International Business Machines Corporation

Merlyn Mind, Inc.

Xio Research, Inc.

Sharad C Sundararajan

Vijay Ekambaram

Malolan Chetlur

Ashok Pon Kumar Sree Prakash

Vikas V Joshi

Aditya Vempaty

Jonathan Lenchner

Ravindranath Kokku

Christian Makaya

Satya Venkata Nitta

Keith William Grueneberg

Jason L Crawford

Patrick D Watson

Maria Chang

Jae-Wook Ahn

Satya Nitta

Shom Ponoth

Tamer Abuelsaad

Satyanarayana Venkata Nitta

Ruchir Puri

Prasenjit Dey

Ravi Tejwani

Andrew James Sullivan

Mihir Choudhury

Robert C Smith

Robert Hutter

Subhendu Roy

Satyanarayana Nitta

Tengfei Ma

Paul V Haley

Rajkumar Chandrasekaran

Juan Ernesto Penarrieta Cornejo

Helene Alonso

Mohammad Niknazar

Amol Nayate

Javier Villafana

Robert Smith

Latha Ramanan

A component management server computer ('server') and processing methods are disclosed. In some embodiments, the server is programmed to continuously receive input data regarding what is happening in the physical room from one or more input devices. The server is programmed to then detect an utterance of a spoken word from the input data and generate one or more sound metrics based on the input data. Based on the sound metrics as applied to certain criteria, the server is programmed to activate a component, such as an input device, variable, software system, or output device, and cause one or more output devices to execute an action that alerts a user of the activated component. The server can also be programmed to turn on, off, up, or down any of the components based on the activated component.

Automatic adaptation of multi-modal system components

A meeting summarization method, system, and computer program product, include compiling notes from a meeting between a plurality of users and providing a single document that summarizes the meeting based on the compiled notes.

Summarization method for recorded audio

A method comprises receiving from an input device, a capture of user action as an initial command; interpreting the initial command into an interpreted command; generating a first set of modified commands that are based on the interpreted command, including: a first modified command that has a phonetic similarity to the interpreted command within a certain threshold, and a second modified command that is semantically related to an earlier command; transmitting, to an output device, the first set of modified commands; receiving a response to a group of commands including the first set of modified commands; recording an identifier of an input device from which the response was received and a type of the response in a log; when the response includes acknowledging a specific command of the group of commands as an accepted command, executing, the accepted command; otherwise, generating a second set of modified commands.

Multimodal intent entity resolver

A data management server computer ('server') is disclosed. The server receives action data associated with one or more users identifying a plurality of actions performed through one or more computer devices in a multi-modal networked environment, identifies useful sequences of actions as compound actions, and generates deep links representing the compound actions as UI elements which when invoked cause execution of the represented compound actions.

Generating compound action links in a multi-modal networked environment

Interpretation of user commands is accelerated through digital user interfaces of various modalities, including generation and presentation of command modifications for rapid correction of incomplete or erroneous user commands. An embodiment detects whether the interpreted command is accurate and, if inaccurate, precisely what was the intended command or, at least, what suggested modification to the interpreted command would be sufficient to match the intent of the user. Disambiguation occurs that entails multiple recommendation generators proposing modified commands that may more accurately reflect the intent of the user. The user may provide a response that is either a confirmation of which one of several modified commands that were automatically proposed does the user intend or a correction that computer device may use to filter or replace currently offered modified commands to generate improved modified commands. By iterative refinement, the user and computer device may quickly agree on an accurate command that the computer device should execute.

A meeting summarization method, system, and computer program product, include capturing notes of a user including a time stamp from the user associated with a meeting, synchronizing an agenda of the meeting and the notes of the user based on a correlation between a time stamp of a topic on the agenda and a time stamp of the notes of the user, and analyzing the synchronized topic and the notes to determine highlights of the meeting based on a co-occurrence of the time stamp of the notes of the user and the time stamp of the topic on the agenda.

