会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 51. 发明授权
    • Object position detector
    • 对象位置检测器
    • US5861583A
    • 1999-01-19
    • US680127
    • 1996-07-15
    • Richard R. SchediwyJeffrey O. PritchardTing KaoTimothy P. AllenJohn C. Platt
    • Richard R. SchediwyJeffrey O. PritchardTing KaoTimothy P. AllenJohn C. Platt
    • G06F3/033G06F3/041G06F3/044G06F3/048G06K9/00G08C21/00G09G5/00
    • G06F3/044G06F3/041G06K9/00335G06F2203/04101G06F2203/04808
    • An object proximity sensor includes a capacitive touch-sensitive transducer including row conductive lines insulated from column conductive lines to from a matrix. An insulating layer is disposed over the matrix and has a thickness selected to achieve significant capacitive coupling between an object placed on its surface and the matrix. Circuitry first drives each of the row conductive lines to a fixed voltage and then simultaneously injects a known amount of charge onto each of the row conductive lines, and then senses for each row conductive line a row-sense voltage created by the known amount of charge injected onto each of the row conductive lines, and, simultaneous with injected the known amount of charge, changes the voltage on all of the column conductive lines in the same direction as the row-sense voltage by an amount no greater than about twice the difference between the fixed voltage and an average of all row-sense voltage in the transducer. Circuitry first drives each of the column conductive lines to a fixed voltage and then simultaneously injects a known amount of charge onto each of the column conductive lines, and then senses for each column conductive line a column-sense voltage created by the known amount of charge injected onto each of the column conductive lines, and, simultaneous with injecting the known amount of charge, changes the voltage on all of the row conductive lines in the same direction as the column-sense voltages by an amount no greater than about twice the difference between the fixed voltage and an average of all column-sense voltages in the transducer. A set of object-sensed electrical signals related to all of the row-sense voltages and all of the column-sense voltages is produced.
    • 物体接近传感器包括电容式触敏传感器,其包括从列导电线与矩阵绝缘的行导线。 绝缘层设置在矩阵之上,并且具有选择的厚度,以在放置在其表面上的物体与矩阵之间实现显着的电容耦合。 电路首先将每行行导线驱动到固定电压,然后同时将已知数量的电荷注入到每行行导线上,然后感测每行行导线由已知电荷量产生的行感应电压 注入到每行行导线上,同时注入已知的电荷量,将所有列导电线上的电压与行检测电压沿相同的方向改变不大于两倍的差值 在固定电压和传感器中的所有行感应电压的平均值之间。 电路首先将每个列导电线驱动到固定电压,然后同时将已知量的电荷注入到每个列导电线上,然后感测每个列导电线由已知电荷量产生的列检测电压 注入到每个列导电线上,并且同时注入已知的电荷量,将所有行导电线上的电压与列检测电压沿相同的方向改变不大于两倍的差值 在固定电压和传感器中所有列检测电压的平均值之间。 产生与所有行检测电压和所有列检测电压相关的一组物体感测电信号。
    • 55. 发明授权
    • Voice-based search processing
    • 基于语音的搜索处理
    • US08260809B2
    • 2012-09-04
    • US11770535
    • 2007-06-28
    • John C. PlattGary W. FlakeRamez NaamAnoop GuptaOliver Hurst-HillerTrenholme J. Griffin
    • John C. PlattGary W. FlakeRamez NaamAnoop GuptaOliver Hurst-HillerTrenholme J. Griffin
    • G06F7/00G06F17/30
    • G06F17/30976G06F17/276G10L15/26
    • Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.
