公开(公告)号：US08589410B2

公开(公告)日：2013-11-19

申请号：US13301381

申请日：2011-11-21

Applicant: Avneesh Sud ,  Rajeev Prasad ,  Ayman Malek Abdel Hamid Kaheel ,  Pragyana Mishra ,  Sumit Amar ,  Kancheng Cao

Inventor： Avneesh Sud ,  Rajeev Prasad ,  Ayman Malek Abdel Hamid Kaheel ,  Pragyana Mishra ,  Sumit Amar ,  Kancheng Cao

IPC: G06F17/30

CPC classification number: G06F17/30256 ,  G06F17/30277 ,  G06F17/30619 ,  G06F17/30651 ,  G06F17/30864

Abstract: Systems, methods, and computer-readable storage media for web-scale visual search capable of using a combination of visual input modalities are provided. An edgel index is created that includes shape-descriptors, including edgel-based representations, that correspond to each of a plurality of images. Each edgel-based representation includes pixels that depicts edges or boundary contours of an image and is created, at least in part, by segmenting the image into a plurality of image segments and performing a multi-phase contour detection on each segment. Upon receiving a search query having a visual query input, the visual query input is converted into shape-descriptors, including an edgel-based representation, and the shape-descriptors, including the edgel-based representation, of each of the plurality of images is compared with the shape-descriptors, including the edgel-based representation, of the visual query input to identify at least one image of the plurality of images that matches the visual query input.

Abstract translation: 提供了能够使用视觉输入模式的组合的用于web尺度视觉搜索的系统，方法和计算机可读存储介质。 创建包含与多个图像中的每一个相对应的形状描述符（包括基于灰色的表示）的暗角指数。 每个基于灰色的表示包括描绘图像的边缘或边界轮廓的像素，并且至少部分地通过将图像分割成多个图像片段并且在每个片段上执行多相轮廓检测来创建。 在接收到具有视觉查询输入的搜索查询时，视觉查询输入被转换成形状描述符，包括基于边缘的表示，并且包括基于灰色的表示的形状描述符，包括多个图像中的每一个的形状描述符是 与形状描述符（包括基于边缘的表示）相比较，用于识别与视觉查询输入匹配的多个图像中的至少一个图像的视觉查询输入。

公开(公告)号：US08051066B2

公开(公告)日：2011-11-01

申请号：US12498556

申请日：2009-07-07

Applicant: Rajeev Prasad ,  Kevin Paul Kornelson

Inventor： Rajeev Prasad ,  Kevin Paul Kornelson

IPC: G06F17/30

CPC classification number: G06F17/3089 ,  Y10S707/99931 ,  Y10S707/99945 ,  Y10S707/99948

Abstract: Configurably storing data in a plurality of files based on expressions and conditions associated with the data. Logging software enables tracking of the navigation pattern of users for selected network properties under specified conditions. The logging software is configurable such that most current and future logging specifications may be fulfilled without any code changes to the logging software.

Abstract translation: 基于与数据相关联的表达和条件，将数据可配置地存储在多个文件中。 记录软件可以在指定条件下跟踪所选网络属性的用户导航模式。 记录软件是可配置的，使得大多数当前和将来的记录规范可以被满足，而没有对记录软件进行任何代码更改。

公开(公告)号：US20110258032A1

公开(公告)日：2011-10-20

申请号：US12759879

申请日：2010-04-14

Applicant: VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD ,  MAHBUBUL ALAM ALI

Inventor： VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD ,  MAHBUBUL ALAM ALI

IPC: G06Q30/00 ,  G06F17/30 ,  G06Q10/00

CPC classification number: G06Q30/0256 ,  G06F16/335 ,  G06F16/9535 ,  G06Q30/02 ,  G06Q30/0243

Abstract: Advertisements are selected for presentation on a search results page based on the presence or absence of user activity within the search results page. When a search results page is provided to an end user, the search results page is tracked for user activity. If user activity is detected, a user context is identified and new advertisements are selected for presentation on the search results page based on the user context. In some embodiments, the search results page provides search results in clusters, and the user context corresponds with a search result cluster selected by an end user. In some embodiments, dominant concepts in the user context are identified and used to select advertisements. Alternatively, if user activity is not detected within a predetermined period of time, new advertisements are selected based on the absence of user activity within the search results page.

Abstract translation: 根据搜索结果页面中用户活动的存在或不存在，选择广告在搜索结果页面上进行演示。 当向最终用户提供搜索结果页面时，跟踪用户活动的搜索结果页面。 如果检测到用户活动，则识别用户上下文，并且基于用户上下文在搜索结果页面上选择新的广告来呈现。 在一些实施例中，搜索结果页面提供集群中的搜索结果，并且用户上下文对应于由最终用户选择的搜索结果集群。 在一些实施例中，用户上下文中的主要概念被识别并用于选择广告。 或者，如果在预定时间段内没有检测到用户活动，则基于搜索结果页面内没有用户活动来选择新的广告。

