Google Inc.

Zhihui Chen

Varun Kacholia

David P Stoutamire

Hao Kai Zhang

Jonathan Frankle

Nitin Khandelwal

Yu He

Hyung-Jin Kim

Henele Iitaka Adams

Nitin Jindal

Hao He

Wenxin Li

Cheng Zhu

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ranking search results. One of the methods includes receiving a search result obtained in response to a query, wherein the search result identifies a resource and has an associated score S. A determination is made that users prefer newer resources over older resources for the query and that the resource is a new resource. A new score S' is associated with the resource in place of S, based on the determination that users prefer newer resources over older resources for the query and that the resource is a new resource.

Freshness based ranking

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering videos and using video clusters to present content. One method includes generating target video-specific clusters of co-watched videos for target videos, according to keywords for each target video, and storing data associating the target video with its clusters. The clusters can then be used in various applications, including identifying related videos, augmenting video search results, re-ordering video search results, and identifying content for a target video.

Target-video specific co-watched video clusters

A computer system determines feature metrics for a content channel. The content channel includes one or more media items. The computer system receives a query that corresponds to a query types. The query type is associated with a subset of the feature metrics. The computer system evaluates the content channel based on the subset of feature metrics to produce a channel score for the query type and provides the channel score to position at least one of the media items of the content channel in a query result of the query.

Evaluating media channels

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a video score for a domain. In one aspect, a method includes determining video resources hosted on devices assigned to a domain, determining a quality metric for the video resources, generating a quality score from the quality metrics for video resources hosted on the domain, generating a quantity score based on counts of video resources hosted on the domain, determining a domain video score from the quality score and the quantity score, and adjusting, based on the domain video score, one or more video search operations on the video resources hosted on the domain.

Measuring video content of web domains

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing video searches using query-independent quality scores.

Query independent quality signals

Obtaining search results responsive to a query, each search result identifying a respective resource and each resource having a respective rank determined by a primary ranking algorithm. The method includes obtaining primary user feedback data and secondary user feedback data for the resource. The primary and secondary user feedback data representing previous user interactions with the resource when the resource was presented as a search result responsive to the query. The method also includes applying a weight to the secondary user feedback data, the weight being at least partially based on a threshold quantity of the primary user feedback data. The method also includes aggregating the primary user feedback data and the weighted secondary user feedback data and modifying the respective rank of the resource as a search result for the query based at least partially on the aggregated data.

Combining user feedback

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ranking search results. One of the methods includes receiving a search result obtained in response to a query. A recent impression probability for the query for a recent time period and an overall impression probability for the query for an overall time period are computed. A ratio QtoA of the recent impression probability to the overall impression probability is computed. A determination is made that users prefer newer resources over older resources for the query based on QtoA and that the resource is a new resource. A new score S' is associated with the resource in place of S, wherein the new score S&#x2032; signifies a better result than the score S signifies, based on determining that users prefer newer resources over older resources for the query, and that the resource is a new resource.

Growing community of inventors

Menlo Park, CA, United States of America

Zhihui Chen