Mobile Iron, Inc.

Amazon Technologies, Inc.

Ajay Kumar Mishra

Suresh Kumar Batchu

Ojas Udayan Rege

Jesse Wagner Lindeman

Thomas Edward Wagner

Robert Bates Tinker

Daniel Bibireata

Rashmi Gangadharaiah

Oleg Rybakov

Laxmikantha Reddy Ponnuru

Avinash Aghoram Ravichandran

Roger Scott Jenke

Meghana Puvvadi

Wei Zhang

Anubhav Gupta

Techniques for generating conversational training data are described. In some instances, a request to generate conversational training data for a goal-oriented conversation model is received, a transitional graph of intents is traversed to generate a conversation template for each intent of the transitional graph, each intent being a task to fulfill a request and comprising one or more slot to be filled by a user of the bot machine learning model, the conversation template including a path including at least one placeholder for an utterance or a slot level utterance, and at least utterances from one or more dictionaries are sampled to fill in the placeholders for the utterances of the path to generate conversational training data.

Goal-oriented conversational training data generation

A computing device can be configured to analyze information, such as frames captured in a video by a camera in the computing device, to determine locations of objects in captured frames using a scene-based tracking approach without individually having to track the identified objects across the captured frames. The computing device can track scenes, a global planar surface, across newly captured frames and the changes to (or transformation) the scene can be used to determine updated locations for objects that were identified in previously captured frames. Changes to the scene between frames can be measured using various techniques for estimating homographies. An updated location for the particular object in the currently captured frame can be determined by adjusting the location of the object, as determined in the previously captured frame, with respect to the transformation of the scene between the previously captured frame and the currently captured frame.

Approaches for scene-based object tracking

In particular implementations, a mobile device management system allows network administrators to control the distribution and publication of applications to mobile device users in an enterprise network. A user profile is accessed to determine a user attribute. A catalog of applications is filtered based at least in part on the user attribute and an enterprise application availability policy to determine a set of applications to be returned and provided via an enterprise mobile device application management interface.

Management of mobile applications

In particular implementations, a mobile device management system allows network administrators to control the distribution and publication of applications to mobile device users in an enterprise network.

In various embodiments, a method is described that includes registering a mobile device with an enterprise by storing registration data for the mobile device in a device management database; designating one or more group designations for the mobile device; storing the one or more group designations in the device management database; determining one or more policies for the mobile device based at least in part on the one or more group designations; and selectively taking action on selected data from the mobile device in the device management database based on the one or more policies.

Selective management of mobile device data in an enterprise environment

Growing community of inventors

Bellevue, WA, United States of America

Ajay Kumar Mishra