申请日：2014-02-20

Applicant: Google Inc.

Inventor： Li-Lun Wang ,  Thomas Deselaers ,  Henry Allan Rowley

IPC: G06K9/00 ,  G06K9/66 ,  G06K9/62 ,  G06N99/00 ,  G06K9/22

CPC classification number: G06K9/00865 ,  G06K9/00402 ,  G06K9/222 ,  G06K9/342 ,  G06K9/4604 ,  G06K9/6256 ,  G06K9/66 ,  G06N99/005

Abstract: Techniques are provided for segmenting an input by cut point classification and training a cut classifier. A method may include receiving, by a computerized text recognition system, an input in a script. A heuristic may be applied to the input to insert multiple cut points. For each of the cut points, a probability may be generated and the probability may indicate a likelihood that the cut point is correct. Multiple segments of the input may be selected, and the segments may be defined by cut points having a probability over a threshold. Next, the segments of the input may be provided to a character recognizer. Additionally, a method may include training a cut classifier using a machine learning technique, based on multiple text training examples, to determine the correctness of a cut point in an input.

Abstract translation: 提供了通过切点分类对输入进行分割和训练切分分类器的技术。 方法可以包括通过计算机化的文本识别系统接收脚本中的输入。 可以将启发式应用于输入以插入多个切割点。 对于每个切割点，可以产生概率，并且概率可以指示切割点是正确的可能性。 可以选择输入的多个段，并且可以通过具有超过阈值的概率的切点来定义段。 接下来，可以将输入的段提供给字符识别器。 另外，一种方法可以包括基于多个文本训练示例使用机器学习技术来训练切割分类器，以确定输入中的切割点的正确性。