Google Inc.

International Business Machines Corporation

Microsoft Technology Licensing, LLC

Beverly Yang

Christopher Rohrs

Adam Sah

Daniel S Tarlow

Ryohei Takahashi

Lawrence Wen-Kai Shih

Glen M Jeh

Bryan Christopher Horling

Marcus Felipe Fontoura

Okan Kolak

Vivek Ravindranath Narasayya

Eugene Jon Shekita

Kevin Scott Beyer

Vanja Josifovski

Gaurav Garg

Sridhar Rajagopalan

Sanjay Agrawal

David Adams

Everett Wetchler

Derek Mauro

Eugene K Shekita

A method, system, and graphical user interface for alerting a computer user to new results for a prior search are disclosed. One aspect of the invention involves a graphical user interface on a computer that includes a plurality of links recommended by a search engine for a computer user. The plurality of links are determined by the search engine by: producing search results by rerunning a plurality of search queries that have been performed previously for the computer user, and evaluating the produced search results to select search results that meet predefined search result selection criteria. At least one of the criteria is based on Internet usage data for the user.

Method, system, and graphical user interface for alerting a computer user to new results for a prior search

This specification describes technologies relating to generation of keywords. In general, one aspect of the subject matter described in this specification can be embodied in methods that include receiving structured data describing a content item, the structured data indicating a category for the content item. The methods may further include searching domains associated with the category using a first query, formed based on data elements in the structured data, to identify resources associated with the identified domains. The methods may further include determining one or more queries based on data reflecting past search queries, where each of the one or more determined queries resulted in one or more of the identified resources being returned as part of a search result, and determining keywords based on the one or more determined queries. The methods may further include transmitting or storing the keywords for use in impression allocation decisions.

Keyword generation

Systems, methods and program products for classifying text. A system classifies text into first subject matter categories. The system identifies one or more second subject matter categories in a collection of second subject matter categories, each of the second categories is a hierarchical classification of a collection of confirmed valid search results for queries, in which at least one query for each identified second category includes a term in the text. The system filters the identified categories by excluding identified categories whose ancestors are not among the first categories. The system selects categories from the filtered categories based on one or more thresholds in which a threshold specifies a degree of relatedness between a selected category and the text. The selected categories are a sufficient basis for recommending content to a user, the content being associated with one or more of the selected categories.

Classifying text into hierarchical categories

A method, system, and graphical user interface for alerting a computer user to new results for a prior search are disclosed. One aspect of the invention involves a graphical user interface on a computer that includes a plurality of links recommended by a search engine for a computer user. The plurality of links are determined by the search engine by: producing search results by rerunning a plurality of search queries that have been performed previously for the computer user; and evaluating the produced search results to select search results that meet predefined search result selection criteria. At least one of the criteria is based on Internet usage data for the user.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for ranking resources within clusters of resources, and for ranking the clusters. In one aspect, a method includes accessing a cluster of a plurality of resources associated with a name context; generating a quality score for a resource; generating a resource ranking score for the resource, with the resource ranking score at least partly based on the quality score and the cluster relation score; and ranking the resources in the cluster at least partly based on the resource ranking score.

Ranking clusters and resources in a cluster

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for ranking resources within clusters of resources, and for ranking the clusters. In one aspect, a method includes accessing clusters; receiving, for a resource in the cluster, a search score for the resource, the search score being indicative of a relevance of the resource to a search query that includes the name context of the cluster; receiving, for the resource in the cluster, a resource ranking score for the resource in the cluster, the resource ranking score indicative of a ranking of the resource in the cluster relative to other resources in the cluster; generating a cluster rank score for the cluster, the cluster rank score at least partly based on the search scores for the resources and the resource ranking scores for the resources; and ranking the clusters according to their cluster rank score.

Methods, systems, and apparatus, including computer program products, for ranking resources. One or more signals reporting one or more actions by the plurality of users related to a respective resource are received, where a reported action is a presentation of the respective resource, an addition of the respective resource, or a deletion of the respective resource. The reported actions include one or more short deletions of the respective resource. A respective long-addition click-through rate (LACTR) is determined for the respective resource based on a number of reported presentations of the respective resource and a difference between a number of reported additions of the respective resource and a number of short deletions of the respective resource. The plurality of resources are ranked based on the respective LACTRs for the plurality of resources. The ranking of the plurality of resources are provided.

Online ranking metric

Generic online ranking system and method suitable for syndication

Methods, systems, and apparatus, including computer program products, for exchanging information in accordance with a protocol. In one aspect, signals reporting user actions related to resources and ranking data ranking the resources based on the signals are exchanged in accordance with a protocol. The protocol defines types of user actions that can be reported by the signals, a format for specifying values for one or more of a set of predefined parameters for qualifying the user actions, a format for specifying one or more subscriber-specific parameters relating to the resources or the user actions, and a format for identifying resources to which the user actions are related using a namespace defined by the subscriber.

Online ranking protocol

Methods, program products, and systems for classifying feeds are described. A system acquires user created labels and user subscribed data feeds from a group of users. The system generates a topic-feed association rule by generating a topic-feed mapping that contains topic-feed pairs, calculating a weight for each topic-feed pair, and selecting topic-feed pairs whose weight reaches a threshold. The data feeds are classified into topics according to the topic-feed association rules. The system obtains user categories from a group of users. Using a probability model, the system matches the user subscribed data feeds with the user categories. The system further generates a topic classification, associating topics with user categories. Using the topic classification, topic-feed association rules, and a user's specific data, the system predicts a user's feeds of interest and recommends data feeds to the user accordingly.

User label and user category based content classification

Methods, systems, and apparatus, including computer program products, for providing ranking services. In one aspect, first signals are received from a first subscriber, and second signals are received from a second subscriber. The signals include information characterizing individual user actions relating to individual ones of first or second resources, respectively, values for one or more predefined parameters, and values for one or more first subscriber-specific parameters that are specific to the first or second subscriber, respectively. First ranking data is generated from the first signals, but not from values for any subscriber-specific parameter that is not a subscriber-specific parameter for the first subscriber. Second ranking data is generated from the second signals, but not from values for any subscriber-specific parameter that is not a subscriber-specific parameter for the second subscriber.

Growing community of inventors

Cupertino, CA, United States of America

Beverly Yang