中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

93 records (took 0.042 seconds)

    Neural network for keyboard input decoding
    1.
    发明授权
    Neural network for keyboard input decoding 有权

    公开(公告)号：US10248313B2

    公开(公告)日：2019-04-02

    申请号：US15473010

    申请日：2017-03-29

    Applicant: Google Inc.

    Inventor： Shumin Zhai ,  Thomas Breuel ,  Ouais Alsharif ,  Yu Ouyang ,  Francoise Beaufays ,  Johan Schalkwyk

    IPC: G06F3/02 ,  G06F3/0488 ,  G06F17/27 ,  G06F3/023 ,  G06F3/0489 ,  G06N3/04 ,  G06F3/0482 ,  G06N3/08

    Abstract: In some examples, a computing device includes at least one processor; and at least one module, operable by the at least one processor to: output, for display at an output device, a graphical keyboard; receive an indication of a gesture detected at a location of a presence-sensitive input device, wherein the location of the presence-sensitive input device corresponds to a location of the output device that outputs the graphical keyboard; determine, based on at least one spatial feature of the gesture that is processed by the computing device using a neural network, at least one character string, wherein the at least one spatial feature indicates at least one physical property of the gesture; and output, for display at the output device, based at least in part on the processing of the at least one spatial feature of the gesture using the neural network, the at least one character string.

    INCREMENTAL MULTI-WORD RECOGNITION
    2.
    发明申请
    INCREMENTAL MULTI-WORD RECOGNITION 审中-公开

    公开(公告)号：US20180018314A1

    公开(公告)日：2018-01-18

    申请号：US15703820

    申请日：2017-09-13

    Applicant: Google Inc.

    Inventor： Shumin Zhai ,  Yu Ouyang ,  Ken Wakasa ,  Satoshi Kataoka

    IPC: G06F17/27 ,  G06F3/023 ,  G06F3/0488 ,  G06F3/01 ,  G06F3/041

    CPC classification number: G06F17/277 ,  G06F3/017 ,  G06F3/0237 ,  G06F3/0414 ,  G06F3/04883 ,  G06F3/04886 ,  G06F17/276

    Abstract: In one example, a computing device includes at least one processor that is operatively coupled to a presence-sensitive display and a gesture module operable by the at least one processor. The gesture module may be operable by the at least one processor to output, for display at the presence-sensitive display, a graphical keyboard comprising a plurality of keys and receive an indication of a continuous gesture detected at the presence-sensitive display, the continuous gesture to select a group of keys of the plurality of keys. The gesture module may be further operable to determine, in response to receiving the indication of the continuous gesture and based at least in part on the group of keys of the plurality of keys, a candidate phrase comprising a group of candidate words.

    PARTIAL GESTURE TEXT ENTRY
    4.
    发明申请
    PARTIAL GESTURE TEXT ENTRY 审中-公开

    公开(公告)号：US20170206193A1

    公开(公告)日：2017-07-20

    申请号：US15478775

    申请日：2017-04-04

    Applicant: Google Inc.

    Inventor： Xiaojun Bi ,  Yu Ouyang ,  Shumin Zhai

    IPC: G06F17/27 ,  G06F3/041 ,  G06F3/0488

    CPC classification number: G06F17/276 ,  G06F3/017 ,  G06F3/0237 ,  G06F3/0412 ,  G06F3/0484 ,  G06F3/04883 ,  G06F3/04886

    Abstract: A graphical keyboard including a number of keys is output for display at a display device. The computing device receives an indication of a gesture to select at least two of the keys based at least in part on detecting an input unit at locations of a presence-sensitive input device. In response to the detecting and while the input unit is detected at the presence-sensitive input device: the computing device determines a candidate word for the gesture based at least in part on the at least two keys and the candidate word is output for display at a first location of the output device. In response to determining that the input unit is no longer detected at the presence-sensitive input device, the displayed candidate word is output for display at a second location of the display device.

    UNLEARNING TECHNIQUES FOR ADAPTIVE LANGUAGE MODELS IN TEXT ENTRY
    7.
    发明申请
    UNLEARNING TECHNIQUES FOR ADAPTIVE LANGUAGE MODELS IN TEXT ENTRY 有权
    自适应语言文本入门技术

    公开(公告)号：US20160282956A1

    公开(公告)日：2016-09-29

    申请号：US14873147

    申请日：2015-10-01

    Applicant: Google Inc.

    Inventor： Yu Ouyang ,  Shumin Zhai

    IPC: G06F3/023 ,  G06F17/27 ,  G06F3/0488

    CPC classification number: G06F3/0237 ,  G06F3/04883 ,  G06F3/04886 ,  G06F17/20 ,  G06F17/22 ,  G06F17/24 ,  G06F17/2715 ,  G06F2203/04808

    Abstract: In some examples, a method includes outputting a graphical keyboard (120) for display and responsive to receiving an indication of a first input (124), determining a new character string that is not included in a language model. The method may include adding the new character string to the language model and associating a likelihood value with the new character string. The method may include, responsive to receiving an indication of a second input, predicting the new character string, and responsive to receiving an indication of a third input that rejects the new character string, decreasing the likelihood value associated with the new character string.

    Abstract translation: 在一些示例中，一种方法包括输出用于显示的图形键盘（120）并且响应于接收到第一输入（124）的指示，确定不包括在语言模型中的新字符串。 该方法可以包括将新的字符串添加到语言模型中并将似然值与新的字符串相关联。 该方法可以包括：响应于接收到第二输入的指示，预测新的字符串，并且响应于接收到拒绝新的字符串的第三输入的指示，减少与新的字符串相关联的似然值。

    ALTERNATIVE HYPOTHESIS ERROR CORRECTION FOR GESTURE TYPING
    8.
    发明申请
    ALTERNATIVE HYPOTHESIS ERROR CORRECTION FOR GESTURE TYPING 有权
    用于姿势类型的替代假设误差校正

    公开(公告)号：US20150277757A1

    公开(公告)日：2015-10-01

    申请号：US14738449

    申请日：2015-06-12

    Applicant: GOOGLE INC.

