International Business Machines Corporation

Danish Contractor

Sachindra Joshi

Kuntal Dey

Sreekanth L Kakaraparthy

Vijay A Kumar

Nitendra Rajput

Mukesh Kumar Mohania

Kenney Ng

Seema Nagar

Bikram Sengupta

Sumit Negi

Manjula Golla Hosurmath

Geetha Karna

Gaurav Pandey

Sreekanth Kakaraparthy Lakshmi

Varun Parashar

Swetha Prasad

Luis Alfonso Lastras-Montano

Ashish Verma

Malolan Chetlur

Ying Li

Ajay Gupta

Pankaj Dhoolia

Ramesh Ambat Gopinath

Raghuram Krishnapuram

Chalapathy Venkata Neti

Harshit Kumar

Jatin Ganhotra

Ateret Anaby-Tavor

Dinesh Raghu

Thomas A Hampp-Bahnmueller

Aniya Aggarwal

Nathaniel Mills

Utkarsh Dwivedi

Ross Warren Judd

Dhiraj Madan

Prasanna Chandrasekharan Nair

Nikhil Verma

Vineet Kumar

Methods, systems, and computer program products for context-based response generation are provided herein. A method includes: obtaining conversation logs comprising agent responses matched to contexts and a set of designated responses that are not matched to the contexts; replacing at least a portion of the agent responses with the designated responses to form modified conversation logs; training a first model, using the modified conversation logs, to output a designated response in the set for a given context and a second model, using the historical conversation logs, to output one of the agent responses for a given context; identifying one or more new responses based at least in part on the output of the second machine learning model for a particular one of the contexts; and retraining the first machine learning model based at least in part on the one or more new responses.

Context-based response generation

Digital teaching content ordering includes receiving, by a data processing system, digital teaching content and any corresponding annotations and content heuristic(s) from a teacher or other presenter, the digital teaching content including text and/or image(s). The data processing system monitors student gaze of the digital teaching content during a class and can cognitively skip some of the digital teaching content during the class based on the monitored student gaze and content heuristic(s). The system can also cognitively modify the digital teaching content outside of class based, in part, on the monitoring and the content heuristic(s). A hypergraph of the digital teaching content may also be received, the cognitively skipping being further based on the hypergraph, and the cognitively modifying being further based on a heat map built using the hypergraph and the student gaze.

Dynamicaly updating digital visual content via aggregated feedback

In an approach to creation and execution of dialog shortcuts, responsive to detecting initiation of a dialog, an utterance is received from a user. Whether the utterance contains an objective of the user is determined, where the objective is chosen from a group including create a shortcut, execute the shortcut, modify the shortcut, and delete the shortcut. Responsive to determining that the utterance contains the objective, the objective is implemented.

Dialog shortcuts for interactive agents

Methods, systems, and computer program products for implementing automated communication exchange programs for attended robotic process automation are provided herein. A computer-implemented method includes invoking, during a user communication associated with an attended robotic process automation context, at least one automated communication exchange program in response to at least one user input; determining, using the at least one automated communication exchange program, information directed to the at least one user input; carrying out, using the at least one automated communication exchange program, at least a portion of the user communication subsequent to determining the information directed to the at least one user input; and performing one or more automated actions in connection with automatically carrying out the at least a portion of the user communication.

Automated communication exchange programs for attended robotic process automation

Methods and systems for delivering personalized learning material are disclosed. A method includes providing, by a computer device, current learning material and advance learning material to a plurality of students; monitoring, by the computer device, a reading performance and a complexity of the advance learning material for a student of the plurality of students; determining, by the computer device, a student comprehension score for the student based on the monitoring the reading performance and the complexity of the advance learning material; and providing, by the computer device, additional learning material to the student based on the student comprehension score being above a threshold.

Delivering personalized learning material

Methods, systems, and computer program products for generating dialog system workspaces are provided herein. A computer-implemented method includes obtaining (i) a set of policy documents and (ii) a set of initial questions; identifying at least one of the policy documents in the set of policy documents that is relevant to answering a given one of the initial questions in the set of initial questions; generating, based at least in part on an analysis of said identified policy document, (i) at least one follow-up question to said given initial question and (ii) two or more candidate answers to said at least one follow-up question; generating a dialog tree comprising at least (i) a parent node corresponding to the at least one follow-up question and (ii) child nodes corresponding to the two or more candidate answers; translating the dialog tree into a dialog workspace; and deploying the dialog workspace in an intelligent dialog system.

Generating dialog system workspaces

An embodiment of the invention may include a method, computer program product and computer system for non-linear video navigation. The method, computer program product and computer system may include a computing device that collects source content and source content metadata from a content device. The computing device may extract the metadata from the source content and store the source content and the metadata on a server. The computing device may receive user profile data from a user device. The computing device may map the semantic data of the source content, the metadata, and the user profile data to a knowledge graph. The computing device may create navigational panels for navigating the source content based on the knowledge graph, the navigational panels enabling non-linear navigation of the source content by a user. The computing device may provide the navigational panels to the user device.

