Google Inc.

Daniel Wyatt

Andrew Stephen Tomkins

Alexander Fabrikant

Renaud Bourassa-Denis

Prathab Murugesan

Tanmay Sanjay Khirwadkar

Jesse M Rosenstock

Galen Pickard

Rob Schonberger

Anna Teytelman

Boris Mazniker

Alexander Johannes Smola

Daniel Joseph Clancy

Junbin Teng

Amr Ahmed

Martin Zinkevich

Maryam Karimzadehgan

Methods and apparatus related to determining an activity of a user based on sensor readings from sensor(s), and providing, for presentation to the user via a user interface output of a computing device of the user, information that is based on the determined activity. In some implementations, the information may be provided in response to input entered by the user via a user interface input device of the computing device of the user. In some implementations, the input may be a search query and the information may be search results. In some implementations, the input may be a partial query and the information may be query suggestions.

Providing query suggestions and/or search results based on determined user activity

Systems and methods for increasing a visibility of a content item with a comment by a close contact are provided. In some aspects, a first content item is received. A ranking for the first content item in a stream for a viewing user is determined based on an upload time of the first content item. A comment for the first content item is received from a first user, where a predicted affinity level of the viewing user for the first user is within an affinity level range. In response to receiving the comment, the ranking for the first content item in the stream for the viewing user is updated based on an upload time of the comment. The stream is provided for the viewing user.

Increasing a visibility of a content item with a comment by a close contact

Systems and methods for generating a user location history are provided. One example method includes obtaining a plurality of location reports from one or more devices associated with the user. The method includes clustering the plurality of location reports to form a plurality of segments. The method includes identifying a plurality of location entities for each of the plurality of segments. The method includes determining, for each of the plurality of segments, one or more feature values associated with each of the location entities identified for such segment. The method includes determining, for each of the plurality of segments, a score for each of the plurality of location entities based at least in part on a scoring formula. The method includes selecting one of plurality of locations entities for each of the plurality of segments.

Systems and methods for generating a user location history

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying a set of items that are displayed to a user of a social networking service, the items comprising digital content distributed using the social networking service and being associated with item features, the item features comprising item-dependent features and user-dependent features; receiving feature values that are associated with one of an item-dependent feature and a user-dependent feature; receiving probabilities that are associated with a group and reflecting a likelihood that the user is a type of user associated with the group, the groups including a set of weights; determining an item score based on the feature values and a set of weights to provide item scores, the set of weights being identified based on the probabilities; and determining a subset of items to be displayed to the user based on the item scores.

Ranking and ordering items in user-streams

Growing community of inventors

San Francisco, CA, United States of America

Daniel Wyatt