公开(公告)号：US09083730B2

公开(公告)日：2015-07-14

申请号：US14099600

申请日：2013-12-06

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Baris Coskun ,  Suhrid Balakrishnan ,  Suhas Mathur

IPC: G06F11/00 ,  G06F12/14 ,  G06F12/16 ,  G08B23/00 ,  H04L29/06

CPC classification number: H04L63/1416 ,  H04L63/14 ,  H04L63/1408 ,  H04L63/1425 ,  H04L2463/146

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to identify an Internet protocol address blacklist boundary. An example method includes identifying a netblock associated with a malicious Internet protocol address, the netblock having a lower boundary and an upper boundary, collecting netflow data associated with a plurality of Internet protocol addresses in the netblock, establishing a first window associated with a lower portion of Internet protocol addresses numerically lower than a candidate Internet protocol address, establishing a second window associated with an upper portion of Internet protocol addresses numerically higher than a candidate Internet protocol address, calculating a breakpoint score based on a comparison between a behavioral profile of the first window and a behavioral profile of the second window, and identifying a first sub-netblock when the breakpoint score exceeds a threshold value.

Abstract translation: 公开了方法，装置，系统和制品以识别因特网协议地址黑名单边界。 示例性方法包括识别与恶意因特网协议地址相关联的网络块，网络块具有下边界和上边界，收集与网络块中的多个因特网协议地址相关联的网络流数据，建立与下部相关联的第一窗口 互联网协议地址数字地低于候选互联网协议地址，建立与互联网协议地址的上部相关联的第二窗口，数字地高于候选互联网协议地址，计算断点得分，基于第一 窗口和第二窗口的行为简档，以及当断点得分超过阈值时识别第一子网块。

公开(公告)号：US20140040176A1

公开(公告)日：2014-02-06

申请号：US14052705

申请日：2013-10-12

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Suhrid Balakrishnan ,  Sumit Chopra

IPC: G06N99/00

CPC classification number: G06N5/027 ,  G06F17/18 ,  G06F17/30979 ,  G06N7/005 ,  G06N99/005 ,  G06Q30/0203 ,  G06Q30/0631

Abstract: Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.

Abstract translation: 方法，系统和产品适应具有成对反馈的推荐系统。 一个成对的问题是向用户提出的。 收到一个响应，选择对成对问题中的一对项目的偏好。 潜在因素模型适用于纳入响应，并且基于响应向用户推荐项目。

公开(公告)号：US10193900B2

公开(公告)日：2019-01-29

申请号：US14792938

申请日：2015-07-07

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Baris Coskun ,  Suhrid Balakrishnan ,  Suhas Mathur

IPC: H04L29/06 ,  G06F12/14

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to identify candidate boundaries of Internet protocol addresses associated with a malicious Internet protocol address. An example method includes collecting, with a processor, netflow data associated with the Internet protocol addresses within a netblock having a lower boundary Internet protocol address and an upper boundary Internet protocol address, generating, with the processor, a first window of Internet protocol addresses numerically lower than the malicious Internet protocol address, generating, with the processor, a second window of Internet protocol addresses numerically higher than the malicious Internet protocol address, for respective Internet protocol addresses in the first and second windows, calculating, with the processor, occurrence counts associated with behavior features, and identifying candidate boundaries within the netblock based on divergence values caused by the behavior features.

公开(公告)号：US20140098141A1

公开(公告)日：2014-04-10

申请号：US13648549

申请日：2012-10-10

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Subhabrata Sen ,  Suhrid Balakrishnan ,  Emiliano Miluzzo ,  Alexander Varshavsky

IPC: G09G5/00

CPC classification number: G06F3/04886 ,  G06F21/55 ,  G06F2221/031

Abstract: Data entry using a software keyboard such as a touchscreen keyboard is secured by varying key sizes in the keyboard from key to key and from software keyboard configuration to software keyboard configuration, decoupling display locations from keys. Multiple software keyboard configurations are generated, each having different sets of key sizes. The keyboard configuration may be changed with each keystroke, or may be changed for each prompted entry including multiple keystrokes.