    Inventor： Yu Ouyang ,  Shumin Zhai

    IPC: G06F3/0488 ,  G06F17/27

    CPC classification number: G06F3/04886 ,  G06F3/0236 ,  G06F3/0237 ,  G06F3/04883 ,  G06F3/04897 ,  G06F17/273 ,  G06F17/276 ,  Y10S707/99935 ,  Y10S707/99936

    Abstract: In one example, a method may include outputting, by a computing device and for display, a graphical keyboard comprising a plurality of keys, and receiving an indication of a gesture. The method may include determining an alignment score that is based at least in part on a word prefix and an alignment point traversed by the gesture. The method may include determining at least one alternative character that is based at least in part on a misspelling that includes at least a portion of the word prefix. The method may include determining an alternative alignment score based at least in part on the alternative character; and outputting, by the computing device and for display, based at least in part on the alternative alignment score, a candidate word based at least in part on the alternative character.

    Abstract translation: 在一个示例中，方法可以包括由计算设备输出并显示包括多个键的图形键盘，以及接收手势的指示。 该方法可以包括确定至少部分地基于词前缀和由手势穿过的对准点的对准分数。 该方法可以包括确定至少部分地基于包含词前缀的至少一部分的拼写错误的至少一个替代字符。 该方法可以包括至少部分地基于替代角色确定替代对准分数; 以及至少部分地基于所述替代字符，至少部分地基于所述替代对准分数来输出所述计算设备并用于显示候选词。

    Incremental multi-word recognition
    9.
    发明授权
    Incremental multi-word recognition 有权
    增量多字识别

    公开(公告)号：US09134906B2

    公开(公告)日：2015-09-15

    申请号：US14196552

    申请日：2014-03-04

    Applicant: Google Inc.

    Inventor： Shumin Zhai ,  Yu Ouyang ,  Ken Wakasa ,  Satoshi Kataoka

    IPC: G06F15/00 ,  G06F13/00 ,  G06F3/0488 ,  G06F3/01 ,  G06F3/023 ,  G06F17/27

    CPC classification number: G06F17/277 ,  G06F3/017 ,  G06F3/0237 ,  G06F3/0414 ,  G06F3/04883 ,  G06F3/04886 ,  G06F17/276

    Abstract: In one example, a computing device includes at least one processor that is operatively coupled to a presence-sensitive display and a gesture module operable by the at least one processor. The gesture module may be operable by the at least one processor to output, for display at the presence-sensitive display, a graphical keyboard comprising a plurality of keys and receive an indication of a continuous gesture detected at the presence-sensitive display, the continuous gesture to select a group of keys of the plurality of keys. The gesture module may be further operable to determine, in response to receiving the indication of the continuous gesture and based at least in part on the group of keys of the plurality of keys, a candidate phrase comprising a group of candidate words.

    Abstract translation: 在一个示例中，计算设备包括至少一个处理器，其可操作地耦合到存在敏感显示器和由所述至少一个处理器可操作的手势模块。 手势模块可以由至少一个处理器操作以输出用于在存在敏感显示器处显示的包括多个键的图形键盘并且接收在存在敏感显示器处检测到的连续手势的指示，连续的 选择所述多个键中的一组键的手势。 手势模块还可以进一步操作以响应于接收到连续手势的指示并至少部分地基于多个键的键组来确定包括一组候选词的候选短语。

    Character and word level language models for out-of-vocabulary text input
    10.
    发明授权
    Character and word level language models for out-of-vocabulary text input 有权
    字符和词级语言模型，用于外部词汇文本输入

    公开(公告)号：US09047268B2

    公开(公告)日：2015-06-02

    申请号：US13774656

    申请日：2013-02-22

    Applicant: Google Inc.

    Inventor： Yu Ouyang ,  Shumin Zhai ,  Ciprian Ioan Chelba

    IPC: G06F17/27 ,  G06F3/023 ,  G06F3/0488 ,  G10L15/06 ,  G10L15/00 ,  G10L25/00 ,  G06F3/02 ,  G06F3/048 ,  G06F17/00 ,  G06K9/72

    CPC classification number: G06F17/276 ,  G06F3/0237 ,  G06F3/04886 ,  G06F17/273

    Abstract: A computing device determines, based at least in part on indications of user input, scores for a first set of candidate strings and a second set of candidate strings. Each candidate string from the first set of candidate strings is in a lexicon. Candidate strings from the second set of candidate strings are not necessarily in the lexicon. The computing device determines the scores for the first set of candidate strings based on probabilities of the candidate strings being entered. For each candidate string from the second set of candidate strings, the computing device determines the scores for the candidate string based on probabilities of characters of the candidate string being entered. The computing device selects a candidate string based on the scores for the first and second sets of candidate strings and outputs, for display at the display device, the selected candidate string.

    Abstract translation: 计算设备至少部分地基于用户输入的指示确定第一组候选串和第二组候选字符串的分数。 来自第一组候选字符串的每个候选字符串都在词典中。 来自第二组候选字符串的候选字符串不一定在词典中。 计算装置根据输入的候选字符串的概率来确定第一组候选字符串的分数。 对于来自第二组候选字符串的每个候选字符串，计算设备基于候选字符串的字符的概率来确定候选字符串的得分。 计算装置基于第一和第二组候选串的分数来选择候选串，并输出用于在显示装置处显示所选择的候选串。

Patent Agency Ranking