Predictive information retrieval
    1.
    发明授权
    Predictive information retrieval 有权
    预测信息检索

    公开(公告)号:US08768958B1

    公开(公告)日:2014-07-01

    申请号:US13615791

    申请日:2012-09-14

    IPC分类号: G06F17/30

    摘要: A computer-implemented method for generating results for a client-requested query involves receiving a query produced by a client communication device, generating a result for the query in response to reception of the query, determining one or more predictive follow-up requests before receiving an actual follow-up request from the client device, and initiating retrieval of information associated with the one or more predictive follow-up requests, and transmitting at least part of the result to the client device, and then transmitting to the client device at least part of the information associated with the one or more predictive follow-up requests.

    摘要翻译: 用于生成客户端请求的查询的结果的计算机实现的方法涉及接收由客户端通信设备产生的查询,响应于接收查询而产生用于查询的结果,在接收之前确定一个或多个预测性后续请求 来自客户端设备的实际后续请求,以及启动与所述一个或多个预测性后续请求相关联的信息的检索,以及将所述结果的至少一部分发送到所述客户端设备,然后至少向所述客户端设备发送 与一个或多个预测性跟踪请求相关联的信息的一部分。

    Template-based cursive handwriting recognition
    2.
    发明授权
    Template-based cursive handwriting recognition 失效
    基于模板的草书手写识别

    公开(公告)号:US07369702B2

    公开(公告)日:2008-05-06

    申请号:US10702663

    申请日:2003-11-07

    IPC分类号: G06K9/00 G06K9/62

    CPC分类号: G06K9/6835

    摘要: Input handwritten characters are classified as print or cursive based upon numerical feature values calculated from the shape of an input character. The feature values are applied to inputs of an artificial neural network which outputs a probability of the input character being print or cursive. If a character is classified as print, it is analyzed by a print character recognizer. If a character is classified as cursive, it is analyzed using a cursive character recognizer. The cursive character recognizer compares the input character to multiple prototype characters using a Dynamic Time Warping (DTW) algorithm.

    摘要翻译: 基于从输入字符的形状计算的数值特征值,输入手写字符被分类为打印或草书。 特征值被应用于人造神经网络的输入,其输出输入字符是打印或草书的概率。 如果字符被分类为打印,则由打印字符识别器进行分析。 如果角色被分类为草书,则使用草书字符识别器进行分析。 草书字符识别器使用动态时间扭曲(DTW)算法将输入字符与多个原型字符进行比较。

    Query image search
    3.
    发明授权
    Query image search 有权
    查询图像搜索

    公开(公告)号:US08782077B1

    公开(公告)日:2014-07-15

    申请号:US13438879

    申请日:2012-04-04

    IPC分类号: G06F17/30

    摘要: In general, in one aspect, a method includes receiving a query image, accessing a database of hash values of other images, determining a hash value for the query image by applying a hash function to a bit-vector of data representing signs of a subset of wavelet coefficients collected from the query image, the subset corresponding to wavelet coefficients having greatest magnitude, comparing the hash value of the query image to the hash values of the database, and based on the comparison, identifying as near duplicate images one or more of the other images having a hash value that matches the hash value of the query image. This and other implementations of this aspect can include corresponding systems, apparatus, and computer program products.

    摘要翻译: 一般来说,一方面,一种方法包括接收查询图像,访问其他图像的哈希值的数据库,通过将散列函数应用于表示子集的符号的数据的位向量来确定查询图像的哈希值 从所述查询图像收集的小波系数,所述子集对应于具有最大幅度的小波系数,将所述查询图像的哈希值与所述数据库的散列值进行比较,并且基于所述比较,将所述小波系数识别为近似重复的图像, 其他图像具有与查询图像的哈希值相匹配的哈希值。 该方面的这个和其他实现可以包括相应的系统,装置和计算机程序产品。