Non-linear navigation of videos

Methods, systems, and computer program products for cognitive content mapping and collating are provided herein. A computer-implemented method includes identifying resources relevant to an existing course; partitioning, based on pre-determined partitioning parameters, (i) the existing course into multiple portions and (ii) the resources into multiple portions; detecting content coverage gaps in the existing course by semantically comparing (i) the multiple portions of the existing course with (ii) the multiple portions of the resources; retrieving, based on the detected content coverage gaps, at least one of the multiple portions of the resources; and generating an updated version of the existing course by incorporating the at least one retrieved portion of the resources into the existing course.

Cognitive content mapping and collating

One embodiment provides a method, including: obtaining a plurality of conversational logs; generating a human agent emulator and a user emulator; providing a workspace for a conversational agent, so that an agent designer generates a conversational specification for the conversational agent, wherein the generating a conversational specification comprises: receiving a selection, by the agent designer, of at least one intent for the conversational agent, wherein the receiving a selection is responsive to the conversational agent workspace providing suggestions for intents; providing at least one suggestion for a dialog node that corresponds to the selected at least one intent; and generating a dialog flow for the conversational agent, wherein the generating comprises iteratively receiving, from the agent designer, selection of at least one aspect and receiving at least one selection of the at least one suggestion for dialog nodes; and providing the conversational agent.

Conversational agent generation

Educational content can be presented to a user via a display. Eye movement of the user while the user gazes at the educational content can be monitored. Based, at least in part, on the monitoring the eye movement of the user while the user gazes at the educational content, a time when to present assessment content to the user can be determined. The assessment content can be presented to the user at the determined time.

Presenting assessment content to a user

Price transparency via aggregation of real-time quoted prices is provided. Real-time quoted service price data corresponding to a service application is collected from registered client devices. The real-time quoted service price data corresponding to the service application is aggregated. It is determined whether a price quoted to a client device by the service application is fair based on the aggregated real-time quoted service price data. In response to determining that the price quoted to the client device by the service application is unfair, a graphical input button is provided within a price transparency display on the client device that enables a user of the client device to send a complaint to a service provider corresponding to the service application with a price transparency log.

Method, system, and computer program product for transparency via opt-in aggregation

Audiovisual documentation of source code in an integrated development environment. A computing device initiates a knowledge transfer session for discussion of source code and generation of audiovisual source code documentation explaining segments of source code from a code base. An audiovisual interface containing a segment of code from the code base is displayed within the integrated development environment. Audio during the knowledge transfer session is recorded with a recording device. Code tracking indicators from an optical tracking device operated by a user are received when the user is reviewing and focused on the segment of code. The computing device determines via the code tracking indicators a module of the segment of code under review. Portions of the recorded audio are associated with the determined module of the segment of code to generate audiovisual source code documentation. The knowledge transfer session is terminated.

Audiovisual source code documentation

Embodiments generally relate to improving drawings. In some embodiments, a method includes receiving a drawing from a user, where the drawing includes one or more primary objects. The method further includes recognizing the one or more primary objects in the drawing, and determining properties of the one or more primary objects. The method further includes generating one or more suggestions for improvements to the drawing, where the one or more suggestions include one or more changes to the one or more properties. The method further includes receiving a version selection from the user, and rendering the drawing based on the version selection.

Cognitive drawing assistant

Methods, systems, and computer program products for non-linear, multi-resolution visualization of a graph are provided herein. A computer-implemented method includes generating multiple sub-graphs derived from an input knowledge graph, wherein the input knowledge graph comprises multiple nodes and multiple edges, and wherein each of the generated sub-graphs comprises a distinct level of resolution; processing an input comprising at least one area of user interest on the input knowledge graph; generating a multi-resolution version of the input knowledge graph by combining two or more of the generated sub-graphs, wherein the two or more sub-graphs are selected based on the at least one area of user interest; and outputting the multi-resolution version of the input knowledge graph to the user via an interactive mechanism.

Non-linear, multi-resolution visualization of a graph

A method for dynamically reforming a moveable display surface to deliver physicality to a user is provided. The method generates a physical profile of the user to calibrate the moveable display surface by receiving a measurement of at a hand of the user and estimating a maximum depth of a palm of the hand when folded based on causing a subset of cells of the plurality of moveable cells of the grid to increase in height. At least one image of a plurality of images, objects of the at least one image, and relative positions of objects of the at least one image are received Physicality is delivered to the user by causing the grid of the moveable display surface to render the objects based at least in part on the physical profile and the relative positions.

Growing community of inventors

Gurgaon, India

Danish Contractor