Google Inc.

T-mobile Usa, Inc.

James McFadden

Tze Way Eugene Ie

Tushar Deepak Chandra

Yangli Hector Yee

Yoram Singer

Tal Shaked

Li Wei

Dasarathi Sampath

John Kraemer

Jeremiah Harmsen

Daniel Artuso

Navneet Loiwal

Brandon Drake

Kristen Riedt LeFevre

A core network for a cellular system may maintain a dataset of one or more cell sites as being in an emergency zone. The dataset may be populated by local network operators in or near the emergency zone. The core network may consult the dataset prior to enforcing contractual terms for data rate throttling or re-prioritization to determine if the subscriber is in a designated emergency zone. If so, the core network may suspend the enforcement of data throttling or lowering priority so that subscribers in the emergency zone receive full access to the communication network. The dataset may include an expiration time or be on a timer so that the local network operators may be required to re-enroll the one or more cell sites as being in an emergency zone.

Non-throttling on emergency cell sites in cellular systems

Systems and techniques are provided for template exploration in a large-scale machine learning system. A method may include obtaining multiple base templates, each base template comprising multiple features. A template performance score may be obtained for each base template and a first base template may be selected from among the multiple base templates based on the template performance score of the first base template. Multiple cross-templates may be constructed by generating a cross-template of the selected first base template and each of the multiple base templates. Performance of a machine learning model may be tested based on each cross-template to generate a cross-template performance score for each of the cross-templates. A first cross-template may be selected from among the multiple cross-templates based on the cross-template performance score of the cross-template. Accordingly, the first cross-template may be added to the machine learning model.

Using template exploration for large-scale machine learning

A method includes presenting a list of one or more videos via a user interface, receiving a selection of a target video to watch from the list, playing the target video in the user interface, and updating the user interface to present one or more suggested videos concurrently with playback of the target video. The one or more suggested videos are predicted to be watched by a user for at least a threshold duration.

Use of user consumption time to rank media suggestions

A system receives a user request for a media item and identifies candidate media items for suggesting to the user with the media item. The system predicts a user consumption time for each candidate media item and selects a sub-set of the candidate media items that have higher predicted user consumption times. The system provides the requested media item with the sub-set of the candidate media items.

Mechanisms for recommending content items based on topics are provided. In some implementations, a method for recommending content items is provided that includes: determining a plurality of accessed content items associated with a user, wherein each of the plurality of content items is associated with a plurality of topics; determining the plurality of topics associated with each of the plurality of accessed content items; generating a model of user interests based on the plurality of topics, wherein the model implements a machine learning technique to determine a plurality of weights for assigning to each of the plurality of topics; applying the model to determine, for a plurality of content items, a probability that the user would watch a content item of the plurality of content items; ranking the plurality of content items based on the determined probabilities; and selecting a subset of the plurality of content items to recommend to the user based on the ranked content items.

Methods, systems, and media for recommending content items based on topics

Systems and techniques are disclosed for training a machine learning model based on one or more regularization penalties associated with one or more features. A template having a lower regularization penalty may be given preference over a template having a higher regularization penalty. A regularization penalty may be determined based on domain knowledge. A restrictive regularization penalty may be assigned to a template based on determining that a template occurrence is below a stability threshold and may be modified if the template occurrence meets or exceeds the stability threshold.

Template regularization for generalization of learning systems

Multiple sets of words and phrases can be used as query terms for accessing sponsored content. Sponsored content is associated with item terms. The query terms are matched with the item terms. The result of the matching operation is a numerical score for each item of sponsored content that can be used to select sponsored content. Conditions present across the set of matched terms are detected. Such conditions can include the occurrence of a matched query term in multiple sets of query terms. This condition can be addressed by determining a number of unique matching query terms across all sets of query terms. The score given to an item of sponsored content can be adjusted if such a condition occurs. For example, the score could be adjusted according to a function of the number of unique matching query terms across all sets of query terms. If the number of matching query terms across all sets of query terms is low, such as one or two, then the function can define a penalty to be applied to the score given to the item of sponsored content. If the number of matching query terms across all sets of query terms is higher, such as three or more, then the function can define an adjustment to be applied to the score given to the item of sponsored content.

Growing community of inventors

San Francisco, CA, United States of America

James McFadden