公开(公告)号：US20110040776A1

公开(公告)日：2011-02-17

申请号：US12542281

申请日：2009-08-17

Applicant: Tarek Najm ,  Phani K Vaddadi ,  Rajeev Prasad ,  Viswanath Vadlamani ,  Eric Schoonover

Inventor： Tarek Najm ,  Phani K Vaddadi ,  Rajeev Prasad ,  Viswanath Vadlamani ,  Eric Schoonover

IPC: G06F17/30

CPC classification number: G06F17/30648 ,  G06F17/30731

Abstract: Review and filtering of search results is facilitated by providing additional types of results beyond links to existing documents can be provided in addition to or in place of links to existing documents. These additional results can facilitate modifying a search request to filter out unwanted documents. The additional results, when in the form of content display objects and/or application display objects, can also provide the user with varying levels of information detail. In some preferred embodiments, an ontology based knowledge base can be leveraged in order to facilitate providing and filtering the results.

Abstract translation: 通过提供额外类型的结果，除了现有文档的链接之外，还可以提供链接到现有文档的链接，可以提供检索和过滤搜索结果。 这些额外的结果可以帮助修改搜索请求以过滤掉不需要的文档。 当以内容的形式显示对象和/或应用程序显示对象时，附加结果也可以向用户提供不同级别的信息细节。 在一些优选实施例中，可以利用基于本体的知识库以便于提供和过滤结果。

公开(公告)号：US20060122889A1

公开(公告)日：2006-06-08

申请号：US10994877

申请日：2004-11-22

Applicant: Brian Burdick ,  Christopher Meek ,  David Heckerman ,  David Chickering ,  Joshua Forman ,  Kevin Kornelson ,  Murali Vajjiravel ,  Rajeev Prasad ,  Raxit Kagalwala ,  Tarek Najm ,  Sachin Dhawan

Inventor： Brian Burdick ,  Christopher Meek ,  David Heckerman ,  David Chickering ,  Joshua Forman ,  Kevin Kornelson ,  Murali Vajjiravel ,  Rajeev Prasad ,  Raxit Kagalwala ,  Tarek Najm ,  Sachin Dhawan

IPC: G06Q30/00

CPC classification number: G06Q30/02 ,  G06Q30/0601

Abstract: Systems and method for managing a plurality of content items designated for placement in a particular position on a rendered page are provided. Methods in accordance with the present invention include receiving a plurality of content items, determining an initial placement allocation frequency for each content item, collecting performance data for one or more of the content items, and determining at least one additional allocation frequency in accordance with the performance data collected. Methods of the present invention may further include randomly allocating placement of each of the content items in the particular position on the page in accordance with one of the respective initial and/or additional allocation frequency for each content item. Additionally, the present invention provides systems and methods for automatically managing a plurality of content items to be displayed in a particular position on a rendered page such that value to the content provider may be maximized.

Abstract translation: 提供了用于管理指定用于放置在呈现页面上的特定位置的多个内容项的系统和方法。 根据本发明的方法包括接收多个内容项目，确定每个内容项目的初始布局分配频率，收集一个或多个内容项目的演奏数据，以及根据所述内容项目确定至少一个附加分配频率 收集性能数据。 本发明的方法还可以包括根据每个内容项目的相应初始和/或附加分配频率之一随机分配每个内容项目在页面上的特定位置的布局。 此外，本发明提供了用于自动管理要在呈现页面上的特定位置显示的多个内容项目的系统和方法，使得可以使对内容提供商的价值最大化。

公开(公告)号：US20060106710A1

公开(公告)日：2006-05-18

申请号：US10999586

申请日：2004-11-30

Applicant: Christopher Meek ,  David Heckerman ,  David Chickering ,  Brian Burdick ,  Li Li ,  Murali Vajjiravel ,  Ying Li ,  Rajeev Prasad ,  Raxit Kagalwala ,  Tarek Najm ,  Sachin Dhawan

Inventor： Christopher Meek ,  David Heckerman ,  David Chickering ,  Brian Burdick ,  Li Li ,  Murali Vajjiravel ,  Ying Li ,  Rajeev Prasad ,  Raxit Kagalwala ,  Tarek Najm ,  Sachin Dhawan

IPC: G06Q40/00

CPC classification number: G06Q30/02 ,  G06Q30/0241 ,  G06Q30/0247 ,  G06Q30/0256 ,  G06Q30/0601 ,  G06Q30/08 ,  G06Q40/04

Abstract: Systems and methods for determining the value of bids placed by content providers for placement positions on a page, e.g., a web page, rendered according to a given context, for instance, the search results listing for a particular query initiated on a search engine web site, are provided. Additionally, systems and methods are provided for determining placement of content items, e.g., advertisements and/or images, on a rendered page relative to other content items on the page based upon bid value.

