Western Digital Technologies, Inc.

Ayla Networks, Inc.

Anirudha Deglurkar

Sudha Sundaresan

Sebastian Maurice

Vadym Byelov

Kenneth Chan Choy

Ronald Louis Maeder

Satyanarayana Ravipati

A system receives a plurality of data streams, including a plurality of data points, associated with properties of a device. The system generates, for each data stream, a data set that includes at least a specified number of data points over a prior time period. The system identifies a first data stream that represents a property to be predicted for a future time period. The system generates a joined data set that includes a subset of the data sets not including a first data set of the first data stream. The joined data set and the first data set are inputted into a trained machine learning model, trained to output a predicted value of the first property for the future time period. The predicted value of the first property indicates an anomaly, and a resolution action for preventing the anomaly from occurring at the future time period is identified.

Over-the-air machine learning

In embodiments a computing device receives a selection of a device template associated with a physical device. The computing device receives a selection of a third-party device type associated with a third-party system. The computing device determines a device rule template associated with the device type, the device rule template comprising a first mapping between one or more commands and one or more additional device properties in the device type. The computing device determines a second mapping between the one or more additional device properties and one or more device properties in the device template. The computing device generates an adapter template comprising the first mapping between the one or more commands and the one or more additional device properties and the second mapping between the one or more additional device properties and the one or more device properties.

Third-party application control of devices in an IoT platform

Systems and methods are disclosed for editing metadata for data objects on a data storage device, which may be configured to identify data objects that have been modified and may be associated with storage locations of a file system. The data storage device may also be configured determine whether a first period of time has elapsed and may further be configured to determine whether a second period of time has elapsed or whether a threshold number of data objects in the file system have been modified in response to a first determination that the first time period has elapsed. The data storage device may further be configured to edit a set of metadata for a set of data objects in response to a second determination that the second period of time has elapsed or the threshold number of data objects in the file system have been modified.

Managing and accessing data storage systems

The embodiments relate to transcoding, cataloging, and extracting metadata about files stored in a storage device. In one embodiment, a crawler runs on the storage device and maintains a database that is stored in the volume with the data that has been cataloged by the crawler. The crawler may discover files of any type and extract associated metadata about the files. The crawler can extract metadata about client interaction with various files, such as edits, play counts, etc. The crawler may discover files of any type and extract associated metadata about the files automatically during a scan or at the request of a client. In one embodiment, the crawler may be responsive to file system events that indicate changes to the file system, such as additions, deletions, or other types of changes. In addition, the crawler may synchronize the database with the file system so that they indicated the same state for a particular file. Furthermore, the crawler may provide notifications to various entities regarding the state of a file.

Growing community of inventors

San Jose, CA, United States of America

Anirudha Deglurkar