A device management server computer ('server') and processing methods are disclosed. In some embodiments, the server is programmed to manage a plurality of input devices and output devices in a physical room. The server is programmed to analyze media data capturing actions performed by a user in real time as a participant in the physical room, determine how the user would like to connect at least one of the input devices and one of the output devices from the analysis, and enable the connection. The sever is programmed to interpret the actions and derive commands for connecting two or more devices based on predetermined data regarding the input devices and output devices and rules for referring to and connecting these devices.

Managing connections of input and output devices in a physical room

Systems, methods, and computer program products to perform an operation comprising receiving text input via a chat interface of a tutor application, identifying, by at least one classifier applied to the text input, a concept in the text input, mapping the concept in the text input to at least one of a visual action and a first visual object, generating, based on a first machine learning (ML) model, a first program code statement corresponding to the at least one of the visual action and the first visual object, and executing the first program code statement to modify a visualization interface of the tutor application based on the text input received via the chat interface.

Enhanced visual dialog system for intelligent tutors

An exploration-based career guidance system is disclosed. The career guidance system receives an assessment regarding a candidate and identifies a first set of roles for the candidate based on the assessment. The system receives a selection of a role from among the first set of roles and provides a simulated experience of the selected role and receives a set of interaction data from the simulated experience. The system adjusts the assessment regarding the candidate based on the set of interaction data and identifies a second, different set of roles for the candidate based on the adjusted assessment.

Exploration based cognitive career guidance system

A method and system of providing education content to a student is provided. A topic to be taught to a student is received. A user model of the student is identified. An electronic content model for the topic is determined. One or more presentation templates are identified based on the electronic content model. A concept map is determined based on the one or more presentation templates. A presentation template is selected from the one or more presentation templates. A segment of an educational content of the topic is provided to a user device of the student, based on the selected presentation template.

Adaptive presentation of educational content via templates

Method and apparatus for generating natural language observations using sequence-to-sequence models are provided. The method includes receiving a first electronic document and dynamically generating, without requiring user intervention, a first natural language observation corresponding to a first portion of the first electronic document by processing the first portion of the first electronic document using a first sequence-to-sequence model. A second natural language observation is received for the first portion of the first electronic document, and the generated first natural language observation and the authoritative natural language observation are provided. The method further includes receiving an evaluation of the first natural language observation and the second natural language observation, and refining the first sequence-to-sequence model based on the evaluation of the first natural language observation and second natural language observation.

Distributed system for evaluation and feedback of digital text-based content

A device management server computer ('server') is programmed to manage a plurality of input devices and output devices in a physical room. The server is programmed to analyze media data capturing actions performed by a user in real time as a participant in the physical room, determine how the user would like to connect at least one of the input devices and one of the output devices from the analysis, and enable the connection. The sever is programmed to interpret the actions and derive commands for connecting two or more devices based on predetermined data regarding the input devices and output devices and rules for referring to and connecting these devices.

An embodiment includes a method for use in presenting a plurality of concepts to a plurality of students. The method includes developing a first statistical model of one or more modalities effective for teaching at least a given concept of the plurality of concepts across the plurality of students. The method also includes developing a second statistical model of one or more modalities effective for learning by at least a given student of the plurality of students across the plurality of concepts. The method further includes combining the first and second models to determine one or more modalities for presenting at least the given concept to at least the given student; and presenting at least the given concept to at least the given student using the determined one or more modalities.

Personalized tutoring with automatic matching of content-modality and learner-preferences

Techniques for conditional presentation of auxiliary information are provided. In one example, a computer-implemented method comprises determining, by a device operatively coupled to a processor, feedback information for a user in response to a media presentation, wherein the feedback information is indicative of a mental state of the user during presentation of the media presentation. The computer-implemented method can further comprise determining content of the media presentation associated with the mental state of the user, and determining auxiliary information about the content based on the mental state of the user. The computer-implemented method can further comprise providing, by the device, the content to a user device during the presentation of the media presentation and for rendering at the user device in association with presentation of the content.

Growing community of inventors

Weehawken, NJ, United States of America

Sharad C Sundararajan