Abstract translation: 用于确定由内容提供商针对在给定上下文呈现的页面（例如，网页）上的放置位置的出价的价值的系统和方法，例如在搜索引擎网络上发起的特定查询的搜索结果列表 现场提供。 此外，提供了系统和方法，用于基于出价值，在相对于页面上的其他内容项目的呈现页面上确定内容项目（例如广告和/或图像）的放置。

公开(公告)号：US08903794B2

公开(公告)日：2014-12-02

申请号：US12700980

申请日：2010-02-05

Applicant: Viswanath Vadlamani ,  Munirathnam Srikanth ,  Phani Vaddadi ,  Abhinai Srivastava ,  Tarek Najm ,  Rajeev Prasad ,  Arungunram Chandrasekaran Surendran

Inventor： Viswanath Vadlamani ,  Munirathnam Srikanth ,  Phani Vaddadi ,  Abhinai Srivastava ,  Tarek Najm ,  Rajeev Prasad ,  Arungunram Chandrasekaran Surendran

IPC: G06F17/00 ,  G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30864 ,  G06F17/30386 ,  G06F17/30672 ,  G06F17/30675 ,  G06F17/30867 ,  G06F17/30946 ,  H04L41/22

Abstract: Systems, methods, and computer-storage media for generating lateral concepts are provided. The system includes a search engine to receive user queries, a storage to store content and its associated categories, and a lateral concept generator. The lateral concept generator is connected to both the search engine and storage. The lateral concept generator selects lateral concepts from categories associated with the content based on similarity scores for the stored content.

Abstract translation: 提供了用于产生横向概念的系统，方法和计算机存储介质。 该系统包括用于接收用户查询的搜索引擎，用于存储内容及其关联类别的存储器以及侧向概念生成器。 侧向概念生成器连接到搜索引擎和存储。 横向概念生成器基于存储的内容的相似性得分来选择与内容相关联的类别的侧向概念。

公开(公告)号：US20110196737A1

公开(公告)日：2011-08-11

申请号：US12701330

申请日：2010-02-05

Applicant: VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD

Inventor： VISWANATH VADLAMANI ,  ABHINAI SRIVASTAVA ,  TAREK NAJM ,  MUNIRATHNAM SRIKANTH ,  PHANI VADDADI ,  ARUNGUNRAM CHANDRASEKARAN SURENDRAN ,  RAJEEV PRASAD

IPC: G06Q30/00 ,  G06F17/30 ,  G06F7/10

CPC classification number: G06F17/30864 ,  G06Q30/02 ,  G06Q30/0251

Abstract: Advertisements are selected for presentation on search result pages and web pages based on phrases generated from lateral concepts and topics identified for the search result pages and web pages. A search query or an indication of a web page is received for which advertisements are to be provided. Lateral concepts and topics are identified based on the search query or content of the web page. The lateral concepts and topics are used as phrases for selecting advertisements from an advertisement inventory. Selected advertisements are provided for presentation on a search results page in response to a search query or on a web page initially identified.

Abstract translation: 根据从搜索结果页和网页标识的横向概念和主题生成的短语，选择广告以在搜索结果页面和网页上呈现。 接收到要向其提供广告的搜索查询或网页的指示。 基于搜索查询或网页内容识别横向概念和主题。 横向概念和主题被用作从广告库中选择广告的短语。 选择的广告被提供用于在搜索结果页面上响应于搜索查询或最初识别的网页上呈现。

公开(公告)号：US07567979B2

公开(公告)日：2009-07-28

申请号：US10748716

申请日：2003-12-30

Applicant: Rajeev Prasad ,  Kevin Paul Kornelson

Inventor： Rajeev Prasad ,  Kevin Paul Kornelson

IPC: G06F17/00

CPC classification number: G06F17/3089 ,  Y10S707/99931 ,  Y10S707/99945 ,  Y10S707/99948

Abstract: Configurably storing data in a plurality of files based on expressions and conditions associated with the data. Logging software enables tracking of the navigation pattern of users for selected network properties under specified conditions. The logging software is configurable such that most current and future logging specifications may be fulfilled without any code changes to the logging software.

Abstract translation: 基于与数据相关联的表达和条件，将数据可配置地存储在多个文件中。 记录软件可以在指定条件下跟踪所选网络属性的用户导航模式。 记录软件是可配置的，使得大多数当前和将来的记录规范可以被满足，而没有对记录软件进行任何代码更改。

公开(公告)号：US20080027920A1

公开(公告)日：2008-01-31

申请号：US11460070

申请日：2006-07-26

Applicant: Vladimir Schipunov ,  Thomas H. Hargrove ,  Rajeev Prasad

Inventor： Vladimir Schipunov ,  Thomas H. Hargrove ,  Rajeev Prasad

IPC: G06F17/30

CPC classification number: G06F17/30539 ,  G06F17/30545 ,  Y10S707/99934 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99945

Abstract: A system that facilitates data processing includes a receiver component that receives an SQL query. A partitioning component partitions the SQL query into multiple tasks and provides the tasks to multiple cluster nodes for processing. The system enables very large amounts of data (e.g., multiple terabytes) to be quickly prepared for analytical processing, such as for use in connection with a search engine, an advertisement provision system, etc.

Abstract translation: 便于数据处理的系统包括接收SQL查询的接收器组件。 分区组件将SQL查询分成多个任务，并将任务提供给多个集群节点进行处理。 该系统使得能够快速准备用于分析处理的非常大量的数据（例如，多TB），例如用于与搜索引擎，广告提供系统等相关联。