    • 通过使用基于人工智能的方案来推断用户的搜索意图来完成搜索查询的架构。 部分查询是实时动态完成的。 此外,还可以使用搜索别名。 可以至少基于文本,涂鸦,图像,手写,语音,音频和视频信号的查询输入进行定制调整。 自然语言处理发生,手写识别和俚语识别。 该系统包括接收部分查询作为输入的分类器,基于查询输入的内容访问查询数据库,并从存储在查询数据库中的查询信息推断预期的搜索目标。 查询制定引擎接收与预期搜索目标相关联的搜索信息,并生成完成的正式查询以供执行。
    • 59. 发明申请
    • ACTIVE LEARNING USING A DISCRIMINATIVE CLASSIFIER AND A GENERATIVE MODEL TO DETECT AND/OR PREVENT MALICIOUS BEHAVIOR
    • 主动学习使用分类分类器和生成模型来检测和/或防止恶意行为
    • US20090099988A1
    • 2009-04-16
    • US11871587
    • 2007-10-12
    • Jack W. StokesJohn C. PlattMichael ShilmanJoseph L. Kravis
    • Jack W. StokesJohn C. PlattMichael ShilmanJoseph L. Kravis
    • G06F15/18
    • G06F15/16
    • A malicious behavior detection/prevention system, such as an intrusion detection system, is provided that uses active learning to classify entries into multiple classes. A single entry can correspond to either the occurrence of one or more events or the non-occurrence of one or more events. During a training phase, entries are automatically classified into one of multiple classes. After classifying the entry, a generated model for the determined class is utilized to determine how well an entry corresponds to the model. Ambiguous classifications along with entries that do not fit the model well for the determined class are selected for labeling by a human analyst The selected entries are presented to a human analyst for labeling. These labels are used to further train the classifier and the models. During an evaluation phase, entries are automatically classified using the trained classifier and a policy associated with determined class is applied.
    • 提供了一种恶意行为检测/预防系统,例如入侵检测系统,其使用主动学习将条目分类到多个类中。 单个条目可以对应于一个或多个事件的发生或一个或多个事件的不发生。 在训练阶段,条目自动分为多个类别之一。 在对条目进行分类之后,使用所确定的类的生成模型来确定条目对应于模型的良好程度。 选择不确定的分类以及不符合确定类别的模型的条目,由人类分析人员进行标签。选定的条目将提交给人类分析人员进行标签。 这些标签用于进一步训练分类器和型号。 在评估阶段,使用训练有素的分类器对条目进行自动分类,并应用与确定类相关联的策略。
    • 60. 发明授权
    • Obfuscation of spam filter
    • 垃圾邮件过滤器的混淆
    • US07519668B2
    • 2009-04-14
    • US10601034
    • 2003-06-20
    • Joshua T. GoodmanRobert L. RounthwaiteJohn C. Platt
    • Joshua T. GoodmanRobert L. RounthwaiteJohn C. Platt
    • G06F15/16
    • H04L51/12
    • The subject invention provides systems and methods that facilitate obfuscating a spam filtering system to hinder reverse engineering of the spam filters and/or to mitigate spammers from finding a message that consistently gets through the spam filters almost every time. The system includes a randomization component that randomizes a message score before the message is classified as spam or non-spam so as to obscure the functionality of the spam filter. Randomizing the message score can be accomplished in part by adding a random number or pseudo-random number to the message score before it is classified as spam or non-spam. The number added thereto can vary depending on at least one of several types of input such as time, user, message content, hash of message content, and hash of particularly important features of the message, for example. Alternatively, multiple spam filters can be deployed rather than a single best spam filter.
    • 主题发明提供了系统和方法,其有助于混淆垃圾邮件过滤系统以阻止垃圾邮件过滤器的反向工程和/或减轻垃圾邮件发送者几乎每次都能始终获得通过垃圾邮件过滤器的消息。 该系统包括随机化组件,其在消息被分类为垃圾邮件或非垃圾邮件之前随机化消息得分,以掩盖垃圾邮件过滤器的功能。 随机化消息分数可以部分地通过在消息分数被分类为垃圾邮件或非垃圾邮件之前向消息得分添加随机数或伪随机数来完成。 附加的数量可以根据例如时间,用户,消息内容,消息内容的散列以及消息的特别重要的特征的散列中的至少一种输入而变化。 或者,可以部署多个垃圾邮件过滤器,而不是一个最好的垃圾邮件过滤器。