Google Inc.

Harish Chandran

Hariharan Chandrasekaran

Lucian Florin Cionca

Junbin Teng

Archit Gupta

Andre Rohe

Amogh Sanjay Asgekar

Alessandra Mazzia

Yumio Saneyoshi

Ka Hung Hui

Panchapagesan Krishnamurthy

Madhavi Yenugula

Matthew Hayes

Training and/or utilizing a machine learning model to generate request agnostic predicted interaction scores for electronic communications, and to utilization of request agnostic predicted interaction scores in determining whether, and/or how, to provide corresponding electronic communications to a client device in response to a request. A request agnostic predicted interaction score for an electronic communication provides an indication of quality of the communication, and is generated independent of corresponding request(s) for which it is utilized. In many implementations, a request agnostic predicted interaction score for an electronic communication is generated 'offline' relative to corresponding request(s) for which it is utilized, and is pre-indexed with (or otherwise assigned to) the electronic communication. This enables fast and efficient retrieval, and utilization, of the request agnostic interaction score by computing device(s), when the electronic communication is responsive to a request.

Generating, using a machine learning model, request agnostic interaction scores for electronic communications, and utilization of same

In one aspect, a method includes identifying a first user viewing a first set of posts at a social networking service, the first set of posts including one or more posts, determining that the level of engagement of the first user at the social networking service is below a predetermined level, generating a second set of posts in response to determining that the level of engagement of the first user at the social networking service is below a predetermined level, the second set of posts including one or more posts not previously seen by the user and providing the second set of posts for display to the user. Other aspects can be embodied in corresponding systems and apparatus, including computer program products.

Multiple social streams

Methods, systems, apparatus, including computer programs encoded on computer storage medium, for a bottom-up approach for generating high-quality content streams. In one aspect, the method includes actions of obtaining data identifying a plurality of content items, generating a plurality of queries for the particular topic, and for each query of the plurality of queries: obtaining a set of search results for the query that identify content items identified in the obtained data, and determining, from the search results for the query, a respective quality score for each of one or more quality characteristics. The method may also include actions such as identifying one or more first high-quality queries from the plurality of queries based on the respective quality scores for the one or more quality characteristics, and populating a stream of content for display on the user device using search results for the one or more first high-quality queries.

Populating streams of content

Aspects of the subject technology relate to systems and methods for action-based content scoring. Scores associated with a content item are determined. Each of the scores is generated by a different predictive model and associated with a respective user interaction type. A composite score for the content item is determined based on at least one of the scores. The content item is provided for display in a content stream associated with a user based on the composite score.

Action-based content scoring

A system comprising a processor and a memory storing instructions that, when executed, cause the system to receive a record of data describing user engagement with content items in an online service; prepare the record of data for generating a model characterizing a network effect of a user interaction with a content item in the online service; generate the model characterizing the network effect of the user interaction with the content item in the online service; generate a predicted network effect score for a plurality of content items based on the model; organize the plurality of content items based on the predicted network effect score; and transmit the plurality of organized content items for presentation to a user. The disclosure also includes similar methods and computer program products.

Ranking content for user engagement

Aspects of the subject technology relate to mixing an aggregated content data structure into a content stream. A first plurality of aggregated content data structures is be received, each comprising a group of content items for display in a content stream of a user and being associated with a respective score. A first aggregated content data structure may be selected from among the first plurality of aggregated content data structures based on the scores and predetermined type target percentages associated with the user. The first aggregated content data structure may be mixed into a content stream associated with a user, and the content stream provided for display.

Mixing content into a content stream

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for feature-based ranking adjustment. In one aspect, a method includes finalizing rankings of resources based on detected features, and for each resource for which a ranking is not finalized, finalizing the respective resources or demoting the resources based on the detection of features common to the resources with the finalized rankings and the resources with the unfinalized rankings.

Growing community of inventors

Sunnyvale, CA, United States of America

Harish Chandran