International Business Machines Corporation

Nuance Communications, Inc.

David M Lubensky

Xiang Yang Li

Wei Liu

Justin David Weisz

Marco Pistoia

Blaine H Dolph

Cheng Wu

Osamuyimen Stewart

Mal Pattiarachi

Ea-Ee Jan

Nitendra Rajput

Juan Manuel Huerta

Andrzej Sakrajda

Baiju Dhirajlal Mandalia

Hani Talal Jamjoom

Carl Kraenzel

Hong-Kwang Jeff Kuo

Justin Gregory Manweiler

Ching-Yung Lin

Vaibhava Goel

Stephen Peter Wood

Jui-Hsin Lai

Kyungmin Lee

Zhong-Hua Wang

Joyram Chakraborty

Dongsuk Yuk

Marcus D Roy

Omer Tripp

Stephane Herman Maes

David Nahamoo

Wen Liu

Yong Qin

Sasha P Caskey

John J Ponzo

Paul Christesten Castro

Joseph W Ligman

Lalit R Bahl

Jiri Navratil

Pietro Ferrara

Anni Rosa Coden

Andrew Aaron

Mukund Padmanabhan

Umut Topkara

Salim Estephan Roukos

Charles Francis Wiecha

Hanghang Tong

Xiang Li

Ruhi Sarikaya

Katherine Vogt

Thiruvilwamalai Venkatraman Raman

Subrata Kumar Das

Danning Jiang

Raymond L Co

Chaitanya J K Ekanadham

Danai Koutra

Sasha Porto Caskey

Systems, computer-implemented methods, and computer program products that can facilitate a classical and quantum ensemble artificial intelligence model are described. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an ensemble component that generates an ensemble artificial intelligence model comprising a classical artificial intelligence model and a quantum artificial intelligence model. The computer executable components can further comprise a score component that computes probability scores of a dataset based on the ensemble artificial intelligence model.

Boosting quantum artificial intelligence models

From a hardware sensor at a first time, sensor data comprising a first sample and a second sample is received. The sensor data is modified to create new data, wherein a first data point of the new data corresponds to the first sample, a second data point of the new data corresponds to the second sample, and wherein the first data point and the second data point are arranged differently from the first sample and the second sample. The hardware sensor is emulated by sending, to a consumer of hardware sensor data at a second time, the new data instead of the sensor data.

Sensor data manipulation using emulation

A method, system and computer readable program are disclosed for managing data in a computing network. In an embodiment, the invention provides a method comprising obtaining specified data from a database in the computing network, aggregating the specified data in a defined data structure stored in the computing network, and specifying in the data structure properties over the data aggregated in the data structure. In an embodiment, a plurality of services in the computing network use the data in the data structure in accordance with the properties specified in the data structure. In an embodiment, one or more of the services modifies one or more of the properties specified in the data structure based on a transformation by the one or more of the services of the data aggregated in the data structure.

Data-centric approach to analysis

A database comprises historical information of a user's response to previous notifications. The database is accessed to determine a time at which to provide a (new) notification to the user, utilizing at least: a) current user activity status (e.g., determined from measurement information collected from one or more personal devices and/or user calendar events; b) time/day; and c) context information about the notification (e.g., geo-location, indoors/outdoors) including notification type (e.g., calendar entry, email, IM). The user gets the notification via a portable device at the determined time. A machine learning model can select the determined time by discriminating features of the previous notifications for which the user immediately attended versus those that were deferred and/or ignored. Content of the notification can also be altered in view of such discriminating features so as to increase a likelihood the user will immediately attend to the provided notification.

Predicting user attentiveness to electronic notifications

A workflow extraction method, system, and computer program product include analyzing, for each of the design screens, a relatability of one design screen to a previously analyzed design screen in the database and generating a tag that represents a workflow and creating a database linking the tag to a sequence of design screens from a transition graph that details how to move from one of the design screens to another.

Extracting mobile application workflow from design files

Techniques are disclosed for generating a voice user interface (VUI) modality within an application that includes graphical user interface (GUI) screens. A GUI screen parser analyzes the GUI screens to determine the various navigational GUI screen paths that are associated with edge objects within multiple GUI screens. Some edge objects are identified as select objects or prompt objects. A natural language processing system generates a select object synonym data structure and a prompt object data structure that may be utilized by a VUI generator to generate VUI data structures that give the application VUI modality.

Automated voice enablement of applications

Techniques for optimizing training data within voice user interface (VUI) of an application under development are disclosed. A VUI feedback module synthesizes human speech of a training phrase. This phrase is presented upon a speaker which is simultaneously captured upon a microphone. A speech to text framework converts the synthesized training phrase into text (textualized training phrase). The VUI feedback module compares the textualized training phrase to the actual training phrase and generates a speech training data structure that identifies similarities or dissimilarities between the textualized training phrase and the actual training phrase. This data structure may be utilized by an application developer computing system to identify training data that is most venerable to misinterpretation when a user interacts with the VUI. The VUI may subsequently be adjusted to account for the vulnerabilities to improve operations or user experience of the VUI.

Training data optimization in a service computing system for voice enablement of applications

Training data optimization for voice enablement of applications

Techniques are disclosed for identifying which graphical user interface (GUI) screens of an application that is under development would benefit from a voice user interface (VUI). A GUI screen parser analyzes to determine the GUI objects within GUI screens of the application. The parser assigns a speechability score to each analyzed GUI screen. Those GUI screens that have a higher speechability score than a predetermined speechability threshold are indicated as GUI screens that would benefit (e.g., the user experience in interacting with those GUI screens would increase, the number of GUI screens displayed would be reduced, or the like) with the addition of a VUI.

Prospective voice user interface modality identification

A mobile application workflow extraction method, system, and computer program product include extracting functional elements from a design file to create a database of design screens, generating a flow graph of the design screens and the functional elements in the design file, creating a transition graph that details how to move from each of the design screens to another, and analyzing, for each of the design screens, a relatability of each design screen to a previously analyzed design screen in the database and generating a tag that represents a workflow.

A method, system, and computer product for detecting an oral temperature for a human include capturing a thermal image for a human using a camera having a thermal image sensor, detecting a face region of the human from the thermal image, detecting a mouth region on the face region, detecting an open mouth region on the mouth region, detecting a degree of mouth openness on the detected open mouth region, determining that the degree of mouth openness meets a predetermined criterion, and detecting the oral temperature, responsive to determining that the degree of mouth openness meets the predetermined criterion.

Detecting oral temperature using thermal camera

Controlling drones and vehicles in package delivery, in one aspect, may include routing a delivery vehicle loaded with packages to a dropoff location based on executing on a hardware processor a spatial clustering of package destinations. A set of drones may be dispatched. A drone-to-package assignment is determined for the drones and the packages in the delivery vehicle. The drone is controlled to travel from the vehicle's dropoff location to transport the assigned package to a destination point and return to the dropoff location to meet the vehicle. The delivery vehicle may be alerted to speed up or slow down to meet the drone at the return location, for example, without the delivery vehicle having to stop and wait at the dropoff location while the drone is making its delivery.

Operating a plurality of drones and trucks in package delivery

Growing community of inventors

Danbury, CT, United States of America

David M Lubensky