Abstract translation: 使用诸如触摸屏键盘的软件键盘的数据输入通过键盘从键到键的不同键尺寸以及从软件键盘配置到软件键盘配置，将显示位置与键分离来确保。 生成多个软件键盘配置，每个键盘配置具有不同的键大小集合。 键盘配置可以随每次按键而改变，或者可以针对每个提示的条目进行更改，包括多个按键。

公开(公告)号：US10284893B2

公开(公告)日：2019-05-07

申请号：US15644915

申请日：2017-07-10

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Suhrid Balakrishnan ,  David Lee Applegate ,  Sumit Chopra ,  Simon Urbanek

IPC: H04H60/32 ,  H04N21/2668 ,  H04N21/24 ,  H04N21/2543 ,  H04N21/442 ,  H04N21/658 ,  H04N21/81 ,  H04N21/25 ,  G06Q30/02 ,  H04N21/433

Abstract: A system that incorporates teachings of the subject disclosure may include, for example, determining identified impressions that are detected from consumption data collected from a group of media processors where the identified impressions represent viewing of selected content and where the consumption data indicates channel tuning events at the group of media processors including changing of channels, applying a ridge regression analysis to the identified impressions to determine a predicted number of target impressions per advertisement slot, and generating a media plan based on a ratio of an advertisement slot cost to the predicted number of target impressions per advertisement slot. Other embodiments are disclosed.

公开(公告)号：US20170311020A1

公开(公告)日：2017-10-26

申请号：US15644915

申请日：2017-07-10

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Suhrid Balakrishnan ,  DAVID LEE APPLEGATE ,  SUMIT CHOPRA ,  SIMON URBANEK

IPC: H04N21/2668 ,  H04N21/658 ,  H04N21/442 ,  H04N21/433 ,  H04N21/2543 ,  H04N21/25 ,  H04N21/24 ,  H04N21/81 ,  G06Q30/02

CPC classification number: H04N21/2668 ,  G06Q30/0244 ,  H04N21/2407 ,  H04N21/252 ,  H04N21/25435 ,  H04N21/433 ,  H04N21/44222 ,  H04N21/6582 ,  H04N21/812

Abstract: A system that incorporates teachings of the subject disclosure may include, for example, determining identified impressions that are detected from consumption data collected from a group of media processors where the identified impressions represent viewing of selected content and where the consumption data indicates channel tuning events at the group of media processors including changing of channels, applying a ridge regression analysis to the identified impressions to determine a predicted number of target impressions per advertisement slot, and generating a media plan based on a ratio of an advertisement slot cost to the predicted number of target impressions per advertisement slot. Other embodiments are disclosed.

公开(公告)号：US20150163235A1

公开(公告)日：2015-06-11

申请号：US14099600

申请日：2013-12-06

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Baris Coskun ,  Suhrid Balakrishnan ,  Suhas Mathur

IPC: H04L29/06

CPC classification number: H04L63/1416 ,  H04L63/14 ,  H04L63/1408 ,  H04L63/1425 ,  H04L2463/146

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to identify an Internet protocol address blacklist boundary. An example method includes identifying a netblock associated with a malicious Internet protocol address, the netblock having a lower boundary and an upper boundary, collecting netflow data associated with a plurality of Internet protocol addresses in the netblock, establishing a first window associated with a lower portion of Internet protocol addresses numerically lower than a candidate Internet protocol address, establishing a second window associated with an upper portion of Internet protocol addresses numerically higher than a candidate Internet protocol address, calculating a breakpoint score based on a comparison between a behavioral profile of the first window and a behavioral profile of the second window, and identifying a first sub-netblock when the breakpoint score exceeds a threshold value.

