公开(公告)号：US20070005646A1

公开(公告)日：2007-01-04

申请号：US11171123

申请日：2005-06-30

申请人： Susan Dumais ,  Eric Horvitz ,  Xuehua Shen

发明人： Susan Dumais ,  Eric Horvitz ,  Xuehua Shen

IPC分类号： G06F17/00

CPC分类号： G06F16/9535 ,  G06F2216/03

摘要： The subject invention relates to probabilistic models that are trained from transitions among various topics of pages visited by a sample population of search users. In one aspect, probabilistic models of topic transitions are learned for individual users and groups of users. Topic transitions for individuals versus larger groups are analyzed, wherein the relative accuracies of personal models of topic dynamics with models constructed from sets of pages drawn from similar groups and from a larger population of users are compared. To exploit temporal dynamics, the accuracy of these models are tested for predicting transitions in topics of visits at increasingly more distant times in the future. The models can be applied to search topic dynamics of tagged pages, and then utilized to predict topics of subsequent pages visited by users.

摘要翻译： 本发明涉及由搜索用户的样本群访问的各个主题之间的转换训练的概率模型。 在一个方面，为个人用户和用户组学习主题转换的概率模型。 对个人与较大群体的主题过渡进行了分析，其中比较了主题动态个人模型的相对准确性，以及从较大群体的用户组中绘制的模型构建的模型。 为了利用时间动力学，对这些模型的准确性进行了测试，以预测未来越来越遥远的访问主题的过渡。 这些模型可以应用于搜索标签页面的主题动态，然后用于预测用户访问的后续页面的主题。

公开(公告)号：US20060248055A1

公开(公告)日：2006-11-02

申请号：US11118284

申请日：2005-04-28

申请人： Brian Haslam ,  David Andrews ,  Susan Dumais ,  Danielle Holmes

发明人： Brian Haslam ,  David Andrews ,  Susan Dumais ,  Danielle Holmes

IPC分类号： G06F17/30

CPC分类号： G06F16/35 ,  G06F16/382

摘要： A system and method for analysis of portfolios of documents is presented. The portfolios may comprise patent-related documents, academic articles, product literature, or any other textual material. In one aspect of the invention, a user-defined classification schema is developed, and predictions for associations with classifications from the user-defined classification schema are used directly, or compared for two portfolios via an analysis computer program. In yet another aspect of the invention, the results from the automatic classifier are combined with a custom classification schema to find and rank related documents. In yet another aspect of the invention, a citation computer program compares citation statistics between entire portfolios of documents. In yet another aspect of the invention, two aspects of the invention can be combined, such that citation statistics are presented for documents that have been classified.

摘要翻译： 介绍了分析文件组合的系统和方法。 投资组合可能包括专利相关文件，学术文章，产品文献或任何其他文字资料。 在本发明的一个方面，开发了用户定义的分类模式，并且直接使用来自用户定义的分类模式的与分类的关联的预测，或者通过分析计算机程序对两个组合进行比较。 在本发明的另一方面，将自动分类器的结果与定制分类模式组合以找到并排列相关文档。 在本发明的另一方面，引用计算机程序比较文档的整个组合之间的引用统计。 在本发明的另一方面，本发明的两个方面可以组合，使得针对已被分类的文献呈现引文统计。

公开(公告)号：US20060129606A1

公开(公告)日：2006-06-15

申请号：US11348018

申请日：2006-02-06

申请人： Eric Horvitz ,  Susan Dumais ,  Meredith Ringel ,  Edward Cutrell ,  Paul Koch

发明人： Eric Horvitz ,  Susan Dumais ,  Meredith Ringel ,  Edward Cutrell ,  Paul Koch

IPC分类号： G06F17/00

CPC分类号： G06F16/40 ,  G06F16/148 ,  G06F16/48 ,  G16H10/20

摘要： One or more models of memorability are provided that facilitate various computer-based applications including those centering on the storage, retrieval, and processing of information, applications that remind people about items they risk not recalling or overlooking, and facilitating communications of reminders. In one application, the models are used to help compose and navigate large personal stores of information about a user's activities, communications, images, and other content. In another application, views of files in directories are extended with the addition of memory landmarks, and a means for controlling the number of landmarks provided via changing a threshold on inferred memorability. Another application centers on the use of models of memorability to select subsets of images from larger sets representing events, for display in a slide show or ambient photo display. In another application, a system is provided that facilitates computer-based searching for information by providing for the design and analysis of timeline visualizations in connection with displaying results to queries based at least in part on an index of content. A query is received by a query component (which can be part of search engine that provides a unified index of information a user has been exposed to). The query component parses the query into portions relevant to effecting a meaningful search in accordance with the subject invention. The query component can access and populate a data store which may include information searched for. A landmark component receives and/or accesses information from the query component as well as the data store, and anchors public and/or personal landmark events to search results-related information.

公开(公告)号：US20050210024A1

公开(公告)日：2005-09-22

申请号：US10805706

申请日：2004-03-22

申请人： Oliver Hurst-Hiller ,  Susan Dumais

发明人： Oliver Hurst-Hiller ,  Susan Dumais

IPC分类号： G06F17/30

CPC分类号： G06F17/30867 ,  Y10S707/99931 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99935

摘要： Context-based user behavior data is collected from a search mechanism. This data includes, for a given query, user feedback (implicit and explicit) on the query and context information on the query. This information can be used, for example, to evaluate a search mechanism or to check a relevance model. This context-based user behavior data may include user information. In one embodiment, explicit feedback is requested from the user except when the user requests a pause in explicit feedback requests, or only periodically, in order to reach a target value for requests for explicit feedback. The explicit feedback may include feedback concerning results not visited, and concerning non-standard results. Implicit feedback will include particular data items such as requeries by a user.

摘要翻译： 从搜索机制收集基于上下文的用户行为数据。 对于给定的查询，该数据包括查询上的用户反馈（隐式和显式）以及关于查询的上下文信息。 该信息可用于例如评估搜索机制或检查相关性模型。 该基于上下文的用户行为数据可以包括用户信息。 在一个实施例中，除了当用户请求显式反馈请求中的暂停或仅仅周期性地为了达到用于显式反馈的请求的目标值的情况下，请求来自用户的显式反馈。 明确的反馈可能包括关于未访问的结果以及非标准结果的反馈。 隐式反馈将包括特定数据项，如用户的请求。