Google Inc.

Atscale, Inc.

Madison Reed, Inc.

David A Ross

Sarah Gerweck

Douglas Eck

Ruei-Sung Lin

Christopher Tim Althoff

Richard Francis Lyon

Hrishikesh Balkrishna Aradhye

Sudheendra Vijayanarasimhan

Thomas Chadwick Walters

Timothy Priestley Novikoff

Arvind Balasubramanian

Alexis Bienvenu

Jay Yagnik

Omid Madani

David G King

Huazhong Ning

Clifford Samaniego

Alexander Joshua Frank

Kenji Arai

Chelsea Leigh Smith

Mohamad Tarifi

Matthew Nirvan Sharifi

Hartwig Adam

Andrew Rabinovich

Jay Michael Ponte

Gheorghe Postelnicu

Sanketh Shetty

Yaniv Bernstein

Caroline Rebecca Pantofaru

Kevin Patrick Murphy

Anand Pillai

Susanna Maria Ricco

Matthew Baird

David P Mariani

Weijian Cheng

Nitin Jindal

Thomas William Knych

DaRen Drummond

Sherol Chen

The present disclosure provides a detailed description of techniques used in systems, methods, and in computer program products for dynamic aggregate generation and updating for high performance querying of large datasets. Certain embodiments are directed to technological solutions for determining at least one aggregate of selected virtual cube attributes (e.g., measures, dimensions, etc.) describing a virtual multidimensional data model of a subject database, and generating an aggregate table and a set of aggregate metadata for the aggregate. In some embodiments, an aggregate database statement configured to operate on the subject database can be issued to generate the aggregate table and/or aggregate metadata. Further, the aggregate can be dynamically determined responsive to receiving a database statement configured to operate on the virtual multidimensional data model representing the subject database. Also, the aggregate table can comprise one or more partitions in an aggregate view to facilitate aggregate management and/or quality.

Dynamic aggregate generation and updating for high performance querying of large datasets

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a machine-learned object tracking policy. One of the methods includes receiving a current video frame by a user device having a plurality of installed object trackers, wherein each object tracker is configured to perform a different object tracking procedure on the current video frame rent video frame. The current video frame and one or more object tracks previously generated by the one or more object trackers are provided as input to a trained policy engine that implements a reinforcement learning model to generate a particular object tracking plan. A particular object tracking plan is selected based on the output of the reinforcement learning model, and the selected object tracking plan is performed on the current video frame to generate one or more updated object tracks for the current video frame.

Adaptive object tracking policy

A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.

Generating a video segment of an action from a video

Techniques are presented for applying fine-grained client-specific rules to divide (e.g., chunk) data statements to achieve cost reduction and/or failure rate reduction associated with executing the data statements over a subject dataset. Data statements for the subject dataset are received from a client. Statement attributes derived from the data statements are processed with respect to fine-grained rules and/or other client-specific data to determine whether a data statement chunking scheme is to be applied to the data statements. If a data statement chunking scheme is to be applied, further analysis is performed to select a data statement chunking scheme. A set of data operations are generated based at least in part on the selected data statement chunking scheme. The data operations are issued for execution over the subject dataset. The results from the data operations are consolidated in accordance with the selected data statement chunking scheme and returned to the client.

Data statement chunking

A processor determines metadata associated with an audio track. The processor identifies categories that are related to the audio track based on the metadata. The processor determines rankings for the categories that are related to the audio track. The ranking is indicative of a relevance of a particular category to the audio track. The processor performs a query to identify visual media for one or more of ranked categories. The visual media is related to the audio track. The processor generates a visual presentation for the audio track by selecting at least some of the visual media to include in the visual presentation.

Creating a video for an audio file

Techniques are presented for rule-based selection of query engines for performing data operations on a variety of datasets stored in heterogeneous data storage environments. Data statements for a subject dataset are mapped to a logical data structure representation of the subject dataset to formulate a logical plan for the data statements. The data statements are analyzed to derive a set of statement attributes associated with the data statements. Query engine attributes describing the query engines available to query various instances of the subject dataset are accessed. A set of query engine selection rules are evaluated subject to the statement attributes and/or the query engine attributes to dynamically select a target query engine for the data statements. A physical plan structured for the target query engine is generated from the logical plan. The physical plan is executed on the target query engine to perform data operations on the subject dataset.

Query engine selection

A text query from a user may be received. Playlists associated with the text query may be identified. A relevance score may be calculated for each of the playlists based at least in part on a relevance of the corresponding playlist to the text query. Furthermore, content items may be identified where each of the content items is included in at least one of the playlists. For each of the identified content items, one or more playlists that includes the corresponding content item may be identified. A score for each of the content items may be calculated based on the relevance score for each of the playlists that includes the corresponding content item. Furthermore, a new playlist may be generated for the user based on the scores for each of the content items.

Algorithmic radio for arbitrary textual queries

Highlighting device

The user feedback module receives from a user device a selection of a seed media item. The seed media item includes a seed label. The user feedback module further generates a list, the list includes the seed label and a set of related labels based on the seed label. The seed label and each related label include a separate label weight. The user feedback module also identifies multiple media items associated with an associate label. The associate label includes at least one of the seed label or a related label of the first set of related labels. The user feedback module also transmits to the user device a first media item from the multiple media items. The user feedback module adjusts the label weight of the associate label based on a user feedback on the first media item.

Adaptive music and video recommendations

Systems and methods described herein relate to automation of video creation for an associated audio file or musical composition. In particular, a video can be generated for the audio file that includes images and videos that are compelling and contextually relevant to, and technically compatible with, the audio file.

Growing community of inventors

San Jose, CA, United States of America

David A Ross