Abstract translation: 公开了方法，装置，系统和制品以识别因特网协议地址黑名单边界。 示例性方法包括识别与恶意因特网协议地址相关联的网络块，网络块具有下边界和上边界，收集与网络块中的多个因特网协议地址相关联的网络流数据，建立与下部相关联的第一窗口 互联网协议地址数字地低于候选互联网协议地址，建立与互联网协议地址的上部相关联的第二窗口，数字地高于候选互联网协议地址，计算断点得分，基于第一 窗口和第二窗口的行为简档，以及当断点得分超过阈值时识别第一子网块。

公开(公告)号：US08682677B2

公开(公告)日：2014-03-25

申请号：US13873661

申请日：2013-04-30

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jason William ,  Suhrid Balakrishnan ,  Lihong Li

IPC: G10L21/00 ,  G10L11/00

CPC classification number: G10L15/063 ,  G06F3/167 ,  H04M3/4936 ,  H04M2203/355

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features.

Abstract translation: 这里公开了用于自动生成用于在口头对话系统中使用的对话管理器的系统，方法和计算机可读存储介质。 实施该方法的系统接收具有特征的一组用户交互，识别初始策略，评估算法的线性评估步骤中的所有特征以识别一组最重要的特征，对所识别的一个或多个特征进行立体策略改进步骤 一组最重要的特征，重复前一个步骤一次或多次，并且基于所得到的策略和/或一组最重要的特征生成用于在口头对话系统中的对话管理器。 评估所有特征可以包括估计每个特征的权重，其指示每个特征对至少一个所识别的策略贡献多少。 系统可以忽略不属于最重要功能集的功能。

公开(公告)号：US20150312269A1

公开(公告)日：2015-10-29

申请号：US14792938

申请日：2015-07-07

Applicant: AT&T Intellectual Property I., L.P.

Inventor： Baris Coskun ,  Suhrid Balakrishnan ,  Suhas Mathur

IPC: H04L29/06

CPC classification number: H04L63/1416 ,  H04L63/14 ,  H04L63/1408 ,  H04L63/1425 ,  H04L2463/146

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to identify candidate boundaries of Internet protocol addresses associated with a malicious Internet protocol address. An example method includes collecting, with a processor, netflow data associated with the Internet protocol addresses within a netblock having a lower boundary Internet protocol address and an upper boundary Internet protocol address, generating, with the processor, a first window of Internet protocol addresses numerically lower than the malicious Internet protocol address, generating, with the processor, a second window of Internet protocol addresses numerically higher than the malicious Internet protocol address, for respective Internet protocol addresses in the first and second windows, calculating, with the processor, occurrence counts associated with behavior features, and identifying candidate boundaries within the netblock based on divergence values caused by the behavior features.

Abstract translation: 公开了方法，装置，系统和制品，以识别与恶意因特网协议地址相关联的因特网协议地址的候选边界。 一个示例性方法包括与处理器一起收集与具有较低边界因特网协议地址和上限网络协议地址的网络块内的因特网协议地址相关联的网络流数据，其中处理器以数字方式生成互联网协议地址的第一窗口 低于恶意互联网协议地址，利用处理器，为第一和第二窗口中的各个互联网协议地址生成数字上高于恶意互联网协议地址的互联网协议地址的第二窗口，与处理器一起计算发生次数 与行为特征相关联，并且基于由行为特征引起的发散值来识别网络块内的候选边界。

公开(公告)号：US20130238333A1

公开(公告)日：2013-09-12

申请号：US13873661

申请日：2013-04-30

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Jason William ,  Suhrid Balakrishnan ,  Lihong Li

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G06F3/167 ,  H04M3/4936 ,  H04M2203/355

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features.

Abstract translation: 这里公开了用于自动生成用于在口头对话系统中使用的对话管理器的系统，方法和计算机可读存储介质。 实施该方法的系统接收具有特征的一组用户交互，识别初始策略，评估算法的线性评估步骤中的所有特征以识别一组最重要的特征，对所识别的一个或多个特征进行立体策略改进步骤 一组最重要的特征，重复前一个步骤一次或多次，并且基于所得到的策略和/或一组最重要的特征生成用于在口头对话系统中的对话管理器。 评估所有特征可以包括估计每个特征的权重，其指示每个特征对至少一个所识别的策略贡献多少。 系统可以忽略不属于最重要功能集的功能。