公开(公告)号：US09942255B1

公开(公告)日：2018-04-10

申请号：US15394963

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Liam MacDermed ,  Elie Bursztein ,  Sean Gilpin ,  Pierre Grinspan ,  Xiaofeng Liu ,  Devasia Manuel

IPC: H04L29/06

CPC classification number: H04L63/1425 ,  G06F21/552 ,  H04L63/1466

Abstract: A hosted service monitoring system detects abuse of a hosted service by monitoring user actions over a period of time. The system will identify an entity, which is a subset of the user actions that share one or more features in common. The system will also identify feature statistics to measure how often the features are associated with the user actions in the entity. The system will project the feature statistics to a vector and use the vector to generate an anomaly score for the entity. The system will determine that the entity is associated with an automated initiator if it generates an anomaly score that exceeds a threshold. Upon determining that the entity that is associated with an automated initiator, the system will cause the hosted service to take an action that will block the automated initiator from accessing the hosted service.

公开(公告)号：US20170046668A1

公开(公告)日：2017-02-16

申请号：US14827330

申请日：2015-08-16

Applicant: GOOGLE INC.

Inventor： Henry Allan Rowley ,  Sanjiv Kumar ,  Xiaofeng Liu ,  Brian Lin Chang ,  Daniel Niels Holtmann-Rice

IPC: G06Q20/10 ,  G06Q20/36 ,  G06K9/20

CPC classification number: G06Q20/10 ,  G06K9/00442 ,  G06K9/03 ,  G06K9/2063 ,  G06K9/723 ,  G06K2209/01 ,  G06Q20/36

Abstract: An application extracts a user name from a financial card image using optical character recognition (“OCR”) and compares segments of the user name to names stored in user data to refine the extracted name. The application performs an OCR algorithm on a card image and compares an extracted name with user data. The application identifies likely matching names to the extracted name. The OCR application breaks the extracted name into one or more series of segments and compares the segments from the extracted name to segments from the stored names. The OCR application determines an edit distance between the extracted name and each potentially matching stored name. If the edit distance is below a configured threshold then the OCR application revises the extracted name to match the identified stored name. The refined name is presented to the user for verification.

Abstract translation: 应用程序使用光学字符识别（“OCR”）从金融卡片图像中提取用户名，并将用户名的段与存储在用户数据中的名称进行比较，以优化提取的名称。 应用程序在卡片图像上执行OCR算法，并将提取的名称与用户数据进行比较。 该应用程序可识别提取的名称可能匹配的名称。 OCR应用将提取的名称分解为一个或多个片段，并将来自提取的名称的片段与存储的名称的片段进行比较。 OCR应用程序确定提取的名称和每个潜在匹配的存储名称之间的编辑距离。 如果编辑距离低于配置的阈值，则OCR应用程序将修改提取的名称以匹配所标识的存储名称。 将精简的名称呈现给用户进行验证。